PSY:2811 (Research Methods and Data Analysis in Psych I) Final Exam
You test your hypothesis that greater time outdoors is related to less anxiety. Your correlation is r = -.40, p = .08. Your conclusion should be to ___. A. Report your correlation as statistically significant B. Fail to reject the null hypothesis C. Reject the null hypothesis D. Support the alternative hypothesis
Fail to reject the null hypothesis
True or false: "Multivariate correlational designs are often used when it is impossible to conduct an experiment." A. True B. False
True
What are some examples of frequency claim headlines?
1. "39% of Teens Admit to Texting While Driving" 2. "Screen Time For Kids Under 2 More Than Doubles" 3. "Most Students Don't Know When News is Fake"
What percentage of scores are within 1 SD from the mean?
68%
What proportion of a normal distribution is within 1 standard deviation of the mean? A. 99% B. 50% C. 95% D. 68%
68%
Weight of the Evidence
A conclusion drawn from reviewing scientific literature and considering the proportion of studies that are consistent with a theory
Cronbach's Alpha
A correlation-based statistic that measures a scale's internal reliability; also called coefficient alpha
Scientific Journal
A monthly or quarterly periodical containing peer-reviewed articles on a specific academic discipline or subdiscipline, written for a scholarly audience
Experiment
A study in which at least one variable is manipulated and another is measured
What should occur with good internal reliability?
A study participant will give a consistent pattern of answers, no matter how the researchers phrase the question
Use the following data to calculate the z-score: Score = 6.99, Mean = 5.35, SD = 1.131
(6.99 — 5.35)/1.131 = 1.45 Z-score = 1.45
Negative Skew Box-and-Whisker Plot
(Q3 — Q2) < (Q2 — Q1)
Positive Skew Box-and-Whisker Plot
(Q3 — Q2) > (Q2 — Q1)
Given the equation of the linear regression line, Y' = -.127(x) + 9.1024, how many behavioral problems per class period could we expect if we give students 30 minutes of recess?
-.127(30) + 9.1024 = 5.29 behavioral problems
A z-score of ___ always means 1 SD above the mean
1
What is the calculation for statistical power?
1 — Probability of type II error
What are the four main types of validity?
1. Construct 2. Statistical 3. External 4. Internal
What types of validities fall under construct validity?
1. Face validity 2. Content validity 3. Criterion validity (concurrent/predictive) 4. Convergent validity 5. Discriminant validity
How are mean and standard deviation used together?
1. Mean and SD values can be used to predict the shape of population distribution 2. The shape is used to predict the target population for the given variable
What are the threats to valid observations?
1. Observer bias 2. Observer effects 3. Reactivity
Debriefing (Standard 8.08)
1. Researchers must debrief participants if they have been involved in a deception study 2. In a debriefing session, the researchers describe the nature of the deception and explain why it was necessary for the study 3. Nondeceptive studies may include a debriefing session too
What is Pearson's correlation coefficient r?
1. r is a unitless measurement 2. r is on the same scale, no matter what we are correlating 3. r is an effect size for the strength of the relationship 4. Effect sizes are comparable across different variables and studies
What percentage of scores are within 3 SDs from the mean?
99.7%
Mean
A measure of central tendency computed from the sum of all the scores in a set of data, divided by the total number of scores (average)
Cluster Sample
A probability sampling technique in which clusters of participants within the population of interest are selected at random, followed by data collection from all individuals in each cluster Sample from pre-existing subgroups of target population Subgroups that are sampled are chosen randomly from all possible subgroups Ex: Target population is adults between 60-80 years, randomly choose 5 countries in the state and sample all individuals in those countries in the target population Ex: Target population is new moms, randomly pick 10 hospitals to obtain birth records from and sample all individuals from the records
Multi-Stage Cluster Sample
A probability sampling technique involving at least two stages where a random sample of clusters is followed by a random sample of people within the selected clusters Sample from pre-existing subgroups of target population Subgroups sampled are chosen randomly from all possible subgroups Then, sample randomly within each subgroup
Concurrent Validity
Association of measure with a measure of a related concept at same point in time expected to be strong
What does greater deviation from the mean indicate?
Greater deviation from the mean indicates greater spread of scores (more variability)
___ testing involves testing a prediction against an alternative possibility (falsification)
Hypothesis
Dependent Variable (DV)
In an experiment, the variable that is measured and dependent on the values of other variables (particularly the independent variable); DV values are compared for different levels of the IV
When examining the statistical validity of a frequency claim, one should look for the ___ A. Strength of the association B. How representative the sample was C. Margin of error of the estimate D. How well the research measured the concept they hoped to measure E. The probability that the researcher missed a true relationship
Margin of error of the estimate
What is the calculation for the range?
Maximum value — minimum value
A researcher is curious about how different types of candy impact a child's impulsivity. He divides children into groups: one group receives snickers bars, and the other receives hard candies. He then measures how quickly the children reach for the candy. What kind of variable is reaching time? A. Measured B. Manipulated C. Constant
Measured
What kind of variable would behavioral problems be considered? A. Measured B. Manipulated C. Constant
Measured
What kind of variable would sleep be considered? A. Measured B. Manipulated C. Constant
Measured
You would like to study whether people eat more when they distract themselves with their phone while eating. You decide to randomly choose five fast food restaurants where you'll observe the amount ordered, what someone does while eating, and how much they ate. Your method of observation is best described as ___. A. Participant B. Controlled C. Naturalistic D. Self-report
Naturalistic
How can the skew of the following frequency histogram be described (left/right and positive/negative)?
Negatively (left) skewed
Can psychological science only depend on theories and use logic or reasoning to develop new theories?
No, logic and reasoning are not enough because they rely on assumptions, which needs data to support; observations and data are crucial to psychological science
Naturalistic Observation
Observation in the "wild"
Participant Observation
Observation in which the experimenter interacts with participant
Undue Influence
Offering an incentive that is too attractive to refuse, such as a large amount of money in exchange for participating
Correlations can be drastically impacted by ___
Outliers
Observer Effects
Participants change behavior to match observers' expectations
What shape would the distribution for this data have: Mean = 8.972, Median = 7.000, Mode = 10.0? A. Uniform B. Symmetrical C. Negatively skewed D. Positively skewed
Positively skewed Median < mean
What measurement scale is the minutes of vigorous physical activity per week? A. Nominal B. Ordinal C. Interval D. Ratio
Ratio
Data-Driven Research
Reasoning from the data to the general theory
Translational Research
Research that uses knowledge derived from basic research to develop and test solutions to real-world problems Ex: Biochemistry of cell membranes can be translated into a new drug for schizophrenia
Basic Research
Research whose goal is to enhance the general body of knowledge, without regard for direct application to practical problems Ex: Researching the capacity of human memory
Which variable would we want to manipulate to turn the following association claim into a causal claim: A researcher is interested in whether children that sleep less exhibit more behavioral problems in school. They survey parents about their children's sleep habits and survey teachers about the behavioral conduct of those children. They find that children who sleep less have greater behavioral problems. A. Sleep B. Behavioral problems
Sleep
Negative (Left) Skewed
Tail is on the left and peak is on the right
Content Validity
The extent to which a measure captures all parts of a defined construct Does the measure capture all parts of the construct?
Informed Consent
The right of research participants to learn about a research project, know its risks and benefits, and decide whether to participate
What is the references section of an empirical journal article?
The section that contains a full bibliographic listing of all of the sources the authors cited in writing their article
What is the results section of an empirical journal article?
The section that describes the quantitative and qualitative results of the study, including the statistical tests that were used to analyze the data; includes tables and figures that summarize key results
Which of the following is not a condition to establish causation? A. The study is an observational study B. Variables are correlated C. Cause comes before the effect D. There are no other variables to explain the effect
The study is an observational study
How is a good theory parsimonious?
The theory should be made simple without compromising the ability to explain data
Deception
The withholding of some details of a study from participants (deception through omission) or the act of actively lying to them (deception through commission)
What is the purpose of cumulative frequency tables?
Useful for counting scores below or above a threshold value Ex: How many people spend less than $50? Ex: How many people spend between $50 and $174?
Which one is the correct interpretation? A. 95% of the apples in Harry's sample weigh between 147 and 151 B. There is a 95% chance that the mean weight of all apples in the population lies between 147 and 151 C. We can be 95% certain that the mean weight of all apples in the population lies between 147 and 151
We can be 95% certain that the mean weight of all apples in the population lies between 147 and 151
The ___ of confidence intervals gives a probable window for the population parameter
Width
Z-Score Logarithm
z = log(1 + r/1 — r)*√(N — 3) r = Pearson's r N = Sample size
Which r value represents the strongest correlation? A. 0.42 B. 0.75 C. 0.28 D. -0.90
-0.90
Which of the following r values indicate the strongest correlation? A. 0.89 B. 0.45 C. -0.93 D. -0.32
-0.93
What are some examples of causal claim headlines?
1. "Pretending to Be Batman Helps Kids Stay on Task" 2. "To Appear More Intimidating, Just Tilt Your Head Down, Study Suggests" 3. "Family Meals Curb Teen Eating Disorders"
What are some examples of association claim headlines?
1. "Speech Delays Could Be Linked to Mobile Devices" 2. "Girls Are More Likely to Be Compulsive Texters" 3. "Study Links Coffee Consumption to Lower Depression in Women"
What are the components of an empirical journal article?
1. Abstract 2. Introduction 3. Method 4. Results 5. Discussion 6. References
What is useful about r being unitless?
1. Allows us to compare correlations across measures 2. Prevents us from using r to make specific predictions about the variables with their unit of measure
What are the two types of participant variability?
1. Between-subject Ex: Students will score differently from each other on a self-report measure of extraversion Ex: Quarterbacks in the Big Ten will all have a different level of average pre-game anxiety 2. Within-subject Ex: The same student may fluctuate slightly in how extraverted they feel they are throughout the year Ex: The same quarterback will fluctuate in their pre-game anxiety across games in the season
How can betas be compared?
1. Can be helpful to report both 2. Raw units may be more interpretable (ex: # of cigarettes, # of steps a day to reduce risk of death) 3. Standardized units may help compare relative strength of relationship of independent variables with the dependent variable (ex: which is a stronger predictor?)
What are the types of biased samples?
1. Convenience 2. Purposive 3. Snowball 4. Self-selected
What problems might arise when trying to establish causation?
1. Correlational studies do not enable us to establish causation 2. Cause comes before the effect 3. Third variable
What are the rules for finding a proportion for a given z-score?
1. For positive z-score and proportion above z, use column C 2. For positive z-score and proportion below z, use column B + 0.5 or 1 — column C 3. For negative z-score and proportion above z, use column B + 0.5 or 1 — column C 4. For negative z-score and proportion below z, use column C
Why might forced choice questions be used?
1. Forced choice questions provide a few possible categories of responses 2. Coding is straightforward and analysis is simpler 3. Richness may be lost (disadvantage) Ex: What if no options are appropriate for a participant? Ex: What if a participant is between categories?
What are invalid ways to affirm the consequent?
1. If theory correct (P), then predicted data (Q); predicted data (Q), therefore, theory is correct (P) - Invalid because there may be other reasons to cause Q Ex: If it rains, then it is wet; it is wet, therefore, it rained 2. If theory correct (P), then predicted data (Q); get the predicted data (Q), therefore, theory is correct (P) - Invalid because all data needs to be tested; this is why data cannot prove theory 3. If theory correct (P), then predicted data (Q); did not get the predicted data (Q), therefore, theory is not correct (not P) - Invalid because all possible Qs need to be invalidated Ex: If it snows, then it is wet or snowy; it is not wet, therefore, it does not snow
Informed Consent (Standard 8.02)
1. Participants are informed of the purpose of research, the right to decline and consequences of declining, risks and benefits, confidentiality, incentives for participating, and contact information 2. Informed consent is usually obtained by providing a written document that outlines the procedures, risks, and benefits of the research, including a statement about any treatments that are experimental
What are self-reports not good at measuring?
1. Precise analysis of behavior 2. What may actually be influencing their behavior 3. When self-report is not possible for a population (infants)
What are the two types of measurement variability (error)?
1. Random Ex: Children are being measured on how long they take to complete a puzzle, and the experimenter must press "start" and "stop" on the timer; sometimes the experimenter will be a little early and sometimes a little late, and the timer itself will sometimes round up or down when going from millisecond to seconds 2. Systematic Ex: The timer used has a faulty second hand that is consistently 20 milliseconds faster than it should be for every measurement
What is the purpose of hypothesis testing?
1. Seek to answer a question about population parameters 2. Test a question by collecting data from a sample
What is the difference between self-report and observation?
1. Self-reports rely on participants reflecting on their thoughts, feelings, or behaviors 2. Observation records actual behavior 3. Both forms of data collection have challenges for construct validity
What can be determined from a histogram?
1. Shape of distribution 2. Most common values for each variable 3. The variability of values for each variable
What are the qualities of a good theory?
1. Supported by data 2. Falsifiable 3. Parsimonious
What are the four norms introduced by Robert Merton that explain how scientists should act?
1. Universalism 2. Communality 3. Disinterestedness 4. Organized skepticism
When are population SDs used vs. sample SDs?
1. Use sample SDs when measuring from a sample to infer about a larger population 2. Use population SD if the true population mean (μ) can be measured 3. Typically, sample SDs (s) are used
What do histograms need to have?
1. X-axis has all possible values (bins from frequency table) 2. Y-axis reflects frequency (raw count or relative using proportion or percentage) 3. Increment of values on the y-axis should be equal-sized 4. Bins should be equal-sized, exclusive and without gaps, and exhaustive of all possible scores
Suppose X has a normal distribution with a mean of 10 and a standard deviation of 5. Between what values of X do 68% of the values lie? A. 0 and 20 B. 5 and 15 C. 7.5 and 12.5 D. 3.2 and 16.8
5 and 15 Calculation: 68% = +1 SD and -1 SD (10 — 5) = 5 (10 + 5) = 15
What proportion of a normal distribution is within 2 standard deviations of the mean? A. 95% B. 50% C. 5% D. 68%
95%
Conceptual Definition
A careful, theoretical definition of the construct
Probability Sample
A category name for random sampling techniques in which a sample is drawn from a population of interest so each member has an equal and known chance of being included in the sample Based on probability sampling; also called random sampling Every member of the population of interest has an equal chance of being selected for the sample
Association Claims
A claim about two variables, in which the value (level) of one variable is said to vary systematically with the value of another variable What types of things happen together?
Causal Claims
A claim arguing that a specific change in one variable is responsible for influencing the value of another variable What causes something to happen?
Standard Deviation (SD)
A computation that captures how far (on average) each score in a data set is from the mean
Strength of Association
A description of an association indicating how closely the data points in a scatterplot cluster along a line of best fit drawn through them
Falsifiability
A feature of a scientific theory in which it is possible to collect data that will indicate that the theory is wrong
Box-and-Whisker Plot
A graph of IQR and range, which helps visualize variability and skew
Score Bin
A grouped frequency table that combines nearby items that represent a range of values
Taking the mean of the raw deviation scores for a set of data gives you ___. A. The standard deviation B. A mean of zero C. The mean absolute deviation D. A measure of the range of the data
A mean of zero
Known-Groups Paradigm
A method for establishing criterion validity, in which a researcher tests two or more groups who are known to differ on the variable of interest, to ensure that they score differently on a measure of that variable
Which of the following would require us to use median instead of mean? A. Bell curve-shaped histogram B. A positively skewed histogram C. Normal distributions but with high variability D. When your variables are nominal
A positively skewed histogram
Self-Correcting
A process in which scientists make their research available for peer review, replication, and critique, with the goal of identifying and correcting errors in the research
Evidence-Based Treatments
A psychotherapy technique whose effectiveness has been supported by empirical research
Interval Scale
A quantitative measurement scale that has no "true zero", and in which the numerals represent equal intervals (distances) between levels
Anonymous Study
A research study in which identifying information is not collected, thereby completely protecting the identity of participants
Likert Scales (Likert-Type Scales)
A scale that provides a range of forced choice responses that are ratings
Empirical Journal Articles
A scholarly article that reports the results of a research study for the first time; contains details about the study's method, the statistical tests used, and the results of the study
Outlier
A score that stands out as either much higher or much lower than most of the other scores in a sample
Data
A set of observations representing the values of some variable, collected from one or more research studies
Descriptive Statistics
A set of statistics used to organize and summarize the properties of a set of data
The Belmont Report
A short formal document that was produced following the series of ethics violations of the Tuskegee Syphilis Study (1932-1972) and outlines three main principles for guiding ethical decision-making
Correlation Coefficient r
A single number, ranging from -1.0 to 1.0, that indicates the strength and direction of an association between two variables
Interrogating Information
A skill that involves asking the right questions and evaluating studies on the basis of their answers
Third Variable
A variable that represents a plausible alternative explanation for an existing correlation between two variables May imply that the existing correlation is spurious (meaningless) because the two variables are not directly related, meaning that manipulating the independent variable would have no effect on the dependent variable
Categorical (Nominal) Variables
A variable whose levels are categories
Principle of Justice
An ethical principle calling for a fair balance between the kinds of people who participate in research and the kinds of people who benefit from it 1. Fair distribution of costs and benefits to all potential participants 2. Justify your subject selection
Construct Validity
An indication of how well a variable was measured or manipulated in a study; the extent to which the operational variables in a study are a good approximation of the conceptual variables Is the operational definition appropriate?
Population Parameter
Any summary number that describes characteristics of the entire population; a fixed quantity or statistical measure that is used as the value of a variable in some general distribution or frequency function to make it descriptive of that population
Sample (Descriptive) Statistic
Any summary number that describes the sample
Percentile
Area under the curve or the proportion less than x
Which of the following is a frequency claim? A. Making children gesture bring out implicit knowledge and leads to learning B. Between 5% and 10% of the population have dyslexia C. Physically fit children do better at math D. Couples who experience parental interference in their love relationship report intensified feelings of romantic love
Between 5% and 10% of the population have dyslexia
Between-Subject Variability
Between different subjects; people differ from each other
Double-Blind Design
Both researchers and the participants are unaware of the study hypotheses Minimizes observer bias and observer effects
What type of graph should be used if only DV is interval or ratio?
Box plot
What type of claim is this headline: "Scientists Reveal Why Forest Bathing or Going to the Beach Boosts Our Wellbeing"? A. Frequency B. Association C. Causal
Causal
Standardized Beta
Change in the dependent variable, in standard deviations, per standard deviation change in the predictor
The cornerstone of psychology as an empirical science is ___ A. Developing theories that support any possible outcome B. Collecting data without any guiding theory C. Developing theories that depend on good logic D. Collecting data to test a prediction based on theory
Collecting data to test a prediction based on theory
In a regression equation, your b (beta/slope) is 2, and your a (intercept) is 1. How would we state the b in words? A. X and Y are related B. Every 2 units increase in X corresponds to 1 unit increase in Y C. Every 1 unit increase in X corresponds with a 1 unit increase in y D. Every 1 unit increase in X corresponds with a 2 unit increase in y
Every 1 unit increase in X corresponds with a 2 unit increase in y
For a class project, you collect data on UIowa students' screen-time habits. How would you summarize the data on the number of hours students spend watching TV? A. Median B. Mean C. Mode D. I need to see histogram first
I need to see histogram first
Variability
In a set of numbers, how widely dispersed the values are from each other and from the mean
Which of the following is not a way to deal with observer bias? A. Using multiple observers B. Double-blind designs C. Measuring the behavior unobtrusively D. Having specific coding criteria that observers are trained to use
Measuring the behavior unobtrusively
Playing violent video games is associated with aggressive behavior because children model what they see in video games. What type of prediction is this? A. Third variable B. Moderator C. Mediator D. None of the above
Mediator
Suppose we find that buying pizza for a work party leads to positive morale which then leads to the work being done in half the time. What does positive morale serve as in this example? A. Mediator B. Moderator C. Valid variable D. Third variable
Mediator
As a potential third variable, a researcher decides to measure medication type and classifies medications as "depressants", "stimulants", "hallucinogens", or "other". What measurement scale is this? A. Nominal B. Ordinal C. Interval D. Ratio
Nominal
Leading Questions
Non-neutral words are used in the framing question Ex: "How would you rate the career or legendary Reds player Pete Rose?" vs. "How would you rate the career of baseball player Pete Rose?" Ex: "The University of Iowa should force you to pay more student fees to increase student services" vs. "The University of Iowa should increase student fees"
Which part of the equation can be negative? r = SPxy / √SSxSSy A. Numerator B. Denominator C. Both
Numerator SPxy = ∑((xi - μx) * (yi - μy))
Controlled Observation
Observation in a controlled setting, such as a lab
Confirmatory Hypothesis Testing
Only forming hypotheses that will predict what we want to see
Dots in scatterplots that deviate conspicuously from the main dot cluster are viewed as ___. A. No answer text provided B. Outliers C. More informative as other dots D. Errors
Outliers
Why wouldn't we use a pearson correlation to test the relationship shown in the figure? A. One variable has much more variability than the other B. Pearson correlations should only be used for categorical data C. Pearson correlations should only be used when the relationship is linear
Pearson correlations should only be used when the relationship is linear
When using inferential statistics, researchers calculate a/an ___ to determine "statistical significance" A. Null hypothesis B. Degrees of freedom C. Population parameter D. Probability estimate
Probability estimate
Applied Research
Research whose goal is to find a solution to a particular real-world problem Ex: Efficacy of a treatment for depression can be tested in a sample of trauma survivors
Standard Error of the Estimate Equation
S y|x = Standard error of y given x Σ(yi — yi')² = Each observed y value minus respective predicted y, squared to get rid of the negative deviations (sum of squared deviations) n — 2 = Degrees of freedom for the estimate
What is the calculation for sample sum of squares?
SS = Σ(Xi — X̅)² SS = ΣXi² — N * X̅²
What is the calculation for population sum of squares?
SS = Σ(Xi — μ)² SS = ΣXi² — N * μ²
How can you calculate the sum of squares?
SS = ΣXi² — N * mean² Step 1: Square each score Step 2: Take the sum of the squared scores Step 3: Square the mean Step 4: Multiply the squared mean by the number of scores Step 5: Subtract the step 4 value from the sum of the squared scores
How can variability be explained using "SSy — SS y|x"?
SS y|x = Σ(yi — yi')² Using yi', which is based on xi as prediction SSy = Σ(yi — ȳ)² Using mean of y as prediction SSy — SS y|x = How much better did we do by using X instead of simply the mean of Y? We can then compute the proportion of explained variability to total variability (SSy — SS y|x) / SSy = (Explained) / (Total) What proportion of the total variability was explained by the regression with X? This proportion is known as r² (r is Pearson's r)
A student is interested in estimating how far the average University of Iowa student can throw a football. They collect a sample of 500 students from the quad, and another student who is interested in this question collects data from a sample of 50 students. Whose confidence interval is likely larger? A. Sample N = 500 B. Sample N = 50
Sample N = 50; the sample size is smaller, which results in a larger/wider confidence interval
Sample Statistic Vs. Population Parameter
Sample Statistic: n → Number of cases/scores X̅ → Mean s² → Variance s → Standard Deviation Population Parameter: N → Number of cases/scores µ → Mean σ² → Variance σ → Standard Deviation
Type I Error
Saying an effect exists when it does not (false positive); worst kind of error
Type II Error
Saying no effect exists when one is there (false negative or miss); not as damaging (conservative approach)
How are sample size, effect size, and p-value related?
Small effect size with small p-value → confidence that the small effect exists in the full population, likely detected with hundreds of people An effect could be strong, but not significant
What statistic do we use to quantify the scatter around the regression line? A. Mean absolute deviation B. Standard deviation C. Standard error of the estimate D. Standard beta of estimate
Standard error of the estimate
Multivariable Regression
Statistical modeling of outcome while controlling for suspected confounders Each predictor variable (X) gets a beta weight (b) that reflects its strength of relationship with Y
How do you make a frequency distribution table?
Step 1: Put scores in order Step 2: Count frequency of each score Step 3: Make a new frequency table with these frequencies
What does the standard error of the estimate represent? A. The amount of explained variability B. The amount of unexplained variability C. The r² value of the data D. The predicted Y values, given X
The amount of unexplained variability
Validity
The appropriateness of a conclusion or decision; not a single measure or criteria; every study balances the four main types of validities
How can frequency claims establish external validity?
The claim must have good generalizability (the subjects represent the populations they are supposed to represent, and the settings in the study should represent other settings or contexts)
Think about the formula for r. Which of the following is FALSE regarding the calculation of the correlation coefficient, r. A. The numerator can be negative B. The numerator shows us the amount of shared variability C. The denominator can be negative D. r of 1 means that all variability is shared
The denominator can be negative
Face Validity
The extent to which a measure is a plausible measure of a defined construct; it appears to be a good measure At face value, does the measure seem to measure what it is intended to measure?
Generalizability
The extent to which the subjects in a study represent the populations they are intended to represent; how well the settings in a study represent other settings or contexts
What is the introduction section of an empirical journal article?
The first section of regular text in which the first paragraphs typically explain the topic of the study, and the middle paragraphs lay out the background for the research
Among frequency distributions for physical fitness, the greatest variability would probably occur in the distribution for ___. A. First graders in Iowa B. Patients in a nursing home C. College cross-country team D. The general population of Iowa
The general population of Iowa
In this distribution, how will the mean differ from the median? A. The mean will be lower B. The mean will be higher C. They will be very similar D. Not enough information
The mean will be higher
Systematic Variability
The measure of a construct is consistently offset from the true score, so it is systematically biased; adding error to true reading consistently in one direction
Random Variability
The measure of a construct is randomly off from the true score of the variable (sometimes higher and sometimes lower); adding error to true reading randomly
What does a z-score represent? A. The standard deviation of the data B. The proportion of data that falls beyond some value C. The mean of the data D. The number of standard deviations from the mean
The number of standard deviations from the mean
Degrees of Freedom (df)
The number of values that are free to vary in a sample used to estimate a population score s² = SS/n — 1 Variance of sample = Σ(Xi — X̅)²/df
Statistical Power
The probability that a study will show a statistically significant result when some effect is truly present in the population; inversely related to type II error (high power means low type II error)
Replication
The process of conducting a study repeatedly to test whether the result is consistent
Inference
The process of drawing conclusions about population parameters based on a sample taken from the population
What is the discussion section of an empirical journal article?
The section that summarizes the study's research question and methods, indicates how well the results of the study supported the hypotheses, emphasizes the study's importance, discusses alternative explanations for the data, and poses interesting questions raised by the research
Confirmation Bias
The tendency to consider only the evidence that supports a hypothesis, including asking only the questions that will lead to the expected answer
Population
The total collection of things (people, trees, animals, etc) that we seek information about
Slope Direction
The upward, downward, or neutral slope of the cluster of data points in a scatterplot
Random Assignment
The use of a random method (flipping a coin or rolling a dice) to assign participants into different experimental groups
Empiricism
The use of verifiable evidence as the basis for conclusions; collecting data systematically and using it to develop, support, or challenge a theory; deriving knowledge from observation and experimentation; may also be called empirical method or empirical research
Which of the following is not an issue with observational research? A. Observer effects B. Lack of agreement between observers C. There are few statistical techniques to analyze observational data D. Potential for unclear operational definitions of behavior E. Observer bias
There are few statistical techniques to analyze observational data
In previous studies, Dr. Schulenberg has established that finding meaning in one's everyday work activities can lead to greater success in the workplace (e.g., productivity, creativity). He is curious as to whether this can happen in the college classroom. Specifically, he is curious whether finding meaning in one's classroom experience can lead to greater academic performance. In the spring semester, he has his teaching assistant randomly assign half the class to write a paragraph each class period about how the material has meaning for their lives (meaning group). The other half writes a paragraph about what they did to prepare for class (preparation group). To measure academic performance, he gives the students a midterm essay exam and a final exam. What is the null hypothesis in this study? A. There is not sufficient information to answer the question B. Meaning group has greater academic performance than preparation group C. Preparation group presents greater academic performance than meaning group D. There is no difference between the meaning and preparation group in terms of their academic performance
There is no difference between the meaning and preparation group in terms of their academic performance
Why do we examine mediators? A. To figure out alternative explanations for an association B. To test reliability of our measures C. To attempt to understand the mechanisms underlying an association D. To understand what alters the strength of an association
To attempt to understand the mechanisms underlying an association
Correlate
To occur or vary together (covary) systematically, as in the case of two variables; two variables are said to be related
How can scatterplots show interrater reliability?
Two observers should expect to have consistent ratings, so the dots on the scatterplot should all fall exactly on or close to the line to indicate high interrater reliability
Double-Barreled Questions
Two or more questions are asked in one Ex: "Do you feel it is worth an additional expense to provide internet connectivity to cardio equipment to have additional features of workout tracking, social media, and video streaming?"
What units are used to calculate z-scores?
Units of standard deviation are used when calculating z-scores because it makes them helpful for comparing across measures with different units of measurement
Why is there asymmetry in reliability and validity? (Why can a reliable measure be invalid, but a valid measure can't be unreliable?) A. Low reliability damages face validity B. Validity is more subjective than reliability C. Unreliable measures provide inconsistent data D. There are more types of validity than reliability
Unreliable measures provide inconsistent data
Why are response sets in surveys a potential problem? A. They may reflect social desirability biases B. We are only measuring someone's subjective opinions C. We cannot differentiate someone that supports everything from someone taking a shortcut D. People may not know the correct answer to what we are asking
We cannot differentiate someone that supports everything from someone taking a shortcut
When might open-ended questions be best for a survey? A. When you want to decrease reactivity of the participants. B. When you're interested in socially disapproved behaviors such as drinking and driving C. None of the above D. When you're conducting a large survey and need standardized responses
When you're interested in socially disapproved behaviors such as drinking and driving
What is the calculation for determining cutoff scores for a given z-score or proportion?
Xi = X̅ + (z * s) Xi = Score needed to be converted to a z-score (raw scores of interest) X̅ = Mean of the distribution z = Z-score s = Standard deviation of the distribution
Regression lines can predict ___ scores from ___ scores
Y; X
What would the range for a 95% confidence interval be if the sample average is 149?
[147, 151]
How can you calculate sample variance using sum of squares?
s² = SS/n — 1 Divide SS (sum of squares) by (n-1) instead of N Dividing by (n-1) means that the estimate of sample variance will be lower than the estimate of the population variance "s" is used instead of "σ" to signify the sample The value in the denominator is known as the degrees of freedom (df) Result: Sample of variance for the data
Offering Inducements For Participation (Standard 8.06)
1. Avoid offering excessive inducements that coerce participation 2. When offering personal services, outline the risks
What is the purpose of data visualization?
1. Data visualization puts your data in a graphical format 2. Often easier for identifying errors in the data
What are the characteristics of ordinal scales?
1. Different levels can be compared 2. The categories are distinct, but they have a meaningful order 3. The intervals (increments) may be unequal Ex: A professor might use the order in which exams were turned in to operationalize how fast students worked (fastest exams are on the bottom of the pile, slowest exams are on the top of the pile) Ex: Drink size (short, tall, grande, and venti) Ex: Placing order in a race (first, second, third, last)
What are some characteristics of face validity?
1. Face-valid measures align well with the conceptual definition of a construct Ex: A reading test with math questions does not have high face validity
What are the three types of quantitative variables?
1. Ordinal 2. Interval 3. Ratio
What are sources of variability?
1. Participant variability 2. Measurement variability
What are characteristics of the sum of squares?
1. Summarizes the amount of deviation from the mean 2. The sum of squares equals sum of all squared deviation scores
Which one of the following numbers couldn't possibly be a value of r? A. 1.5 B. 1 C. .5 D. -1
1.5
Histogram
A data visualization technique showing how many of the cases in a batch of data scored each possible value (the range of values/distribution) on the variable
Data Matrix
A grid presenting collected data
Range
A measure of variability that tells how wide the distribution is
Physiological Measures
A method of measuring a variable by recording biological data
Disinformation
A news story, photo, or video deliberately created to be false or misleading
Sample
A representative collection of the things drawn from the population; a subset of the population
Cumulative Frequency Table
A table that counts accumulated scores across bins
Observational Research
A type of research in which a researcher watches or monitors participants (people or animals) and systematically records their behavior
Central Tendency
A value that the individual scores in a data set tend to center on (mean, median, mode)
What is one way to check if an association is driven by a third variable?
Check to see if the relationship is there within similar groups
What might be the cause of a type I error?
False positive/alarm (type I error controlled/prevented by using a stringent p-value threshold)
Homoscedastic
Homogeneity of variability around the regression line
What is a major caveat of the following headline: "Not Enough Zzzzs? Social Media Use Could Be Messing With Your Sleep"? A. It implies the study is valid B. It does not mention third variables that were ruled out with their survey C. It implies a causal relationship based on association D. It should be a frequency claim
It implies a causal relationship based on association
You work for a company that is developing a new phone application that helps students make and track progress on health goals. After its first month available for download, your team leader wants you to summarize data about your app. How could you summarize where students heard about the app (friend, advertisement, etc)? How could you best summarize number of goals users make? When summarizing usage time after download, what type of distribution would your team be most excited about? A. Uniform B. Symmetrical C. Negatively skewed D. Positively skewed
Negatively skewed
Levels
One of the possible variations, or values, of a variable; also called conditions
Social Desirability Biases
Participants may respond in a way they think is socially desirable 1. Participants may be afraid to express opinions that they feel are undesirable Including a survey with questions that we know should elicit socially unacceptable answers help check for this 2. Participants may sometimes fake bad by intentionally giving socially undesirable responses Including questions that we know should elicit socially unacceptable answers help measure a person's tendency for this bias 3. Implicit measures can avoid desirability biases
What are the population, parameter of interest, sample, and descriptive statistic for the question, is there a relationship between social media use and anxiety in teenagers?
Population: All of the teenagers in the world Parameter of Interest: ρ (rho) correlation between social media use and anxiety Sample: A set of 200 teenagers sampled from Iowa City Descriptive Statistic: r correlation between social media use and anxiety computed from your sample
Forced Choice Questions
Questions in which the participant is given a limited set of options and must choose one
Of its 10 ethical standards, ethical standard #8 is written for psychologists in their role as ___
Researchers
Sample Standard Deviation
Sample standard deviation is the square root of the sample variance s = √(s²) = √(SS/n — 1) = √(Σ(Xi — X̅)²/n — 1)
Type I Error
Saying an effect exists when it does not (false positive); worst kind of error Ex: Telling someone they are pregnant when they are not pregnant
Suppose a new participant is added to the data set below with an age of 87 years. Which measure of variability would be most affected? A. Mean B. Median C. IQR D. Standard deviation
Standard deviation
How can the IQR be calculated?
Step 1: Obtain dataset Step 2: Put the dataset in order Step 3: Divide at the median Step 4: Find the middle of each half to get Q1 and Q3 Step 5: Q3 — Q1 Ex: 25th percentile = 4. 00, 75th percentile = 45.00 IQR = 45 — 4 = 41
What are the ranges for different strengths of correlation?
Strong: [0.7, 1] Moderate: [0.5, 0.7) Weak: [0.3, 0.5) None or Very Weak: [0, 0.3)
Which theory is more parsimonious? Theory 1: The lights went out because you pressed the switch Theory 2: The lights went out because the exact second you pressed the light switch, there was a power outage Theory 3: The lights have not actually gone out since the light switch does not work, but at the exact second you pressed the switch, you developed a special type of vision impairment, which caused you to think that they did Theory 4: The lights have not actually gone out since the light switch does not work, but at the exact second you pressed the switch, you developed a special type of vision impairment, which was caused by aliens that visited your hours, which in turn caused you to think that they did
The lights went out because you pressed the switch (theory 1)
Effect Size
The magnitude, or strength, of a relationship between two or more variables
Exhaustive
The measure should cover the entirety of the construct, not a sub-construct Ex: A measure of intelligence should not only measure verbal IQ
Which of the following is true about z-scores? A. They are unit-free B. They are not standardized C. They cannot be negative D. If z = 1, then the point is at the mean
They are unit-free
Suppose we find that frequency of flossing is a predictor of lower risk of death. What would be plausible examples of the following: third variable, moderator, and mediator?
Third variable → conscientiousness Moderator → economic level of the country Mediator → dental health
How do you compute r?
r = SPxy / √SSxSSy SSPxy = Sum of cross product SSx = Sum of squares of variable x SSy = Sum of squares of variable y Step 1: Compute the SS (sum of squares) for each variable (on its own) Step 2: Multiply the two SS's and take the square root of this product The denominator tells us about the variability of the two variables, but not as much about how they relate to each other Step 3: Compute the "cross product" to estimate how strongly the variability is related Step 3A: Compute the distance of each score from the mean for both variables Step 3B: Multiply the differences for each item Step 3C: Sum these products SPxy = Σ((xi — X̅)*(yi — Ȳ)) The ratio of covariance (the amount the two variables vary similarly) to independent variability (the amount each variable varies overall) A ratio of 1 means all of the variability is shared Overall: SSx = Σ((xi — X̅)(xi — X̅)) SSy = Σ((yi — Ȳ)(yi — Ȳ)) SPxy = Σ((xi — X̅)*(yi — Ȳ))
What r value indicates good reliability?
r > 0.7
What is Pearson's r equation?
r² = (SSy — SS y|x) / SSy The value of r² indicates the proportion of total variability in one variable that is predictable from another When you compute the Pearson correlation coefficient and you square it, you can find how much variability in Y can be accounted for with X This r² value is the same as squaring the correlation coefficient Ex: r = -.94, r² = (-.94)² = .8836 88.36% of variance in Y is explained by X We cannot infer cause and effect from r² The regression equation tells us how predictable Y is, given X It does not tell us the X causes Y When we say "explained variability", that does not mean we explained the cause of the variability
How can you calculate population variance using sum of squares?
σ² = SS/N Divide the SS (sum of squares) by the number of values Calculates the mean of the sum of squares (population parameter) Result: Population parameter of variance for the data
R²
% of variance in Y (dependent variable) that is accounted for by combined effects of X predictor variables (independent variables); estimated with multiple linear regressions
What can cause type II errors when you miss an effect that really exists?
1. Alpha level is too stringent (p < .001) 2. Small sample size 3. Alpha level is too stringent (p < .001) 4. Random variability (measurement error, individual differences, situation noise) 5. Wrong choice of statistical test
How do observational measures operationalize a variable?
1. An observational measure operationalizes a variable by recording observable behaviors or physical traces of behaviors Ex: If stress is the variable being studied, researchers might ask people to self-report on the frequency of specific events they have experienced in the past year (marriage, divorce, moving, etc)
Why might likert scales be used?
1. Answer to individual question can be considered an ordinal variable 2. A summary measure of multiple questions using the same scale can be considered an interval variable 3. Likert-type scales are extremely common
What are the four levels of measurement?
1. Nominal 2. Ordinal 3. Interval 4. Ratio
A valid claim is what three things?
1. Reasonable 2. Accurate 3. Justifiable
The Animal Welfare Act (AWA)
1. Replacement: - Researchers should find alternatives to animals in research when possible, such as computer simulations 2. Refinement: - Researchers must modify experimental procedures and other aspects of animal care to minimize or eliminate animal distress 3. Reduction: - Researchers should adopt experimental designs and procedures that require the fewest animal subjects possible
What are the three types of reliability?
1. Test-retest 2. Interrater 3. Internal
Operational definitions turn ___ concepts into ___ variables
Abstract; measurable
Regression Equation
An equation that describes the precise numeric relationship between the variables We can derive the equation for the best-fit line, which lets us predict scores of one variable if given scores of the other in their measured units Regression line = best-fit line Regression lines go beyond strength of relationship and let us predict future data points
How can you calculate confidence intervals?
CI = X̅ ± z(s/√n) X̅ = Sample mean z = Confidence level value s = Sample standard deviation n = Sample size
What type of claim is this headline: "Stress Reduces Self-Control"? A. Frequency B. Association C. Causal
Causal
Bivariate Correlation
Correlation that expresses the relationship between exactly two variables
___ is used to evaluate internal reliability
Cronbach's alpha
Psychologists are empirical scientists; therefore, ___ A. They use logic to prove that their theories are right B. Data is used to prove a theory is right C. Data is used to test whether a theory makes the correct predictions D. Intuition can be used to derive knowledge for how the mind works
Data is used to test whether a theory makes the correct predictions
How can data be sorted?
Data sorted by value → sorted data Sorted data into # of data points for each number/bin → raw frequency table Raw frequency table summed up to current number/bin → cumulative frequency table Raw frequency table where each frequency is divided by total sample size → relative frequency table Relative frequency table summed up to current number/bin → cumulative frequency table Raw vs. relative frequency table = points vs. proportion Non-Cumulative vs. cumulative = the current bin vs. sum up to the current bin
My alpha is currently set at p = .05 (5%), but I decide to lower it to p = .001 (.1%). This will ___ my risk of making a type I error, and ___ my statistical power. A. Decrease; increase B. Decrease; decrease C. Increase; increase D. Increase; decrease
Decrease; decrease
What is the possible range for raw beta coefficients? A. -1 to 1 B. 0 to 1 C. Depends on predictor variable only D. Depends on predictor and dependent variable
Depends on predictor and dependent variable
Probabilistic
Describing the empirical method, stating that science is intended to explain a certain proportion (but not necessarily all) of the possible cases
Students in research methods last semester had an average of 741 facebook friends and 499 instagram followers. What kind of statistic is reported? A. Descriptive B. Inferential C. Neither
Descriptive
What does it mean by saying that statistical significance is not the same as effect size?
Effect size = strength = absolute value of the correlation Statistical significance = p-value
When calculating the sum of squares with the definition formula, each deviation is squared in order to ___. A. Eliminate negative signs from deviation scores B. Generate squared units of measurement C. Emphasize the contributions of larger deviations D. For computational efficiency
Eliminate negative signs from deviation scores
What is considered the most reliable basis for conclusions?
Empiricism
A researcher is conducting a study on how the wording of questions affects people's responses. In her study, she only includes native speakers of English and excludes people under 40 to ensure hearing is adequate. These decisions about her sample hurt the study's ___ A. External validity B. Internal validity C. Construct validity D. Statistical validity
External validity
Statistically Significant
In NHST, the conclusion assigned when p < .05; when it is unlikely that the result came from the null hypothesis population
Not Statistically Significant
In NHST, the conclusion assigned when p > .05; when it is likely that the result came from the null-hypothesis population
P-Value
In NHST, the probability of getting the results in a sample or one more extreme, by chance, if there is no relationship or difference in the population; the probability that you would have observed your data if the null hypothesis were true
Having lots of "noise" in the data (using an unreliable measure) ___. A. Increases type I errors only B. Increases type II errors only C. Increases type I and type II errors D. Affects statistical power but not statistical decision errors
Increases type II errors only
The 95% confidence interval for how far a University of Iowa undergraduate can throw a football is 15 to 45 yards. What kind of statistic is reported? A. Descriptive B. Inferential C. Neither
Inferential
Frequency Statistics
Information related to how often a particular event happens in a particular set of data
Observer Bias
Inherent biases observers may have that can affect interpretations of data Occurs when observers' expectations influence their interpretations of the participants' behaviors or outcome in the study
Survey
Method of gathering information from participants via self-report
Measures of central tendency summarize the ___ or most ___values for a variable
Middle; typical
Does transforming scores in your dataset to z-scores transform the shape of the distribution of your variable? A. Yes B. No
No
What is the shape of a normal distribution?
Normal distributions are symmetrical with a single peak and a bell shape
A behavioral problems survey asks teachers to pick whether the child is disruptive in class with responses such as "never", "sometimes", or "always". What measurement scale is this? A. Nominal B. Ordinal C. Interval D. Ratio
Ordinal
Population Standard Deviation
Population estimate of standard deviation is the square root of the population variance σ = √(σ²) = √(SS/N) = √(Σ(Xi — μ)²/N)
Theory-Driven Research
Reasoning from a general theory to the data
Positive Deviation
Scores greater than the mean
What are the shapes of skewed distributions?
Skewed distributions have a single peak that is off-centered; many observations are clustered near one end followed by a long tail at the other end
The following problematic question appears on a personality test for job placement: "Please indicate your agreement to the following statement: I am almost always on time for appointments and I enjoy having a wide circle of acquaintances." How could this question be changed to improve its construct validity? A. Include an additional component to the same question to determine social desirability response bias B. Split the question into two so that it is not double-barreled C. Add an additional phrase to capture more in the same question, such as, "and it is difficult to get me excited" D. Use less neutral language so that it is more of a leading question
Split the question into two so that it is not double-barreled
You develop a new 10-question survey of a stable trait of narcissism that can be used online. You first test this on your friends by sending them the survey every three times a month to test the consistency of their overall score across tests. You are testing the ___ reliability of your measure A. Test-retest B. Interrater C. Internal D. None of the above
Test-retest
Why are results about the null hypothesis and not the alternative hypothesis?
Tests are performed with respect to the null hypothesis to determine whether the predicted relationship would be observed if the null hypothesis were true
Operational Definitions
The specific way in which a concept of interest is measured or manipulated as a variable in a study; also called an operational variable
Operationalize
To turn a conceptual definition of a variable into a specific measured variable or manipulated variable in order to conduct a research study
Fence-Sitting
When participants are hesitant to choose extreme answers and always opt for neutral responses Can be prevented by removing the option of a neutral response
Parsimony
When two theories both explain data equally well, the simpler theory is preferred (Ockham's Razor)
As your sample size increases ___. A. Your confidence interval gets narrower B. Your confidence level increases C. Your confidence level decreases D. Your confidence interval gets wider
Your confidence interval gets narrower
If there is a negative correlation between X and Y, then the linear regression equation Y = bX + a would necessarily have ___. A. b < 0 B. a < 0 C. a > 0 D. b > 0 E. A and C
b < 0
Given a sample of 10 and a sample of 100,000, which sample standard deviation will be adjusted more with the correction for degrees of freedom with n-1? A. n = 10 B. n = 100 C. Same D. Need to know SD
n = 10
What is an example of how question order can impact responses?
#1: "What is the most important problem facing the nation?" #2: "Do you approve or disapprove of the job the president is doing?" The first question biases answer to the second to reflect the primary focus of the first #1: "Which of the following four activities are your favorite way to exercise: walking, running, swimming, tennis?" #2: "How many minutes a week do you exercise?" The first question may bias attention to a subset of exercises
In the correlation matrix below, what is the p-value for pearson r between "Fruit Per Day" and "Steps Per Day"? A. .025 B. .698 C. 1 D. 250
.698
What proportion of scores in the standard normal curve are between a z-score of -1.50 and the mean? A. 0.4332 B. 0.0668 C. 1.50 D. 0.5668
0.4332 First, find 1.50 in column A of the z-score table Then, find the number across from 1.50 in column B
What z-score corresponds to where 33% of the scores in the standard normal curve are greater than this z-score? A. 0.1293 B. 0.1700 C. 0.3707 D. 0.4400
0.4400 First, find 0.3300 in column C of the z-score table Then, find the number across from 0.3300 in column A
What are the most typical confidence interval percentages?
1. 90% 2. 95% 3. 99%
What does it mean if the mean is 150 with a 95% confidence interval of 147 to 151?
1. 95% of all possible samples should have a mean within this range 2. If the study is repeated 100 times, then the true population mean will be within this range 95/100 times
What does a high p-value indicate?
1. A high p-value indicates that the sample result would be likely if the null hypothesis were true (p > .05) 2. Not strong evidence against null 3. Observed relation/difference due to chance 4. Retain (fail to reject) the null hypothesis
What does a low p-value indicate?
1. A low p-value indicates that the sample result would be unlikely if the null hypothesis were true (p < .05) 2. Strong evidence against null 3. Reject the null hypothesis
What are some characteristics of association claims?
1. A pair of frequency claims in which the frequency of one variable is tied to the frequency of the other 2. States a relationship between at least two variables, and that relationship is measured to determine whether they are associated 3. Does not signal directionality, but they may seek to imply causality (correlation does not imply causation)
What is the relation between population variation and the width of the confidence interval?
1. A population with low variation leads to similar samples with low variation → narrow CI 2. A population with lots of variation leads to varied samples with lots of variation → wide CI 3. Generally speaking, the narrower the CI, the better 4. Narrow CI gives a more precise estimate of the effect size 5. Wider CI gives a less precise estimate of the effect size 6. More studies with similar results and larger studies lead to a narrow CI
How do self-report measures operationalize a variable?
1. A self-report measure operationalizes a variable by recording people's answers to questions about themselves in a questionnaire or interview Ex: If stress is the variable being studied, researchers might ask people to self-report on the frequency of specific events they have experienced in the past year (marriage, divorce, moving, etc)
What do z-scores equal to 1 and -1 mean?
1. A z-score equal to 1 represents an element that is 1 standard deviation greater than the mean 2. A z-score equal to -1 represents an element that is 1 standard deviation less than the mean
What do z-scores equal to 2 and -2 mean?
1. A z-score equal to 2 represents an element that is 2 standard deviations greater than the mean 2. A z-score equal to -2 represents an element that is 2 standard deviations less than the mean
What do z-scores less than, greater than, and equal to 0 mean?
1. A z-score less than 0 represents an element less than the mean 2. A z-score greater than 0 represents an element greater than the mean 3. A z-score equal to 0 represents an element equal to the mean
What is the purpose of a z-score table?
1. A z-score table lets you convert from z-scores to proportions 2. When given a certain z-score, a z-score table can help determine what proportion of the data falls below or above the z-score
What is the Socioemotional Selectivity Theory (SEST), and how can it be tested using null hypothesis testing?
1. As we get older, we perceive we will die soon, and we are motivated to regulate emotions so that we emphasize positive emotions and wellbeing and tune out negative emotions; therefore, we improve our emotional awareness and intelligence with age, which is an explanation for increases in wellbeing during late life, despite all of the other negative ways our body and mind are impacted with age The theory implies the conceptual prediction that we actually get happier as we get closer to dying Hypothesis: If SEST, then age should be positively correlated with global wellbeing as measured by the WB ladder for those between 40 and 90 years of age 2. Two possibilities in the population: Null: This effect does not exist in the population Alternative: This effect does exist in the population 3. Test these predictions with data from the sample Compute correlation from sample: r = .60 How close is this estimate to the population relationship? → get confidence interval What is the probability that I could have gotten this correlation if the correlation in the population were r = 0? 4. Assign a p-value to infer, where p stands for probability
What are the characteristics of the mean?
1. Average of all values 2. Best for symmetrical distributions (interval and ratio variables) 3. Uses all of the values in the data 4. Could use for interval and ratio scales 5. Can be computed from the frequency distribution 6. As distribution varies from normal, the averages diverge 7. Most influenced by outliers
What does cronbach's alpha do?
1. Averages all possible correlations of each item with every other item and number of items 2. The closer cronbach's alpha is to 1.0, the better the scale's reliability 3. For self-report measures, a cronbach's alpha of .70 or higher is considered acceptable for good internal reliability
What graphs are best for nominal or ordinal data?
1. Bar graph 2. Pie graph
How can p-values be interpreted for regression?
1. Beta Null Hypothesis (Ho): There is no relationship between the independent variable and the dependent variable; the slope is flat (zero) Alternative Hypothesis (HA): There is a relationship between the independent variable and the dependent variable; the slope is expressing their relationship is significantly different than zero 2. Intercept Null Hypothesis (Ho): When predictor variables are zero, Y is not significantly different than zero Alternative Hypothesis (HA): When predictor variables are zero, Y is significantly different than zero
What are the characteristics of score bins?
1. Bins are exclusive, equal-sized, and exhaustive Exclusive = Each item fits in no more than one bin Equal-Sized = Each bin has the same range Exhaustive = Every item fits in a bin 2. Outliers are included 3. 5-20 bins should be included Too few bins does not portray the data well Too many bins can be hard to comb through
What is the checklist for determining the type of measurement scale being used?
1. Categorizes labels and variables Nominal: ✔ Ordinal: ✔ Interval: ✔ Ratio: ✔ 2. Ranks categories in order Nominal: ⓧ Ordinal: ✔ Interval: ✔ Ratio: ✔ 3. Has equal intervals (increments) Nominal: ⓧ Ordinal: ⓧ Interval: ✔ Ratio: ✔ 4. Has a true zero Nominal: ⓧ Ordinal: ⓧ Interval: ⓧ Ratio: ✔
What verbs are used in causal claims?
1. Causes 2. Enhances 3. Affects 4. Promotes 5. Reduces 6. Prevents 7. Fights 8. Worsens 9. Adds 10. Hurts 11. Decreases 12. Exacerbates 13. May lead to 14. Sometimes makes 15. Changes
What are common response dimensions for questions about attitudes and judgment?
1. Degree of attractiveness (like/dislike, favor/oppose) 2. Satisfaction 3. Intensity (a little, somewhat, or very much) 4. Certainty 5. Importance Ex: "Over the past 7 days, rate your sleep quality" Response Dimensions: 1- Not at all 2 3 4 5- Very much
What are the two broad classes of statistical methods?
1. Descriptive 2. Inferential
What are some characteristics of construct validity?
1. Determines how well the variables in a study measure what they are intended to measure 2. The extent to which the measure provides an accurate estimate of the theoretical construct 3. Strong construct validity means that the measure provides an exhaustive and selective estimate of the theoretical construct
What are some characteristics of external validity?
1. Determines the degree to which the results of a study (and its conclusions) generalize to a larger population or to other situations 2. If a study was conducted in a new setting, the same (or similar) results should be expected
What are some characteristics of statistical validity?
1. Determines the degree to which the statistical results support the claim 2. Two types of statistical errors; type I error and type II error 3. Determines the likelihood that these results occurred because of random chance (type I error) 4. Answer to questions given by a probability value (p-value) ranging from 0 (lowest chance) to 1 (highest chance)
What are some characteristics of internal validity?
1. Determines the extent to which the effect arises because of the experimental treatment and not some alternative variable Ex: Living in residence halls causes higher social satisfaction with campus experience The confound (something other than the target manipulated variable also varies between conditions) could be year in college
What are the characteristics of criterion validity?
1. Determines whether the measure under consideration correlates with another concrete behavioral measure of the construct 2. Useful for developing diagnostic measures 3. Especially important for self-report measures because the correlation can indicate how well people's self-reports predict their actual behavior 4. Criterion validity provides some of the strongest evidence for a measure's construct validity Ex: If Aptitude Test A and Aptitude Test B are both acceptable in terms of face and content validity but Aptitude Test A correlates more strongly with the type of performance it is supposed to measure, then Aptitude Test A would be considered to have better criterion validity
How can association claims establish construct validity?
1. Each variable must be assessed to determine whether the construct validity is strong or weak 2. The types of construct validity questions asked during assessment of the variables will determine the strength of the construct validity
How do you find the amount above a negative z-score using a z-score table?
1. Find the positive z-score in column A 2. Add .5 to column B 3. This works because we know the amount above the mean is 0.5, so we just need to know how much is between the score and the mean
How do you find the amount below a negative z-score using a z-score table?
1. Find the positive z-score in column A 2. Column B is the amount between the mean and this z-score 3. Column C is the amount below the z-score 4. This works because the distribution is symmetric
What are some characteristics of causal claims?
1. Has directionality (the value of one variable is the source of changes in the other variable) 2. Tends to suggest that one variable comes first in time and acts on the other variable 3. May contain tentative language (could, may, seem, suggest, sometimes, potentially, etc) 4. Advice is a causal claim 5. Must satisfy three criteria 6. Considered to be the strongest type of claims, but they are also the most difficult to show support for
What are ways to minimize observer bias?
1. Having very specific coding criteria that observers are trained to use 2. Multiple raters 3. Double-blind designs
What is the purpose of confidence intervals?
1. Helps express a population estimate as a range of best bet 2. Provides a probable range of values that, with a known degree of certainty, includes an unknown population characteristic, such as a population mean
What graphs are best for interval or ratio data?
1. Histogram 2. Stem-and-leaf
What questions should be asked using r² answers?
1. How much variability in Y did the regression explain with X? 2. How much better did we do by using X instead of simply the mean of Y?
Institutional Review Boards (Standard 8.01)
1. IRB approval is gained when appropriate 2. Before conducting a study, researchers must fill out a detailed application describing their study, its risks and benefits (to both participants and society), its procedures for informed consent, and its provisions for protecting people's privacy 3. An effective IRB should not permit research that violates people's rights, poses unreasonable risk, and lacks a sound rationale
A school can only afford to provide an intervention to the lowest 40% of students relative to the state population. Given a mean score of 50 and an SD of 8 at the population, what is the cutoff score for the lowest 40%?
1. Identify the relevant information Mean: 50 SD: 8 Proportion: Lowest 40% 2. Use the z-score table to determine the cutoff score: You want the lowest 40% of scores, so you want to find where column C = 0.4000 and use the z-score in column A (find closest score if there is not an exact match) The z-score for the lowest 40% is -0.25 3. Calculate the cutoff score: xi = 50 + (-0.25 * 8) = 48 4. Conclusion: Students scoring below 48 get the intervention
How can the area under the curve (proportion of the distribution less than x) be calculated?
1. If we want to know the proportion of the distribution less than x, we sum up the density function from -∞ to x (the percentile) ∫ p(x)dx, with x at top of integral and -∞ at bottom of integral Σ p(x), with x at top of sigma and -∞ at bottom of sigma 2. For any distribution with known p(x), the area under the curve can be calculated for any x
What is included in the Principle of Respect For Persons?
1. Individuals potentially involved in research should be free to make up their own minds about whether they want to participate in a study 2. In obtaining informed consent, researchers are not allowed to mislead people about the study's risks and benefits, nor may they coerce or unduly influence a person into participating because that would violate the principle of respect for persons 3. Some people have less autonomy, so they are entitled to special protection when it comes to informed consent (children, prisoners, and people with intellectual or developmental disabilities)
How can one be aware of unexpected range restrictions?
1. Know the target population 2. Know the typical spectrum available in the relevant literature
What two factors guide the choice of what central tendency to use?
1. Level of measurement (nominal, ordinal, etc) 2. Shape of distribution (normal, skewed, etc)
How do linear regression and multivariable regression differ?
1. Linear regression equation predicts a dependent variable with one independent (predictor) variable Y = bX + a Single predictor 2. Multivariable regression includes more than one independent (predictor) variable Y = b1X1 + b2X2 + a Multiple predictors
How can type II errors be reduced?
1. Make alpha level less stringent (p < .05) 2. Increase sample size 3. Be careful about over-interpreting a null effect
What is an example of how an attempt to improve internal validity can hurt external validity?
1. Making some variables constant 2. Only focusing on one sample that is not a good representation of the general population Ex: A researcher wants to see whether reading to children is related to better academic performance; to ensure effects arise because of reading, he only includes families with high SES, who already have at least two hours of face-time with their kids a day, and families that have two parents in the household High internal validity (few possible confounds) Low external validity (very restricted population)
What are the two parameters that describe a normal distribution?
1. Mean 2. Standard deviation
What are the characteristics of convergent validity?
1. Measures how exhaustive a measure is (covers all of the construct) 2. If several different operational definitions of the construct are highly correlated, then it is likely that the measures are covering most of the construct 3. Correlations should be strong (r = .70 or better) 4. If the correlations are weak, the measure may be incomplete because it is not covering all of the construct Ex: Scores on a new intelligence test correlate with scores on the Stanford-Binet scale
What are characteristics of the median?
1. Middle point of values 2. Best for ordinal and skewed distributions (interval and ratio variables) 3. Does not use all of the values in the data 4. Applicable to ordinal, interval, and ratio scales 5. Complement with frequencies if small number of levels 6. Not applicable to nominal data 7. The distance between scores does not matter 8. Not typically influenced by outliers
What are characteristics of the mode?
1. Most frequent value 2. The only and best measure for nominal variables 3. Complement with frequencies of each category 4. Does not require comparison between variable values or calculation of average 5. Applicable to ordinal, interval, and ratio if the values are discrete (variables can take on a finite number of values) 6. Not very helpful for continuous variables (height, weight, etc) 7. Least influenced by outliers
What are the limitations of the regression approach compared to experimental manipulations?
1. Multiple regressions on their own do not establish temporal precedence 2. Often measuring all variables at one point in time 3. We cannot assess which variable (IV or DV) came first if we measure all variables at once 4. Multiple regressions can only control for what they measure 5. Can never be sure that all possible third variables were accounted for 6. Best way to do this is to use random assignment in an experiment, and if possible, use within-subject designs
What three criteria must be met in order for a causal claim to be accepted?
1. Must establish that the two variables (the causal variable and the outcome variable) are correlated; the relationship cannot be zero (covariance) 2. Must show that the causal variable came first and the outcome variable came later (temporal precedence) 3. Must establish that no other explanations exist for the relationship; the study must support it (internal validity)
What central tendency should be used for each measurement scale?
1. Nominal data → mode 2. Ordinal data → median 3. Interval or ratio data with skewed distribution → median 4. Interval or ratio data with symmetrical distribution → mean
What are the advantages and disadvantages of naturalistic observations?
1. Observing behavior in natural settings can give the most accurate measure of behavior 2. Naturalistic observation brings up new ethical issues to consider, such as participant consent 3. In public settings, there is no assumption of privacy 4. Natural settings may not provide the opportunity to observe relevant behaviors
Why do association claims not always state why the relationship exists?
1. One variable causes the other 2. Both variables are caused by a third factor 3. Coincidental relationships (unexplained third factor)
What makes a study correlational?
1. Only measured variables (no manipulated variables) 2. That may be the only option in some cases (some variables are not manipulable) Ex: Age Ex: Ethnicity Ex: Family status Ex: Brain injuries
What are characteristics of the degrees of freedom?
1. Only n-1 values in a sample are truly free to vary independently from each other 2. "n-1" provides an unbiased estimate of the population variance 3. If the sample size is large enough, the sample variance will approach the population variance 4. If "n" is used as the degree of freedom for sample variance, sample variance is expected to be lower than population variance
What are common response dimensions for questions about events and behaviors?
1. Opportunity to experience or know something 2. Occurrence of an event or behavior within a defined time period 3. Frequency (counts or rates) 4. Regularity (time interval) 5. Duration 6. Date or timing Ex: "On average, how many minutes per day do you use social media for personal, non-work related purposes?" Response Dimensions: 0-30 mins 31-60 mins 61-120 mins > 120 mins
What is the purpose of descriptive statistics?
1. Organize data 2. Screen data for issues 3. Summarize main features of the data 4. Visualize data with graphs 5. Describe data from the sample
What is the relationship between p-value and z-score?
1. P-value is obtained from z-score (p is the proportion beyond the z-score) Higher r = Higher z and lower p Higher N = Higher z and lower p
What are the three principles stated in the Belmont Report?
1. Principle of Respect For Persons 2. Principle of Beneficence 3. Principle of Justice
What are the types of unbiased samples?
1. Probability 2. Simple random 3. Systematic 4. Cluster 5. Multi-stage cluster 6. Stratified random 7. Oversample
What are the rules for finding a z-score for a given proportion?
1. Proportion above z and proportion < 50%, look for proportion in column C, z-score is positive 2. Proportion above z and proportion > 50%, look for 1 — proportion in column C, z-score is negative 3. Proportion below z and proportion < 50%, look for proportion in column C, z-score is negative 4. Proportion below z and proportion > 50%, look for 1 — proportion in column C, z-score is positive
What is the calculation for proportion involving relative frequency tables?
1. Proportion is frequency over total measurements Proportioni = fi/Σf i = Proportion for a bin fi = Frequency of that bin Σf = Total of all frequencies (number of observations)
How can you determine the median with an even number of data points?
1. Put points in order 2. Count the points (n) 3. Take points surrounding (n+1)/2 4. Median is midpoint of these two points Ex: 2, 2, 3, 7, 8, 9, 11, 11 (8 + 1)/2 = 4.5 Median is at midpoint of 7 and 8 = 7.5 7 and 8 are data points #4 and #5
What methods are used for settling differences between raters?
1. Quantitative, such as taking average 2. Raters discuss where disagreements were made and decide what score to use 3. An independent third rater would moderate between raters and decide which score to use 4. Whatever method is done should be reported in the methods section
What are things to consider when writing a good survey question?
1. Question structure (open-ended vs. forced choice) 2. Wording of questions (no phrases associated with bias, double-barreled questions, or double-negative questions) 3. Question order 4. Using a previously tried and tested questionnaire helps in getting started 5. If making a new questionnaire, always pilot test to understand the impact of these factors
What is the difference between raw and relative frequency tables?
1. Raw frequency tables (with numbers) reflect sample size This can be useful if you want to see sample sizes It can make it hard to compare across studies with different sample sizes 2. Relative frequency tables include proportions and percentages 3. Patterns across different sample sizes can be compared
What is regression used for?
1. Regression lets us predict variability in one variable from that of another variable 2. Given what we know about X, how well can we predict a value of Y? 3. The standard error of the estimate tells us on average how much we mispredict 4. How much of variability in Y are we unable to account for, given X? 5. Misprediction estimate is in units of measurement for the predicted variable Y 6. Without X, our best prediction for Y is to always predict the mean (using X allows for better predictions) 7. We know overall variability of the variable (SSy) and how much is left after the regression (SS y|x) 8. SSy — SS y|x = Variability explained SSy = Total variability in Y SS y|x = Unexplained variability
What is included in the Principle of Justice?
1. Researchers consider the extent to which the participants involved in a study are representative of the kinds of people who would also benefit from its results 2. If researchers decide to study a sample from only one ethnic group or only a sample of institutionalized individuals, they must demonstrate that the problem being researched is especially prevalent in that ethnic group or type of institution
How can experiments support causal claims?
1. Researchers must conduct a well-designed experiment, in which one variable is manipulated and the other is measured 2. When psychologists conduct an experiment, they manipulate the variable they think is the cause and measure the variable they think is the effect or outcome 3. Experiments are considered the gold standard of psychological research because of their potential to support causal claims
What is included in the Principle of Beneficence?
1. Researchers must take precautions to protect participants from harm and to ensure their wellbeing 2. Researchers carefully assess the risk and benefits of the study they plan to conduct as well as consider how the community might benefit or be harmed 3. Researchers cannot withhold treatments that are known to be helpful to study participants 4. To prevent harm and risk having people's personal information revealed to others, researchers usually make participant information either anonymous or confidential
When might open-ended questions be used?
1. Sensitive or socially disapproved behaviors Ex: More accurate reports of drinking and sexual behaviors 2. Research questions on explicit content of a self-generated response or information implicit in response Ex: Use of language 3. Preliminary research Ex: Narrow down responses for future research Open-ended questions provide rich data, but they can be hard to code (disadvantage)
What types of participant issues can impair the validity of data gathered in self-report?
1. Shortcuts and biases (response sets and fence-sitting) 2. Social desirability 3. Limits of what can be self-reported
What are some characteristics of frequency claims?
1. Statement of how common a behavior or occurrence is 2. Mentions the percentage of a variable, the number of people who engage in some activity, or a certain group's level 3. Focuses on one single variable 4. Does not show associations or causations between variables 5. A simple description of data collected
What are the pros and cons of self-report and observational research?
1. Survey is easier and works well if perspective of the self is of interest or if it is possible to accurately self-report a behavior 2. Observation allows measurement of behavior that otherwise would be hard to access from self-perspective 3. It is difficult so it must be justified to answer the research question 4. Always need specific coding manual based on operational definitions, multiple raters, and a system for deciding final ratings
What are the interpretations of the mode?
1. Technically mode is the absolute peak, but sometimes there is another peak that it misses 2. Quantitative bimodal considerations: Multiple environmental causes targeting different ages? Multiple genetic causes with different latencies? Multiple diseases classified under one name? Faulty or insufficient data? Combinations of different causes/data? 3. Quantitative multimodal considerations: Were different versions of a measure used? Was there some procedural difference that could have created unintended groupings in the data? Are there naturally occurring groups in the data that should be examined separately?
What are the characteristics of the IQR?
1. Tells how widespread the observations are in the middle of the distribution 2. Less affected by outliers 3. For normal distributions, IQR is symmetrical such that the range of Q1 to Q2 is equal to the range of Q2 to Q3 4. For skewed distributions, IQR may be asymmetric such that the range of Q1 to Q2 is different than the range of Q2 to Q3
When is test-retest reliability relevant?
1. Test-retest reliability is relevant whether the operationalization is self-report, observational, or physiological, but it is most relevant when researchers are measuring constructs that are theoretically stable Ex: If IQ is being tested by administering a test to the participants, those who scored the highest the first time should also score the highest the second time, even if all of the scores from the second time have increased (due to practice or schooling)
What are characteristics of the range?
1. The absolute range tells the difference between the smallest and largest observed value 2. Range can be calculated no matter the shape of the distribution 3. Finding the minimum and maximum values is independent of the rest of the distribution 4. Highly susceptible to outliers
How can being persuaded by what easily comes to mind be problematic?
1. The availability heuristic might lead us to wrongly estimate the number of something or how often something happens 2. Our attention can be inordinately drawn to certain instances, leading to overestimation
How can frequency claims establish construct validity?
1. The conceptual variable must be operationalized well 2. Each variable has been measured reliably (the measure yields similar scores on repeated testings) 3. Different levels of a variable accurately correspond to true differences
What is the correlation statistic?
1. The correlation statistic tells about the link between values of two variables 2. Knowing the value of one variable gives information about the value of the other variable 3. Specifically measures linear relationships (relationships that can be modeled or "fit" with a straight line) 4. The strength of the correlation can be visually estimated by how close the points are to a trendline (-1 to 1) 5. The direction is shown by the slope (+ or -)
How can standard deviations be interpreted?
1. The distance from the mean can be measured by how many standard deviations away a value is 2. For most distributions, most values fall within one standard deviation of the mean (left or right) 3. For a normal distribution, 68% of values are less than one standard deviation above or below the mean 4. For a normal distribution, less than 5% of data are greater than two standard deviations from the mean 5. Variability tells us about uncertainty for the mean
How can frequency claims establish statistical validity?
1. The estimate of a value in some population should be taken (point estimate) 2. The confidence interval should be calculated 3. The study should be replicated to gain multiple estimates and determine the margin error of the estimate
Why would multiple predictor variables be put in a regression?
1. The estimates for the beta (slope) for each variable are adjusted for the inter-relationships of the predictors 2. This helps account for potential third variables 3. Sometimes a relationship between two variables arises because of another variable 4. This helps compare relative strength of multiple predictor variables
What are some reasons for poor interrater reliability?
1. The measure itself is unreliable (if scores are inconsistent within a rater, they will also be inconsistent across raters) 2. The raters are biased (if raters are not scoring accurately, they may not agree) 3. The raters are poorly trained (if raters have different criteria, their scores will diverge) 4. The score is too subjective (if the score relies on judgment, individual differences can reduce interrater agreement)
What are the advantages and disadvantages of participant observations?
1. The researcher interacts directly with the group being observed 2. Interacting with those being observed may alter their behavior
What is the difference between normal distributions and standard normal distributions?
1. The standard normal is one set of parameters for a normal distribution (μ = 0, σ = 1) 2. Any normal distribution can be standardized (z-scored) to a standard normal distribution, which is defined as having a μ = 0 and σ = 1
How can association claims establish statistical validity?
1. The statistical validity considers how strong the estimated association is and how precise that estimate is, and it considers other estimates of the same association 2. Strong associations typically have high percentages, while weak associations have low percentages 3. The confidence interval is designed to capture the true relationship between two variables 4. Studies with smaller samples (fewer people) have wider, less precise intervals that reflect uncertainty 5. Studies with larger samples (more people) have narrower, more precise intervals 6. The study should be replicated to gain multiple estimates and determine the margin error of the estimate
What two things does the validity of a survey depend on a good match of?
1. The type of information needed with the feasibility of self-report in your target population Ex: Some types of information are just not suitable for surveys Ex: Extremes (anxiety of an infant, number of minutes spent on your smartphone in a day) 2. Quality of the questions Ex: How questions are structured and worded is crucial to construct validity
What does the width of the confidence interval measure?
1. The variation within the population of interest (similar population vs. different population) 2. The size of the sample (small sample vs. large sample) 3. Sample size is an important factor in determining confidence interval
What does it mean if p > .05?
1. There is greater than a 5% chance of obtaining the result if the null model were true for the population (by chance) 2. There is greater than a 5% chance that no relationship exists in the target population 3.. Retain (fail to reject) the null hypothesis 4. Never say a null hypothesis is proven 5. If the p-value is equal to or greater than your chosen cutoff, the result is "not statistically significant" 6. Fail to reject null and infer that the predicted effect unlikely exists in the population → theory is not supported and needs revision
What does it mean if p < .05?
1. There is less than a 5% chance of obtaining the result if the null model were true for the population (by chance) 2. There is less than a 5% chance for the observed relationship if there was none in the population 3. Reject the null hypothesis 4. Accept the alternative hypothesis 5. If the p-value is less than the chosen cutoff, the result is "statistically significant" 6. Reject null and infer that the predicted effect likely exists in the population → theory supported
Plagiarism (Standard 8.11)
1. To avoid plagiarism, it is important to cite the sources of all ideas that came from somewhere else and give appropriate credit to the original authors 2. Psychologists must follow the style guidelines for citations in the APA 3. When using another person's exact words, put quotation marks around the quoted text and add the page number where the quotation appeared in the original source
How can decisions be made regarding the null hypothesis?
1. Truth is effect present (Ho false, HA true) + decision is effect present (Reject Ho, accept HA) = Correct 2. Truth is effect present (Ho false, HA true) + decision is no effect present (Retain Ho, reject HA) = Type II Error (miss) 3. Truth is no effect (Ho true, HA false) + decision is effect present (Reject Ho, accept HA) = Type I Error (false alarm) 4. Truth is no effect (Ho true, HA false) + decision is no effect present (Retain Ho, reject HA) = Correct
What are the advantages and disadvantages of controlled observations?
1. Using controlled settings can allow the researcher to focus on certain behaviors of interest (external vs. internal validity) 2. Often easier than waiting for specific situations to occur naturally 3. Eliminates other sources of variability 4. Controlled observations can create less natural situations
Frequency Claim
A claim that describes a particular rate or degree of a single variable How often does something happen?
Institutional Review Board (IRB)
A committee responsible for ensuring that research using human participants is conducted ethically An IRB panel includes five or more people with different backgrounds: 1. A scientist 2. A person with academic interests outside the sciences 3. A community member who has no ties to the institution (pastor, community leader, or interested citizen) 4. In the case of a proposal to use prison participants, one person must be a designated prisoner advocate
Stratified Random Sample
A form of probability sampling in which the researcher identifies particular demographic categories (strata) and randomly selects individuals within each category Researcher selects particular demographic categories on purpose and then randomly selects participants within the categories Allows researcher to force a match of the sample demographic to the population by randomly drawing within population strata Ex: Target population is adults between 60-90 years, generate separate list for age categories (60-69, 70-79, 80-90) from census list and then use probability sampling to choose within groups
Data Fabrication
A form of research misconduct in which a researcher invents data that fit the hypothesis
Plagiarism
A form of research misconduct that involves representing the ideas or words of others as one's own
Self-Selected Sample
A form of sampling bias that occurs when a sample contains only people who volunteer to participate Sampling only those who invite themselves Ex: Surveys in popular magazines or newspapers Ex: Online polls or surveys Ex: Ratings for products on amazon
Confidence Interval
A given range indicated by a lower and upper value that is designed to capture the population value for some point estimate (percentage, difference, or correlation); a high proportion of CIs will capture the true population value
Confidence Interval (CI)
A given range indicated by a lower and upper value that is designed to capture the population value for some point estimate (percentage, difference, or correlation); a high proportion of CIs will capture the true proportion value
Histogram
A graphical depiction of a frequency table by showing how often values in the data occur
Scatterplot
A graphical representation of an association, in which each dot represents one participant in the study measured on two variables
No Correlation
A lack of systematic association between two variables; also called zero association
Mode
A measure of central tendency that is the most common score in a set of data (most common value of the variable)
Median
A measure of central tendency that is the value at the middlemost score of a distribution of scores, dividing the frequency distribution into halves; the point that falls in the middle of all points when putting the data in order
Z-Score
A measure that describes how far an individual score is above or below the mean in units of standard deviations, rather than in units of the original variable
Which of the following is true? A. Validity and reliability are never related B. A measure with low validity can never have high reliability C. A measure with low reliability can never have high validity D. Highly reliable measures are always highly valid
A measure with low reliability can never have high validity
Why are convergent validity and discriminant validity are typically evaluated together?
A measurement should have higher correlations (higher r values) with similar traits (convergent validity) than it does with dissimilar traits (discriminant validity)
Observational Measures
A method of measuring a variable by recording observable behaviors or physical traces of behaviors; also called behavioral measures
Self-Report Measures
A method of measuring a variable in which people answer questions about themselves in a questionnaire or interview
Ratio Scale
A numeric measurement scale in which the numerals have equal intervals and the value of zero truly means "none" of the variable being measured
Self-Plagiarism
A potentially unethical practice in which researchers recycle their own previously published text, verbatim and without attribution, in a subsequent article
Systematic Sample
A probability sampling technique in which the researcher uses a randomly chosen number (N), and counts off every Nth member of a population to achieve a sample Pick first participant random, then call/contact every Nth person N = number drawn at random Ex: Start at 3rd person in the list of the target population and sample every 3rd person in the list, numbers 3 and 3 were randomly chosen from a list of possible numbers
Ordinal Scale
A quantitative measurement scale whose levels represent a ranked order, and in which distances between levels are not equal
Confidential Study
A research study in which identifying information is collected, but protected from disclosure to people other than the researchers
What should occur with good test-retest reliability?
A study participant will get nearly the same score each time they are measured with it
Correlational Study
A study that includes two or more variables, in which all of the variables are measured; can support an association claim
Frequency Distribution Table
A table showing how many of the cases in a batch of data scored each possible value (the range of values) on the variable
Cumulative + Relative Frequency Table
A table that counts accumulated scores across bins and includes percentages (percentiles) Ex: What percent of people spend less than $50 on a haircut?
Standard Normal Curve
A theoretical normal distribution with a mean of 0 and a SD of 1
Freud's Unconscious Motivation Theory
A theory that states that behavior is shaped by unconscious psychological forces
Mediator
A variable that helps explain the meaningful association between two variables that have an existing correlation Medium = in middle = middleman The mediator variable arises from or is internal to the independent variable
Standard Error of the Estimate
Amount of deviations (scatter, dispersion, or variation) from the predicted regression line In values of the predicted variable
Positive Correlation
An association in which high levels of one variable go with high levels of the other variable, and low levels of one variable go with low levels of the other variable; also called a positive association
Sampling Error
An error that occurs when a sample does not represent the target population
Principle of Respect For Persons
An ethical principle stating that research participants should be treated as autonomous agents and that certain groups deserve special protection 1. Participants know about and consent to research 2. Informed consent
Principle of Beneficence
An ethical principle stating that researchers must take precautions to protect participants from harm and to promote their wellbeing 1. Do no harm, maximize benefits, minimize risks 2. Risk-benefit assessment
Coercion
An implicit or explicit suggestion that those who do not participate in a research study will suffer a negative consequence
Which of the following is the worst operational definition of self-control? A. The choice in response to: "Do you choose a candy bar worth 50 cents now or one worth $2 next week?" B. Ask a participant to report if giving into temptation interferes with their life C. Activation in the regions in the brain that respond more to distractor objects in a visual scene than a target object D. The number of marshmallows someone eats in a day
Ask a participant to report if giving into temptation interferes with their life
Homoscedasticity
Assumption that error in our prediction (scatter around the line) is evenly distributed across range of X and Y
What are the shapes of bimodal and multimodal graphs?
Bimodal and multimodal graphs have more than one peak
A researcher thinks students who take notes by hand will learn the material better than those who take notes by typing. She tests this in her lab by having participants watch documentaries and informing them that they will be tested on the material. Half watch a documentary about the history of baseball and are instructed to take notes by hand; half watch a documentary about America's most-wanted criminals and where they may be now. She compares groups on memory for the material based on a multiple choice test. What kind of claim would the researcher hope to make with their experiment? A. Frequency B. Association C. Causal
Causal
Convenience Sample
Choosing a sample based on those who are easiest to access and are readily available Researcher requests volunteers from a group who meet general criteria but are recruited in a variety of non-random ways Ex: Ex: College students on a college campus Ex: Research subject pool for class credit Ex: Fliers and advertisements
You want to measure reading proficiency in children. Which measure below would be an example of a measure with an ordinal level of measurement? A. Number of books read per week B. Who picks the books read (parent or child) C. Class rank based on a reading assessment D. Test score on a reading assessment
Class rank based on a reading assessment
I obtain contact information for all older adults in the U.S. between 60-80 years old that have a landline or cellphone. I randomly pick four states and then sample all individuals in the target population within those states. What kind of sampling am I doing? A. Cluster sample B. Multi-stage cluster sample C. Convenience sample D. Stratified sample
Cluster sample
How can the construct "coffee consumption" be operationalized?
Coffee consumption could be operationalized as a structured question in which people tell an interviewer how often they drink coffee
Indra wants to investigate the relationship between job status (whether or not they have a job) and grades among college students. She goes to the student center and hands out a survey with two questions about job status and GPA. She finds that at her institution, students with jobs have higher grades than students without jobs. Which of the following variable could be an alternative explanation for the association between job status and grades? A. Gender B. Number of part-time jobs C. SAT scores D. Conscientiousness
Conscientiousness
What should occur with good interrater reliability?
Consistent scores will be obtained no matter who measures the variable
Range Restrictions
Correlations may exist across a wide range, but be imperceptible in small portions of the range When we restrict a range, we ignore some values of the variable Range restrictions limit variability of at least one variable Reduced r due to range restriction Reduced and flipped sign due to range restriction Range restrictions often arise unexpectedly from biased sampling Ex: If we think intelligence is correlated with another variable, using college students (and those from extremes in selectivity) restricts the range of intelligence
A random sample of high school students was selected to take an SAT preparation course. After completing the course, the mean SAT score for this group of students was 25 points higher. What kind of statistic is reported? A. Descriptive B. Inferential C. Neither
Descriptive
In last semester's class, there was a positive correlation of r = .48 between facebook friends and instagram followers. What kind of statistic is reported? A. Descriptive B. Inferential C. Neither
Descriptive
A researcher thinks students who take notes by hand will learn the material better than those who take notes by typing. She tests this in her lab by having participants watch documentaries and informing them that they will be tested on the material. Half watch a documentary about the history of baseball and are instructed to take notes by hand; half watch a documentary about America's most-wanted criminals and where they may be now. She compares groups on memory for the material based on a multiple choice test. Is this a correlational study or an experiment? A. Correlational B. Experiment
Experiment
You test you hypothesis that greater time outdoors is related to less anxiety. Your correlation is r = -.40, p = .08. Given an alpha (type I error rate) of .05, your conclusion should be able to ___. A. Reject the null hypothesis B. Fail to reject the null hypothesis C. Support the alternative hypothesis D. Report your correlation as statistically significant
Fail to reject the null hypothesis
What type of claim is this headline: "A Quarter of the World's Population Now Uses Facebook Every Month"? A. Frequency B. Association C. Causal
Frequency
What is the purpose of frequency distribution tables?
Frequency distribution tables help organize data in such a way as to see patterns and detect weird values
Heteroscedastic
Heterogeneity of variability around the regression line
When examining the construct validity of an association claim, one should look for ___ A. How well the measure of each variable measures the concepts they're intended to measure B. Whether the association is positive C. Whether the sample was randomly chosen from the population D. How much the measure of one variable is tied to the measure of the other variable in the association E. Whether there is a third variable that could explain the association
How well the measure of each variable measures the concepts they're intended to measure
Internal Reliability
In a measure that contains several items, the consistency in a pattern of answers, no matter how a question is phrased; also called internal consistency Consistency across different times
Independent Variable (IV)
In an experiment, a variable that is manipulated and predicted to affect other variables; the IV value is independent of the values of other variables
Margin Error of the Estimate
In the context of a percentage estimate, an inferential statistic providing a range of values that has a high probability of containing the true population value
In order to measure motivation to study, Dr. Maine designs a survey with 6 items, all of which try to capture that construct. This is a test of which of the following? A. Test-retest reliability B. Internal reliability C. Interrater reliability D. Content reliability
Internal reliability
Dr. Johnson is studying children's interactions with their mothers while playing with some toys. He and a research assistance are recording how many physical approach and eye gaze behaviors the children exhibit. The two sets of observations are strongly correlated, r = .88. A. Test-retest B. Interrater C. Internal D. None of the above
Interrater
How would someone assess interrater reliability of a new questionnaire? A. Assess consistency of answers between two people that you know are narcissistic B. Assess consistency of the pattern of responses to each question C. Assess the consistency of a given participant's answers over multiple tests D. Interrater reliability would be more appropriate for an observational measure of narcissism
Interrater reliability would be more appropriate for an observational measure of narcissism
In his measure of "need for cognition" (degree to which people like thinking and problem-solving), Dr. Jonason asks his participants to rate their agreement with the following statement: "I have never not enjoyed thinking." A. What is the problem with this question B. It is a forced choice question C. It is a double-barreled question D. It has a double negative E. It is a leading question
It has a double-negative
Which of the following is true of probability sampling? A. It is the best way to obtain a representative sample B. It is the same as random assignment C. It results in larger samples than non-probability sampling D. It should be used when external validity is not hte goal of the study
It is the best way to obtain a representative sample
Which of the below is not true of regression analyses? A. Errors in prediction based on our regression line are minimized using a least squares method B. Enables us to make predictions with original units of the measures C. Enables us to predict future data points D. It is unitless and thus allows us to compare strength of association across measures
It is unitless and thus allows us to compare strength of association across measures
What does kappa do?
Kappa computes the ratio of agreement to agreement expected by chance, and the closer it is to 1.0, the more similar the ratings are (should be above 0.70)
What does it mean by saying that p-value is determined by effect size and sample size?
Larger effect size = lower p-value (assuming sample size is constant) Larger sample size = lower p-value (assuming effect size is constant) An effect size could be significant but weak
Typically, a probability of ___ than 5% is accepted to be a "real" effect, which is "statistically significant" (p < .05)
Less
What information is not needed to calculate the z-score for a score? A. Mean B. Score to be converted C. Standard deviation D. M.A.D
M.A.D
A researcher is curious about how different types of candy impact a child's impulsivity. He divides children into groups: one group receives snickers bars, and the other receives hard candies. He then measures how quickly the children reach for the candy. What kind of variable is the type of candy? A. Measured B. Manipulated C. Constant
Manipulated
Which of the following is most prone to outliers? A. Mode B. Median C. Mean D. Equally prone to outliers
Mean
What is the calculation to find the mean?
Mean = Sum of all scores / total number of scores
Which two central tendencies are better for determining skew direction?
Median and mean
A researcher thinks students who take notes by hand will learn the material better than those who take notes by typing. She tests this in her lab by having participants watch documentaries and informing them that they will be tested on the material. Half watch a documentary about the history of baseball and are instructed to take notes by hand; half watch a documentary about America's most-wanted criminals and where they may be now. She compares groups on memory for the material based on a multiple choice test. What is the dependent variable that is measured? A. Type of note-taking B. Type of documentary C. Memory for learned material D. Group
Memory for learned material
You work for a company that is developing a new phone application that helps students make and track progress on health goals. After its first month available for download, your team leader wants you to summarize data about your app. How could you summarize where students heard about the app (friend, advertisement, etc)? A. Mode B. Median C. Mean D. I need to see the histogram first
Mode
I have three statistics: 10.3, 10.5, and 10.75. Which of the statistics is the mode, median, and mean?
Mode = 10.75 Median = 10.5 Mean = 10.3
Playing violent video games is associated with aggressive behavior very strongly among teenagers but less strongly among adults. What type of prediction is this? A. Third variable B. Moderator C. Mediator D. None of the above
Moderator
Suppose we find that physical activity is related to lower levels of depression symptoms, and the relationship is stronger for older adults. What kind of variable is age in this example? A. Third variable B. Moderator C. Mediator D. None of the above
Moderator
Suppose we wanted to look at the relationship between the number of hours spent practicing the guitar per week and skill level. If we had reason to believe that the strength or direction of the relationship between these variables will vary by level of enjoyment, what would the level of enjoyment serve as? A. Mediator B. Significant variable C. Moderator D. Third variable
Moderator
What shape would the distribution for this data have: Mean = 6.860, Median = 7.000, Mode = 7.0? A. Uniform B. Symmetrical C. Negatively skewed D. Positively skewed
Negatively skewed Mean < median
What is the numeric order for central tendency in unimodal distributions?
Negatively skewed: Mean < median < mode (mean < median) Positively skewed: Mode < median < mean (median < mean) Symmetric: Median = mean = mode (median = mean)
Dispensing With Informed Consent (Standard 8.05)
No consent is needed during these circumstances: 1. Research creates no psychological harm 2. Study of normal practice 3. Completely anonymous 4. Done in a work setting
Are confidence intervals only used for means?
No, they can be used for correlation, mean group differences, etc
What measurement scale is college major (1 = psychology, 2 = neuroscience, 3 = health and human physiology, 4 = sociology, 5 = other)? A. Nominal B. Ordinal C. Interval D. Ratio
Nominal
What would be the null and alternative hypotheses involving probability for the statement, "Students that spend more time outside will have less anxiety"?
Null Hypothesis: H₀: ρ ≤ 0 (no correlation or positive correlation between time outside and anxiety) Alternative Hypothesis: HA: ρ > 0 (negative correlation between time outside and anxiety)
A psychology professor wants to measure how often parents read to their children and how much the parent and child interact during the reading process. The best measurement approach would be ___. A. Self-report B. Observation C. Equally good D. Equally bad, need experiment
Observation
In the hockey study example, what kind of bias would it be if the raters had read the news reports about fans being negative towards youth players (male fans in particular) and this affected how they coded the audiotapes of fan comments? A. Observer bias B. Observer effects C. Reactivity
Observer bias
In the hockey study example, what kind of bias would it be if the raters had read the news reports about fans being negative towards youth players, in particular male fans and this affected how researchers/observers coded the audiotapes of fan comments? A. Observer effects B. Observer bias C. Inter-rater reliability D. Reactivity
Observer bias
Masking corders of videos to experimental condition helps avoid ___. A. Observer bias B. Observer effects C. Participant reactivity D. B and C
Observer bias
You are observing a classroom of children to study the relationship between biological sex and participation during math class. You are aware of the cultural assumption that boys outperform girls in math at early ages. You inadvertently make eye contact with more boys as you observe the room when the teacher asks questions and observe they participate more. What kind of bias effect does this sound like? A. Observer bias B. Observer effect
Observer effect
Internal Validity
One of three criteria for establishing a causal claim; a study's ability to rule out alternative explanations for a causal relationship between two variables; also called third-variable criterion Can you really establish a relation between the IV and DV? How well can other explanations be ruled out? Could another factor of the study explain the results?
College football rankings use what measurement scale? A. Interval B. Nominal C. Ordinal D. Ratio
Ordinal
What measurement scale is military ranks (colonel, captain, etc)? A. Nominal B. Ordinal C. Interval D. Ratio
Ordinal
What measurement scale is scores on a self-esteem questionnaire whose 10 is the minimum (lowest self-esteem) and 40 is the maximum (highest self-esteem)? A. Nominal B. Ordinal C. Interval D. Ratio
Ordinal
What measurement scale is the birth order of siblings? A. Nominal B. Ordinal C. Interval D. Ratio
Ordinal
What are the population, parameter of interest, sample, and descriptive statistic for the question, how far can a typical University of Iowa undergraduate throw a football?
Population: All of the undergraduate students at the University of Iowa Parameter of Interest: µ average distance thrown Sample: A set of 30 students sampled from campus Descriptive Statistic: The actual average of throwing distance thrown of those in your sample
What are the population, parameter of interest, sample, descriptive statistic, and inference for the question, how much do apples from Wilson's orchard weigh?
Population: All the apples at Wilson's apple orchard Parameter of Interest: µ (mu) estimated average weight Sample: A set of 100 apples picked from the trees Descriptive Statistic: The actual average weight of your sample of apples Inference: Sample mean = 149 g → population mean = about 149 g
Which of the following is the most direct way to control for question order effects? A. Give the survey questions to different groups of people B. Prepare different versions of the survey, varying order of the questions C. Combine the two questions into a single question D. Both B and C control for question order effects
Prepare different versions of the survey, varying order of the questions
Correlational studies have ___ data for both variables
Quantitative
Open-Ended Questions
Questions that allow the participant to respond any way they would like Ex: "Describe a time when you've had trouble sleeping and what you think may have caused it"
Double-Negative Questions
Questions that involve the use of two negative words that cancel each other out, causing the person reading it to be confused Ex: "Rate the extent to which you agree or disagree that students should never not go to class"
Simple Random Sample
Random draw from sample frame Ex: Target population is adults between 60-80 years, generate random list from census list and call Ex: Target population is new moms, generate a list from state birth records and randomly pick people to send recruitment information
A sleep survey asks parents to indicate number of hours the child sleeps on a typical school night. What measurement scale is this? A. Nominal B. Ordinal C. Interval D. Ratio
Ratio
Todd is studying the effect of popularity on academic success for his research methods project. He decides to measure popularity by asking each elementary school student to tell him how many friends he or she has. He assumes that more friends mean the student is more popular. Which of the following best describes this variable? A. Ratio variable B. Categorical variable C. Self-report measurement D. Ordinal variable
Ratio variable
Single-Blind Design
Researcher knows the study hypotheses, but participants do not Researcher may unintentionally cue participant to act in accordance with hypotheses (observer effects)
What are the steps to calculate standard error of the estimate?
S y|x = √(SSy(1 — r²) / (n — 2)) Step 1: Subtract each respective predicted y from each observed y-value Step 2: Square the deviations to get rid of negative deviations Step 3: Sum of squared deviations (SS y|x) Step 4: Degrees of freedom for this estimate
What is the following formula for: SS/n — 1? A. Sample mean B. Sample standard deviation C. Sample variance D. Sum of squares
Sample variance
Type II Error
Saying no effect exists when one is there (false negative or miss); not as damaging (conservative approach) Ex: Telling someone they are not pregnant when they are pregnant
What type of graph should be used if IV and DV are interval or ratio?
Scatterplot
Assume the two scatterplots above show data for two different groups in your study. Which scatterplot represents a stronger correlation? A. They have the same strength B. Scatterplot A C. Scatterplot B D. There is no relationship in either scatterplot
Scatterplot B
Which of the following is not one of the four steps to test a mediational hypothesis? A. Show that X the predictor variable is correlated with Y the dependent variable B. Show that X predictor is correlated with the third variable C. Show that the mediator is correlated with the dependent variable Y D. Show that X the predictor variable is correlated with the mediator
Show that X predictor is correlated with the third variable
Say we want a set cutoff for admissions based on ACT scores. If we have an estimate of the mean and SD of scores in the population, z-scores let us determine what percentage of people will pass our cutoff. According to ACT score distributions, the mean is 20.8, and the SD is 4.8. The 25th percentile of ACT scores at University of Iowa is 23. What proportion of the population of all students who take the ACT surpass this level?
Step 1: (23 - 20.8)/4.8 → z = 0.46 Step 2: Use z-score table to find the proportion; z-scores are listed along with two values: Find the z-score in column A → z = 0.46 Column B = 0.1772 Column C = 0.3228 Step 3: If we care about what proportion of data is above a z-score, we care about column C p = 0.3228 Approximately 3% of students who take the ACT score above 23
What are the steps for interpreting z-score information?
Step 1: Convert score to z-score Step 2: Find the proportion corresponding to the z-score Step 3: Make a conclusion about the population above the threshold
What are the steps to designing a questionnaire?
Step 1: Define the problem Step 2: Plan how it will be administered Step 3: Write the questionnaire Step 4: Desk check Step 5: Pilot survey
What is the proportion of scores above z = -0.49?
Step 1: Find 0.49 in column A Step 2: Use number in column B + 0.5 to calculate proportion Area above z-score of -0.49 = 18.79% + 50% = 68.79%
You are working on developing a test of driving intelligence that could be delivered on the internet to screen for drivers who have a high risk of accidents. An example of criterion validity for your test of driving intelligence would be ___. A. Endorsement of your test by an expert in the field B. Strong correlation with number of accidents in the two years after taking the questionnaire C. Strong relationship with a questionnaire commonly used to measure driving aptitude D. Weak relationship with technical knowledge of how automobiles work
Strong correlation with number of accidents in the two years after taking the questionnaire
Dr. Rodriquez is considering conducting a study examining whether narcissistic people have poorer romantic relationships than those who are not narcissistic. One of her first tasks is to determine which of her participants are narcissistic and which are not. She decides to use the scale created by a colleague, the Donal scale. Question 1 reads, "I tend not to think about other people as much as I think about myself." Question 2 reads, "I do not have a high opinion of myself." Question 3 reads, "I think other people think I am really special." Before using the measure in her study, Dr. Rodriquez gives the measure to a group of participants on the first day of the semester and again on the last day of the semester. She then compares the scores between the two-time points. This is a test of which of the following? A. Interrater reliability B. Test-retest reliability C. Construct reliability D. Internal reliability
Test-retest reliability
How can association claims establish external validity?
The claim must have good generalizability
Covariance
The degree to which two variables go together; first of three criteria for establishing a causal claim, which states that, in a study's results, the proposed causal variable must vary systematically with changes in the proposed outcome variable; the two variables are observed to go together
Selective
The measure should only include aspects of the construct, not other outside components Ex: A measure of intelligence should measure intelligence, not age, visual acuity, or other outside components
Interquartile Range (IQR)
The range of the middle 50% of values; the values between the 25th (Q1) and 75th (Q3) percentile
Anton is reading an empirical article on the relations between bullying and self-esteem. Anton is concerned that the researcher made a type I error. What does that mean? A. The researcher concluded there was a relationship, but there isn't really one B. The research did not make a type II error C. The researcher failed to consider a third variable D. The researcher failed to establish the first rule of causation
The researcher concluded there was a relationship, but there isn't really one
In statistics formulas, what does the value of SS represent? A. The sum of the squared standard deviation scores B. The variance C. The square root of the standard deviation D. The sample standard deviation
The sum of the squared standard deviation scores
Which of the following is not an issue with observational research? A. There are few statistical techniques to analyze observational data B. Observer effects C. Potential for unclear operational definitions of behavior D. Lack of agreement between observers
There are few statistical techniques to analyze observational data
Professor Horvat designs a study to assess the work satisfaction and home-life satisfaction of a group of graduate students. She administers the same measures of work and home-life satisfaction on two occasions, 1 year apart. Suppose she finds that home-life satisfaction at the first time point is strongly correlated with job satisfaction at the second time point, but that there is no correlation between job satisfaction at the first time point and home-life satisfaction at the second time point. Which statement explains why Professor Horvat can't conclude that home-life satisfaction causes job satisfaction? A. There are potential third variables that might explain the relationship B. Home-life satisfaction does not occur before job satisfaction C. Home-life satisfaction is not related to job satisfaction
There are potential third variables that might explain the relationship
Which of the following is true about self-reports? A. They are always less reliable and valid than observational data B. They are valuable sources of information when researchers are interested in a person's internal experiences C. They are always biased by socially desirable responding D. They are valuable sources of information when researchers are interesting in measuring people's behaviors
They are valuable sources of information when researchers are interested in a person's internal experiences
Playing violent video games is associated with aggressive behavior because people who play violent video games have more aggressive parents. These aggressive parents are more likely to allow their kids to play violent video games and to accept aggressive behavior in their children. What type of prediction is this? A. Third variable B. Moderator C. Mediator D. None of the above
Third variable
Suppose the researcher finds no effect of note-taking in her study, but then over the next couple of years, five different studies with large representative samples show an effect. The researcher here may have initially committed a ___ error in her conclusion. A. Type I B. Type II
Type II
Which of the following is not a way to deal with reactivity? A. Blending in with the surroundings B. Waiting to begin observations C. Measuring the behavior unobtrusively D. Using multiple observers
Using multiple observer
Dr. Sheffield is a clinical psychologist who specializes in treating pathological gambling. Pathological gambling is defined as being unable to resist impulses to gamble. Bothered by not having a good measure that he can give to clients to determine whether they are suffering from this condition, he creates a new measure of pathological gambling. The measure has 15 questions, and it takes 20 minutes to complete. If Dr. Sheffield's measure does not actually measure pathological gambling, his measure is said to lack which of the following? A. Validity B. Reliability C. Operationalization D. Conceptualization
Validity
In a scatterplot, predictive errors are associated with ___. A. Horizontal discrepancies between dots and the regression line B. Either vertical or horizontal discrepancies between dots and the regression line C. Vertical discrepancies between dots and the regression line D. Discrepancies between dots and the regression line
Vertical discrepancies between dots and the regression line
What does it mean to say that psychology relies heavily on indirect measurements? A. We can't make scientific claims about psychological processes B. Psychology relies on using samples of the population instead of measuring the whole population C. We try to measure unobservable things by using operational measures D. No measure is perfect
We try to measure unobservable things by using operational measures
Why is it critical that a measure has good discriminant validity? A. None of the above B. We want to make sure we are measuring the entirety of the construct C. We want to make sure we are only measuring one construct D. Because constructs aren't real if they're hypothetical
We want to make sure we are only measuring one construct
What does it mean if we find an r² of 0? A. There was no variability in Y, given X (s y|x) B. We can perfectly predict the value of Y from the value of X C. The squared deviations of Y from predicted Y were all zero D. We would be just as accurate by predicting Y from the mean of Y than by using X to predict Y
We would be just as accurate by predicting Y from the mean of Y than by using X to predict Y
A baseball coach was curious about the true mean speed of fastball pitches in his league. The coach recorded the speed in kilometers per hour of each fastball in a random sample of 100 pitches and constructed a 95% confidence interval for the mean speed. The resulting interval was [110, 120]. Which is the correct interpretation? A. If the coach took another sample of 100 pitches, there's a 95% chance the sample mean would be between 110 and 120 B. About 95% of pitches in the sample were between 110 and 120 C. We're 95% confident that the interval [110, 120] captures the true mean pitch speed
We're 95% confident that the interval [110, 120] captures the true mean pitch speed
Response Sets
When participants give consistent responses across questions to save time, rather than accurately answering each question Can be prevented by including reverse-worded questions can avoid some response sets
Informed Consent For Recordings (Standard 8.03)
When recording voices or images, consent must be given before recording except when deception is used (consent for use is obtained during debriefing) and during naturalistic observation in public places (no personal identification)
Within-Subject Variability
Within a given subject; same person fluctuates over time
What is an example of how to calculate the X and Y deviations?
X Deviation (xi - x̄): 7 - 9.5 = -2.5 Y Deviation (yi - ȳ): 28 - 24 = 4.0 X Deviation Squared (xi - x̄)²: (-2.5)² = 6.25 Y Deviation Squared (yi - ȳ)²: (4.0)² = 16.0 X Deviation * Y Deviation ((xi - x̄) * (yi - ȳ)): (7 - 9.5) * (28 - 24) = -10.0
What is an example of how to calculate r?
X Deviation Squared = 17.5 Y Deviation Squared = 392 X Deviation * Y Deviation = -14 r = -14 / √(17.5 * 392) = -.17
How is "a" computed for the least squares equation?
a = Ȳ - bX̅ Ȳ = Mean of Y b = Estimated slope of Y X̅ = Mean of X
Dr. Demir-Lira is interested in examining if there is a correlation between the number of Facebook friends one has and his/her self-esteem. She collects a sample of 800 students from the quad. John, interested in this question, collects data from a sample of 80 students. Ariel collects data from 8 students to address the same question. Sojeong collects data from 8000 students. Whose confidence interval is likely largest? A. Sample size does not influence the size of the confidence interval B. n = 80 C. n = 8 D. n = 800
n = 8
What is the pearson correlation between two variables if one variable has all the same scores? A. r = 1 B. r = 0 C. r is undefined D. r = -1
r = 0 → some statistical software gives 0 AND r is undefined
What are the typical guidelines for assessing interrater reliability between raters?
0-0.2 = poor agreement 0.3-0.4 = fair agreement 0.5-0.6 = moderate agreement 0.7-0.8 = strong agreement >0.8= almost perfect agreement >0.7 is preferable for any publishable study
Which r value represents the weakest correlation? A. 0.42 B. 0.75 C. 0.28 D. -0.90
0.28
What proportion of scores in the standard normal curve are greater than a half standard deviation above the mean? A. 0.1915 B. 0.3085 C. 0.50 D. 0.8085
0.3085 First, find 0.5 in column A of the z-score table Then, find the number across from 0.5 in column C
What are incorrect ways to state the confidence interval?
1. "95% of apples in the sample weigh between 147 and 151" Incorrect because confidence interval is not a sample property 2. "There is a 95% chance that the mean weight in the population lies between 149 and 151" Incorrect because population value is fixed, so it is either within the range or not (the range either contains it or not)
What is an example of how confounds can occur when basing conclusions on experiences?
1. "At the reading program, my son really liked his new teacher, so he is reading more to impress her" 2. "At the reading program, my son met other kids; they became very good friends and read together" 3. Impressing the teacher and meeting other kids could both be possible explanations for why the child was reading more
How do physiological measures operationalize a variable?
1. A physiological measure operationalizes a variable by recording biological data, such as brain activity, hormone levels, or heart rate Ex: If stress is the variable being studied, researchers could measure the amount of the hormone cortisol released in saliva because people under stress show higher levels of cortisol
What is the difference between a population parameter and a sample statistic?
1. A population parameter is frequently impractical or impossible to find for large populations while a sample statistic is often easier to find and provides a reasonable approximation to the population parameter 2. Population parameter is a number that describes a whole population while a sample statistic is a number that describes a sample
What occurs during direct observation of behavior?
1. Behavior is recorded and the events must be coded to extract out information about behaviors of interest 2. Coding transforms behavior into data 3. Often done by people so it is important to beware of subjectivity that can arise from human process 4. Coding is done by experiment raters 5. At least two raters need interrater reliability 6. Quantifies how similar different raters' measurements are to each other 7. Follow strict coding manuals to try to preserve objectivity of the process
How can intuition be biased?
1. Being swayed by a good story or accepting a conclusion just because it makes sense 2. Being persuaded by what easily comes to mind (availability heuristic) 3. Failing to think about what we cannot see (present/present bias) 4. Focusing on the evidence we like best (confirmation bias, cherry-picking, and confirmatory hypothesis testing) 5. Believing our own biases about being biased (bias blind spot)
What guideline stated by the Ethical Principles of Psychologists and Code of Conduct corresponds to the Principle of Beneficence?
1. Beneficence and Nonmaleficence - Treat people in ways that benefit them (benefits must outweigh risks) - Do not cause suffering - Conduct research that will benefit society 2. Fidelity and Responsibility - Establish relationships of trust - Accept responsibility for professional behavior (in research, teaching, and clinical practice) 3. Integrity - Strive to be accurate, truthful, and honest in one's role as researcher, teacher, or practitioner - Do not steal, cheat, or engage in fraud
What are ways to minimize reactivity?
1. Blend in by unobtrusively observing 2. Wait until participants are used to being observed 3. Use implicit measure of the behavior rather than directly observing behavior 4. Use naturalistic observation
What are the characteristics of variability?
1. Central tendencies give a value that summarizes the most typical or most representative value in the full range of scores (usually located near the center of the distribution) 2. Distributions with the same central tendency can have different degrees of variability 3. Discussing only central tendency gives an incomplete picture of the data 4. Some day-to-day variability within a person is expected for most measures Ex: Test-retest reliability, the same exact thing is being measured with the same measures Even if there are no repeated measures in a study, remember that one measure is a snapshot of their possible scores from day-to-day
What are the characteristics of categorical variables?
1. Classifies objects in distinct categories 2. Categories are mutually exclusive (each observation only has one category) 3. Categories have no logical order (only qualitative differences) 4. Cannot take an average across nominal categories Ex: Male and female Ex: Eye color Ex: Yes or no questions
What are the types of observation choices?
1. Code by counting frequency of events of interest (gestures) during a designated period of measured time 2. Code by computing percentage of time spent doing behavior during a designated period of time (% of time gesturing rather than counts) 3. Time-base sampling in which the pre-specified periods of time and whether behavior is present or not are recorded or count frequencies within clips (randomly choose 10 30-second segments)
What can the overall pattern of a scatterplot be described by?
1. Form (mostly focused on linear relationships 2. Direction (positive, negative, or no relation) 3. Strength (determined by its consistency, not by the slope of the line or direction, measured by Pearson's r)
What are the three claims?
1. Frequency 2. Association 3. Causal
What are the goals of graphs?
1. Get to know individual variables 2. Know values are most common for the variable 3. See how much variety or variability is in the values 4. Detect outliers 5. Get to know relationships (trends, directionality, bivariate outliers, etc)
How is a good theory falsifiable?
1. Good theories should lead to hypotheses that could fail to support the theory when tested 2. Not every theory that explains a possible outcome is a good theory
A school district wants to give intervention help to the most struggling math students. They administer a math assessment within Iowa City schools and find a mean score of 25 and an SD of 5. Someone on the board proposes to give the intervention to students in the state of Iowa that scored below 18. What proportion of students in the broader population would receive the intervention with this cutoff?
1. Identify the relevant information: Mean: 25 SD: 5 Raw Score of Interest: 18 2. Calculate z-score: Z-score formula: z = (Raw Score — Mean)/SD z = (18 — 25)/5 = -1.4 3. Use the z-score table to determine the proportion: Use column A to look up the z-score of -1.4 Column C would most efficiently give you the answer for proportion You want to know what proportion of scores fall below the given z-score (normal distribution is symmetrical) Looking at column C, the proportion of scores that fall below -1.4 = 0.0808 4. Conclusion: 8% of students in the broader population would receive the intervention with this cutoff
You administer a reaction time task to children in your study sample that has been used in many other studies. Across other studies, the estimated population mean response time is 275 ms with a standard deviation of 100 ms. The range of your sample is 350 to 425 ms. What proportion of the population score is between the range shown in your sample?
1. Identify the relevant information: Mean: 275 ms SD: 100 ms Raw Scores of Interest: 350 and 425 ms Two z-scores are needed because you care about the proportion between scores of 350 and 425 ms 2. Calculate z-scores: Z-score formula: z = (Raw Score — Mean)/SD z350 = (350 — 275)/100 = 0.75 z425 = (425 — 275)/100 = 1.5 You want to solve for the proportion of data that falls between 0.75 and 1.5 3. Use the z-score table to determine the proportion: The z-score table does not give the proportion between two points, but column C tells the proportion between a point and the mean Column C for z-score 0.75 = 0.2266 Column C for z-score 1.5 = 0.0668 Subtract the two answers: 0.2266 — 0.0668 = 0.1598 4. Conclusion: 16% of the population scores between 350 and 425 ms
You are an elementary school teacher, and you administer a standard math test to your first grade class. Across the population in the state, the mean of the test is 65, and the standard deviation is 13. Your class scores between 50 and 75 on the test, and you want to determine what proportion of the population scores within this range, assuming a normal distribution. Is your class doing okay, performing low, or performing high?
1. Identify the relevant information: Mean: 65 SD: 13 Raw Scores of Interest: 50 and 75 Two z-scores are needed because you care about the proportion between scores of 50 and 75 2. Calculate z-scores: Z-score formula: z = (Raw Score — Mean)/SD z50 = (50 — 65)/13 = -1.15 z75 = (75 — 65)/13 = 0.77 You want to solve for the proportion of data that falls between -1.15 and 0.77 3. Use the z-score table to determine the proportion: The z-score table does not give the proportion between two points, but column B and column C tell the proportion between a point and the mean Column B for z-score 0.77 = 0.28 Column B for z-score -1.15 = 0.37 Add the two answers: 0.28 + 0.37 = 0.65 Column C for z-score 0.77 = 1 — 0.22 = 0.78 Column C for z-score -1.15 = 0.13 Subtract the two answers: 0.78 — 0.13 = 0.65 The sum of the two proportions in column B or the difference of the two proportions in column C tell the total proportion between the two points 4. Conclusion: 65% of the population scores between 50 and 75 on the test
Modus Tollens
1. If P, then Q; not Q, therefore, not P 2. If theory is correct (P), then predicted data (Q); did not get the predicted data (Q), therefore, theory is not correct (not P) 3. Valid to disprove a theory/hypothesis using a counter-example (denying the consequent) Ex: If it rains, then it is wet; it is not wet, therefore, it did not rain
What reasons might a causal claim not be accepted?
1. If both variables were measured at the same time, temporal precedence cannot be determined from the association 2. Without experiments, alternative (third-variable) explanations cannot be ruled out, thus compromising internal validity
How can r determine good or poor interrater reliability?
1. If r is positive and strong, interrater reliability is good 2. If r is positive and weak, the observers' ratings cannot be trusted 3. If r is negative, the observers rated completely different and disagree
How can r determine good or poor test-retest reliability?
1. If r is positive and strong, scores are very good 2. If r is positive and weak, scores changed from Time 1 to Time 2 3. If r is negative and weak, scores are not good Ex: The reliability of an IQ test should not be low unless it is not reliable
Why is the 95% confidence interval used?
1. If repeated samples were taken and a CI was calculated, 95% of the intervals will contain the true mean, and 5% will not 2. Due to the fact that the true mean (population mean) is an unknown value, we do not know if we are in the 5% or the 95% Ex: "There is a 95% chance that the CI calculated contains the true population"
What are the guidelines included in ethical standard #8?
1. Institutional review boards (standard 8.01) 2. Informed consent (standard 8.02) 3. Informed consent for recordings (standard 8.03) 4. Client/patient, student, and subordinate participants (standard 8.04) 5. Dispensing with informed consent (standard 8.05) 6. Offering inducements for participation (standard 8.06) 7. Deception (standard 8.07) 8. Debriefing (standard 8.08) 9. Animal research (standard 8.09) 10. Plagiarism (standard 8.11)
When is internal reliability relevant?
1. Internal reliability is relevant for measures that combine multiple items Ex: If a sample of people take Diener's five-item subjective wellbeing scale, the people who agree with the first item on the scale should also agree with the other items, regardless of the fact that the questions on his scale are worded differently; each item is intended to measure the same construct
When is interrater reliability relevant?
1. Interrater reliability is relevant for observational measures (two or more independent observers will come up with consistent or very similar findings) Ex: If two researchers are assigned to observe the number of times a child smiles in one hour at the playground, both researchers should record the same number
What are the steps in testing for mediation?
1. Is beta coefficient significant for path C? 2. Is beta coefficient significant for path A? 3. Is beta coefficient significant for path B? 4. Last step is a regression (predictors are both recess and physical activity) 5. Does path C get weaker or non-significant when the mediator is in the regression? 6. If yes, evidence is in favor of mediation prediction
What are some characteristics of content validity?
1. Items or questions to assess each of the components must be included Ex: Any operationalization of intelligence should include questions or items to assess each of the seven components (reason, plan, solve problems, think abstractly, comprehend complex ideas, learn quickly, and learn from experience)
What guideline stated by the Ethical Principles of Psychologists and Code of Conduct corresponds to the Principle of Justice?
1. Justice - Strive to treat all groups of people fairly - Sample research participants from the same populations that will benefit from the research - Avoid personal biases
What is the role of a producer of psychological science?
1. Know how to organize and analyze data 2. Know how to measure behavior accurately 3. Understand why scientists randomly assign people to groups
What is the standard error of the estimate used for?
1. Like standard deviation, standard error of the estimate provides a measure of the overall spread of data points away from the prediction 2. Standard error of the estimate is deviation away from the regression line 3. Standard error of estimate is the standard mean deviation of each Y point from the prediction line 4. The units are in units of the dependent variable 5. The lower, the better
What verbs are used in association claims?
1. Links 2. Associates 3. Correlates 4. Predicts 5. Ties to 6. Prefers 7. Is more/less likely to 8. Goes with 9. Is at risk for
What are characteristics of the mean absolute deviation?
1. M.A.D gives a metric for comparing variability 2. Distributions with higher M.A.D have greater spread of scores (greater variability) 3. M.A.D can also be calculated based on the median instead of the mean, which could be helpful for skewed distributions
Client/Patient, Student, and Subordinate Participants (Standard 8.04)
1. Protect subordinates from aversive risks 2. When participation is required, alternatives are given
Animal Research (Standard 8.09)
1. Psychologists who use animals in research must care for them humanely, must use as few animals as possible, and must be sure the research is valuable enough to justify using animal subjects 2. Researchers must abide by the guidelines stated in the Animal Welfare Act (AWA) 3. The Institutional Animal Care and Use Committee (IACUC) must approve any animal research project before it can be conducted 4. The IACUC requires researchers to submit an extensive protocol specifying how animals will be treated and protected 5. The IACUC application also includes the scientific justification for the research; applicants must demonstrate that the proposed study has not already been done and explain why the research is important
How can you determine the median with an odd number of data points?
1. Put points in order 2. Count the points (n) 3. Median is the value of item at (n+1)/2 Ex: 2, 2, 3, 7, 8, 9, 11, 11, 14 Median is at point (9+1)/2 = point 5
What are the characteristics of a box-and-whisker plot?
1. Range = lower and upper extremes 2. IQR and skew = lower and upper quartiles 3. Box-and-whisker plots are helpful for comparing distributions of different variables 4. The whiskers inform us about the spread 5. The box represents where most data points for a variable land Q1 and Q3 refer to cumulative frequencies of quartiles 6. Q1 = First quartile (25%) 7. Q3 = Third quartile (75%) 8. Q3 splits the highest 25% of data from the lowest 75% of data 9. Q1 splits the lowest 25% of data from the highest 75% of data 10. The median splits the data in half 11. Half the data are below the median, and half are above 12. The mean is not typically shown on box plots
What are the two forms of beta coefficients?
1. Raw Data Units (Unstandardized): In units that reflect the scale of the variable, so the value of raw betas for different variables are not directly comparable 2. Standardized Beta: In standard deviation units, so the value of standardized betas for different variables are comparable within the same analysis
What are the characteristics of discriminant validity?
1. Reflects whether the measure is only measuring what it intends to measure 2. Researchers focus on discriminant validity for "near neighbors" of constructs (similar, but different) Ex: A self-report measure of depression (BDI) should not correlate with scores on a test of perceived physical health Ex: A scale that is supposed to diagnose learning disabilities should have discriminant validity (not be correlated) with IQ because learning disabilities are not related to general intelligence
What is the difference between reliability and validity?
1. Reliability has to do with how well a measure correlates with itself Ex: An IQ test is reliable if it is correlated with itself over time 2. Validity has to do with how well a measure is associated with another variable Ex: An IQ test is valid if it is associated with another variable, such as school grades or life success 3. A measure must be reliable to be valid, but not all reliable measures are valid
How does research misconduct occur?
1. Researchers might fabricate or falsify data in order to maintain their prestige or because they are personally invested in their own hypotheses and believe that any data that do not support their predictions must be inaccurate 2. When researchers fabricate data, they mislead others about the actual support for a theory, which can have a costly impact
What guideline stated by the Ethical Principles of Psychologists and Code of Conduct corresponds to the Principle of Respect For Persons?
1. Respect For People's Rights and Dignity - Recognize that people are autonomous agents - Protect people's rights, including the right to privacy, the right to give consent for treatment or research, and the right to have participation treated confidentially - Understand that some populations may be less able to give autonomous consent, and take precautions against coercing such people - All people have access to the benefits and contributions of psychology
Why can population parameters from samples only be estimated or inferred?
1. Samples differ from each other and may not be able to represent the whole population, which can lead to error 2. A sampling error is the difference between the sample statistic and the population parameter
What are the three types of measures to operationalize variables?
1. Self-report 2. Observational 3. Physiological
What does null hypothesis testing do?
1. Tests against the possibility that there is nothing going on in the data related to the theory Ex: No association between social media use and anxiety 2. Tests a hypothesis about variables (dependent and independent) Ex: Students that spend more time outside will have greater wellbeing 3. Tests a hypothesis against a "null model" regarding the dependent variables Null Hypothesis: H₀: ρ ≤ 0 (against hypothesis) Alternative Hypothesis: HA: ρ > 0 (consistent with hypothesis) Ex: People that work outside are happier than people working in offices Null Hypothesis: H₀: μoutside ≤ μoffice Alternative Hypothesis: HA: μoutside > μoffice
What is the Cupboard Theory Vs. Contact Comfort Theory Experiment?
1. The Cupboard Theory of Mother-Infant Attachment explained that a mother is valuable to a baby mammal because she is a source of food 2. The Contact Comfort Theory of Mother-Infant Attachment explained that baby mammals are attached to their mothers because of the comfort of their warm, soft fur 3. Harry Harlow tested the theory by separating the two influences (food and contact comfort) 4. He built two monkey foster "mothers" for the baby monkeys, which were the only mothers they were exposed to 5. One of the mothers only offered food and not comfort 6. The other mother only offered comfort and not food 7. The babies would cling to the cloth mother 12-18 hours a day and only go to the wire mother to obtain food 8. The results supported the Contact Comfort Theory
What are the characteristics of ratio scales?
1. The numerals represent equal intervals between levels 2. There is a true zero (zero means total lack of the quality being measured) 3. Ratios between scores can be examined Ex: On a knowledge test, a researcher might measure how many items people answer correctly (0 truly represents "nothing correct", or zero answers correct) Ex: Height Ex: Income Ex: Reaction time
What are the characteristics of interval scales?
1. The numerals represent equal intervals between levels 2. There is no "true zero" (a person can get a score of 0, but the 0 does not actually mean "nothing" 3. Zero is not the lowest possible value (can be below zero) Ex: IQ test (the distance between scores of 100 and 105 represents the same as the distance between scores of 105 and 110; a score of 0 does not mean that a person does not have intelligence) Ex: Body temperature in degrees Celsius (the intervals between levels are equal, but a temperature of 0 degrees does not mean that a person has "no temperature")
How are sample size and correlation used together?
1. There is no absolute relationship between sample size and the strength of an observed correlation in our sample 2. Sample size affects the power to detect a relationship of a given strength 3. If the sample size is big enough, we can detect a small effect with a low p-value
What are the fundamental ways psychologists approach their work?
1. They act as empiricists in their investigations 2. They test theories through research and revise their theories based on the resulting data 3. They follow norms in the scientific community that prioritize objectivity and fairness 4. They take an empirical approach to both applied research and basic research 5. They make their work public by submitting their results to journalists for review, responding to the work of other scientists, and sharing findings of psychological research with the popular media
What are the different mode distributions?
1. Unimodal (1 mode) 2. Bimodal (2 modes) 3. Multimodal (2+ modes) 4. Uniform (mode is not helpful)
Deception (Standard 8.07)
1. Use deception only when it is justified and there are no alternatives 2. No deception is allowed with research that will cause physical pain or severe emotional distress 3. Deceiving research participants by lying to them or withholding information is often necessary in order to obtain meaningful results 4. In a deception study, researchers must still uphold the principle of respect as well as the principle of beneficence 5. The APA principles require researchers to avoid using deceptive research designs except as a last resort and to debrief participants after the study concludes
What can be done with outliers in correlations?
1. We may be able to learn from them 2. If one or a few points have a drastic effect on the correlation, use a statistic that minimizes its influence 3. In some cases, it may be justified to do the analysis without the outlier data point
How can focusing on the evidence we like best be problematic?
1. We may be biased by the motivation to only look at information that agrees with what we want to believe 2. Confirmation bias, cherry-picking, and confirmatory hypothesis testing are based on selecting information that supports the conclusion we want to believe
How can errors in prediction based on the regression line be minimized using a least squares method?
1. We minimize the squared deviations from the regression line 2. Error = Y - Ypredicted 3. Ypredicted is the score of the regression line given the X-value of the to-be-predicted Y
What questions can be answered using descriptive statistics?
1. What is the most common value or range of values for a variable? 2. What is the shape of the distribution? 3. How much spread, or variability, is there in values for a variable? 4. Which variables are related to each other?
What questions should be asked regarding null hypothesis testing and probability?
1. What is the probability of the observed data from your sample if the null hypothesis were true? 2. Given the model of the population parameters for the variables, if the null hypothesis were true, what is the probability that you would have observed your data?
What are self-reports good at measuring?
1. What people think they are doing 2. What people think they remember 3. What people think is influencing their behavior 4. Attitudes and judgments 5. Exploring a question because method is low-cost 6. Accessing a large and representative sample that spans multiple geographic locations
How can failing to think about what we cannot see be problematic?
1. When examining relationships between two events, we often fail to look for absences because it is easy to notice what is present 2. The availability heuristic plays a role in the present/present bias because instances in the "present/present" cell of a comparison stand out, which adds the tendency to ignore "absent" cells, which are essential for testing relationships
How can r indicate the direction and strength of a relationship?
1. When the slope is positive, r is positive 2. When the slope is negative, r is negative 3. When the relationship is strong, r is closer to 1 or -1 4. When the relationship is weak, r is closer to 0
What is a disadvantage of frequency tables?
1. When there are too many distinct values, a frequency table would not be able to condense the values to spot patterns or problems 2. In this case, one row per possible value would not be able to reasonably include all of the distinct values
Suppose we have a sample of participants, and each reported their height and weight. We correlate their height with weight twice, first time using foot as the unit and second time using inch as the unit. We use weight to predict height twice, first time using foot as the unit and second time using inch as the unit. Second slope will be 12 x of the first slope. Weight + 1 pound = height + 0.04 foot should translate into height + 0.48 inch. What is the intercept for the regression prediction line: yi = (1,91(xi + 1.18? A. 1.01 B. 1.18 C. 40 D. 41.5
1.18
You want to exclude all data more than 2 standard deviations from the mean. If the mean is 75 and the SD is 12, what are the cutoff scores?
2 SD from the mean is the same as z = 2 Cutoff above the mean: xi = 75 + (2 * 12) = 99 Cutoff below the mean: xi = 75 + (-2 * 12) = 51 Exclude scores above 99 and below 51
What proportion of scores in the standard normal curve is between a z-score of -1 and the mean? A. 68% B. 99% C. 95% D. 34%
34%
Indicate which one of the following sets of observations, each having a mean of 50, has the larger standard deviation. A. 40, 49, 50, 51, 60 B. 40, 49, 51, 52, 60 C. 40, 40, 50, 60, 60 D. 40, 42, 50, 58, 60
40, 40, 50, 60, 60
What percentage of scores are within 2 SDs from the mean?
95%
Availability Heuristic
A bias in intuition, in which people incorrectly estimate the frequency of something, relying predominantly on instances that easily come to mind rather than using all possible evidence in evaluating a conclusion
Present/Present Bias
A bias in intuition, in which people incorrectly estimate the relationship between an event and its outcome, focusing on times the event and outcome are present while failing to consider evidence that is absent and harder to notice
Purposive Sample
A biased sampling technique in which only certain kinds of people are included in a sample Researchers target or hand-pick participants that meet specific criteria based on knowledge of the research question Ex: Participants with diagnosed Parkinson's Disease from doctor referral Ex: Recruit children with ADHD from local clinic based on known diagnosis
Snowball Sample
A biased sampling technique in which participants are asked to recommend acquaintances for the study; a variation of purposive sampling Variant of purposive, but participants are asked to recommend other people they know that would also meet criteria Ex: Parent of child with ADHD asked to give contact information for other parents with children with ADHD Ex: Often have access to support groups
What is the abstract section of an empirical journal article?
A brief summary of the article that briefly describes the study's hypotheses, method, and major results
Ethical Principles of Psychologists and Code of Conduct
A broad set of guidelines written by the APA that governs three common roles of psychologists as research scientists, as educators, and as practitioners
Oversample
A form of probability sampling in which the researcher intentionally over-represents one or more groups; a variation of stratified random sampling Researcher intentionally over-represents one or more groups in order to get an accurate estimate from them Used when a variable of interest may have a low proportion in the population, so oversampling is needed to get enough participants for data to do data analysis Ex: Interested in effects of a bilingual household on kids learn to read, the researcher wants to compare an equal number of bilingual families to monolinguals, even though there are far more monolingual families in the population
Data Falsification
A form of research misconduct in which a researcher influences a study's results by selectively deleting observations from a data set or by influencing their research subjects to act in a way that supports the hypothesis
Intuition
A sense of knowing without direct evidence or experience, such that the information feels like it is known instinctively (often implicit, cannot explain how you know or why you feel the way you do)
Inferential Statistics
A set of techniques that uses the laws of chance and probability to help researchers make decisions about what their data mean and what inferences they can make from them
Point Estimate
A single estimate of some population value (such as a percentage, a correlation, or a difference) based on data from a sample
Hypothesis
A statement of the specific result or outcome the researcher expects to observe from a particular study, if the theory is accurate; also called a prediction
Theory
A statement or a set of statements that describes general principles about how variables relate to one another; build upon measured observations and accumulated knowledge from testing predictions
Claim
A statement or argument someone is trying to make about some psychological process/construct
Sum of Squares (SS)
A statistical measure of deviation from the mean; also called sum of squared deviations
Measured Variable
A variable in a study whose levels (values) are observed and recorded
Manipulated Variable
A variable in an experiment that a researcher controls, such as by assigning participants to its different levels (values)
Moderator
A variable that modifies the strength and/or direction of the association between the independent variable and the dependent variable Occurs when the relationship between two variables changes in strength depending on the level of a third variable
Quantitative (Continuous) Variables
A variable whose values can be recorded as meaningful numbers
Meta-Analysis
A way of mathematically averaging the effect sizes of all the studies that have tested the same variables to see what conclusion that whole body of evidence supports
What question should be asked using standard error of the estimate answers?
After we use X to predict Y, how much variability is left in Y?
If A and B are correlated, it could mean ___. A. A causes B or B causes A B. There is no causal relationship between A and B C. A and B are both caused by another factor C D. All of above
All of above
Outliers can ___. A. Increase r B. Decrease r C. Affect the amount of shared variability D. All of the above
All of the above
The theory-data cycle ___ A. Is a measure of how valid a theory is B. Allows researchers to refine their theories in response to new data C. Only concerns theories that make causal claims D. Is only used for applied research
Allows researchers to refine their theories in response to new data
What can cause type I errors when you say an effect exists that really doesn't?
Alpha level = type I error rate
Negative Correlation
An association in which high levels of one variable go with low levels of the other variable, and vice versa; also called inverse association or negative association
Constant
An attribute that could potentially vary, but that has only one level in the study in question
Variable
An attribute that varies, having at least two levels or values; anything that can change or be changed (any factor that can be manipulated, controlled for, or measured in a study)
Which of the following studies is correlational? A. A social psychologist tells some research participants that they need to hurry over to the next building to complete a study. She tells others that they can take their time. Then she observes whether they stop to help a research assistant who is pretending to be hurt B. A cognitive psychologist compares the ability of people to recall words that they were instructed to read with their ability to recall words that they were instructed to imagine C. An educational researcher compares the academic performance of students from the rich side of town with that of students from the poor side of town D. An automotive engineer installs different stick shifts in a new car prototype, each time asking several people to rate how comfortable the stick shift feels
An educational researcher compares the academic performance of students from the rich side of town with that of students from the poor side of town
Criterion Validity
An empirical form of validity measurement that establishes the extent to which a measure associated with a behavioral outcome with which it should be associated; also called predictive validity
Convergent Validity
An empirical test of the extent to which a self-report measure correlates with other measures of a theoretically similar construct
Discriminant Validity
An empirical test of the extent to which a self-report measure does not correlate strongly with measures of theoretically dissimilar constructs; also called divergent validity
Statistical Validity
An indication of how well the numbers support the claim; how strong the effect is and the precision of the estimate; takes into account whether the study has been replicated; the extent to which statistical conclusions derived from a study are accurate and reasonable; also called statistical conclusion validity How much uncertainty is in the data that led to the claim? Did the researcher do the right statistical test?
External Validity
An indication of how well the results of a study generalize to (represent) individuals or contexts besides those in the study itself Is this finding representative of other circumstances?
Null Hypothesis Significance Testing (NHST)
An inferential statistical technique in which a result is compared to a hypothetical population in which there is no relationship or no difference
How is a sampling method chosen?
Ask how important it is to have a sample that accurately represents the full spectrum of the target population If "not very important" → convenience sample If "sort of important" → simple random sample If "very important" → stratified random sample
What type of claim is this headline: "Associations Between Screen-Based Media Use and Brain White Matter Integrity in Preschool-Aged Children"? A. Frequency B. Association C. Causal
Association
What type of claim is this headline: "Unexpected Brain Structures Tied to Creativity, and to Stifling It"? A. Frequency B. Association C. Causal
Association
In one of her articles, Dr. LaSalle makes the claim: "Research shows that making more money correlates with spending less time talking with your spouse." Which type of claim is Dr. LaSalle making? A. Causal claim B. Anectodal claim C. Association claim D. Frequency claim
Association claim
When interpreting a correlation coefficient expressing the relationship between two variables, it is important not to ___. A. Choose X and Y values that are normally distributed B. Measure the values for X and Y independently C. Check the direction of the relationship D. Assume causality
Assume causality
When interpreting a correlation coefficient expressing the relationship between two variables, it is important not to ___. A. Measure the values for X and Y independently B. Choose X and Y values that are normally distributed C. Assume causality D. Check the direction of the relationship
Assume causality
The local news ran a story about a baby who suffered a deadly spider attack while playing outside. The neighborhood becomes quiet as families keep their kids inside so they won't be bitten by deadly spiders. This is an example of ___ A. No comparison group B. The good story C. Availability heuristic D. Cherry-picking
Availability heuristic
Interpretation of SD
Average amount by which scores deviate from the mean
If we computed a regression equation for the two scatterplots in the figure, which would have a higher R²? A. A would have a higher R² B. B would have a higher R² C. The R² values would be the same for the two scatterplots D. R² is undefined for a perfect relationship
B would have a higher R²
What type of graph should be used if IV and DV are nominal or ordinal?
Bar plot
What do the different columns of a z-score table represent?
Column A: Z-score Column B: Proportion of data between the mean and the z-score Column C: Proportion of data beyond the z-score
Calculate the deviation from the mean for the following observed scores: 23, 14, 17, 12, 19, 23. The mean is 18.
Deviation from mean = Xi — X̅ 23 — 18 = 5 14 — 18 = -4 17 —18 = -1 12 — 18 = -6 19 — 18 = 1 23 — 18 = 5 The average deviation from the mean cannot quantify overall variability The mean of all deviation scores will always be zero Mean as a balance point means that the points are evenly distributed around the mean The total negative deviation will always equal the same amount as the total positive deviation ∑(negative deviations) = ∑(positive deviations)
What is meant by the characteristic of exhaustiveness in the frequency table bins? A. Outliers are included B. Each items fits in no more than one bin C. Every item fits into a bin D. Each bin has the same range
Every item fits into a bin
The researcher decides to manipulate sleep. She then finds out that only 5% of the children's families are willing to participate. The change in study design reflects a decrease of ___ validity, and an increase in ___ validity A. Internal; external B. External; internal C. Statistical; internal D. Construct; statistical
External; internal
You work for a company that is developing a new phone application that helps students make and track progress on health goals. After its first month available for download, your team leader wants you to summarize data about your app. How could you summarize where students heard about the app (friend, advertisement, etc)? How could you best summarize number of goals users make? A. Mode B. Median C. Mean D. I need to see the histogram first
I need to see the histogram first (not sure if unimodal)
In order to measure motivation, Dr. Maine designs a survey with six items, all of which try to capture that construct. What reliability does Dr. Maine need to test? A. Test-retest B. Interrater C. Internal D. None of the above
Internal
___ is used when the observers are rating a categorical variable
Kappa
Jiung is conducting a study that involves observing a child's reaction when his/her mother plays with another sibling. He is conducting his study in a controlled laboratory setting and has trained all his research assistants for observation coding with a detailed manual that included a literature review on the topic and his hypotheses for the study. Should he have included information about hypotheses in his coding manual? A. Yes, this limits observer bias B. Yes, this limits observer effects C. No, a masked design would be better D. No, you should only convey hypotheses to coders in a naturalistic observational study E. It would not matter as long as the coders do not interact with the participants
No, a masked design would be better
Reactivity
Participants may act differently if they know they are being observed Not the same as observer effects The observer is not cuing a specific behavior, but their presence is altering natural behavior (can even occur in double-blinded studies)
Theorists
People who develop theories to explain how humans think, feel, and behave
Empiricists
People who rely on empiricism to test the theories
The process of ___ makes research self-correcting
Publication
Mean Absolute Deviation (M.A.D)
Quantifies the mean of the absolute deviation Ex: 5 + 4 + 1 + 6 + 1 + 5 = 22 → M.A.D = 22/6 = 3.67
What is the purpose of score bins?
Score bins are a way to condense data when there are too many distinct values to include in a normal frequency table
Negative Deviation
Scores less than the mean
Temporal Precedence
Second of three criteria for establishing a causal claim, stating that the proposed causal variable comes first in time, before the proposed outcome variable
Journalism
Secondhand news or commentary published or broadcast in the popular media and produced for a general audience
Cherry-Picking
Selecting information that supports a particular position, usually a controversial one
What are the similarities and differences between R² and r²?
Similarities: 1. Unitless 2. Range from 0 to 1 Differences: 1. Refer to r² when talking about the square of a correlation coefficient 2. Refer to R² when talking about variance accounted for in a multivariable regression
What are the similarities and differences between mediators and third variables?
Similarities: 1. Both involve multivariate research designs 2. Both can be detected using multiple regression Differences: 1. Third variables are external to the bivariate correlation (problematic) and are regarded as a nuisance and not of interest to researchers 2. Mediators are internal to the causal variable (not problematic) and are regarded as a mechanism that is of great interest to researchers
You would like to study whether people eat more when they distract themselves with their phone while eating. You decide to randomly choose five fast food restaurants where you'll observe the amount ordered, what someone does while eating, and how much they ate. If you do all the coding of behavior and know the hypothesis of the study, this would be a ___. A. Unblinded study B. Single-blind study C. Double-blind study
Single-blind study
Z-scores talk about data in terms of distance in ___ from the mean, and initial units are ignored
Standard deviations (SDs)
What are the steps of the theory-data cycle?
Step 1: Theory leads the researcher to pose particular research questions Step 2: Research questions lead to an appropriate research design Step 3: Research design is used to test a specific hypothesis Step 4: Hypothesis is ideally preregistered before the researcher collects and analyzes data Step 5: Data is used to feed back into the cycle Step 6: Supporting data strengthens the theory (support of theory) Step 6: Nonsupporting data leads to revised theories or improved research design (revision of theory)
The ___ the relationship between two variables, the more accurate the prediction will be; the ___ the relationship between two variables, the less accurate the prediction will be
Stronger; weaker
Construct validity can be assessed ___ and ___
Subjectively; empirically
I obtain contact information for all older adults in the U.S. between 60-80 years old that have a landline or cellphone. I want to survey 2000 of them. I shuffle the record list and assign them all numbers. I then pick two numbers out of a hat: 198854 and 153. I start at the 198854th name on the list and pick every 153rd record intil I get to 2000 names. What kind of sampling am I doing? A. Cluster sample B. Multi-stage cluster sample C. Simple random sample D. Systematic sample
Systematic sample
Positive (Right) Skewed
Tail is on the right and peak is on the left
Test-Retest Reliability
The consistency in results every time a measure is used Consistency over time
What does the curve of a distribution represent?
The curve of a distribution represents the probabilistic density function, p(x), which is the probability of the variable taking the value x
Theory-Data Cycle
The cycle in which scientists collect data to test, change, or update their theories
Interrater Reliability
The degree to which two or more coders or observers give consistent ratings of a set of targets Consistency across different raters
Regression Lines
The line of best fit drawn through a correlation scatterplot Correlations tell us that two variables are linearly related and how strong the relationship is They do not help us predict the actual values of the variables in a new situation
What is the method section of an empirical journal article?
The section that explains in detail how the researchers conducted the study; contains subsections (participants, materials, procedure, and apparatus)
Bias Blind Spot
The tendency for people to think that compared to others, they themselves are less likely to engage in biased reasoning
True or false: "Multivariate designs cannot be used to establish the case for causation." A. True B. False
True
How can scatterplots show test-retest reliability?
Two measurements should expect to be about the same, so the dots on the scatterplot should all fall exactly on or close to the line to indicate high test-retest reliability
What is the purpose of inferential statistics?
Use data from a sample to infer general patterns and conclusions about a population
Dr. Johnson is surveying to understand people's attitude towards government's new health policy. She is worried that people might show fence-sitting behavior. Which of the following is an ideal approach to create the survey if she would like it to use a likert scale response format? A. Use double-barreled question B. Word the question so that it leads to a certain response C. Use even number of response options on the scale D. Use double negatives
Use even number of response options on the scale
In a scatterplot, predictive errors are associated with ___. A. Discrepancies between dots and the regression line B. Vertical discrepancies between dots and the regression line C. Horizontal discrepancies between dots and the regression line D. Either vertical or horizontal discrepancies between dots and the regression line
Vertical discrepancies between dots and the regression line
If the distribution of ages for college students has a mean of 23.74 and a standard deviation of 3.19, the latter number (3.19) is expressed in units of? A. Years B. Squared years C. Square root of years D. Nothing, since 3.19 is a pure number (without units)
Years
What do z-scores indicate?
Z-scores indicate how many standard deviations a score is above or below the mean of its distribution
How is "b" computed for the least squares equation?
b = r√(SSy/SSx) SSy = SS for the variable being predicted SSx = SS for the predictor variable
What is the calculation for area under the curve for normal distributions?
p(x) = (1/σ√2π)e^-(x — µ)²/2σ²
What is the calculation for area under the curve for standard normal distributions?
p(x) = (1/√2π)e^-(x²/2)
___ is used to evaluate interrater reliability when the observers are rating a quantitative variable
r
Least Squares Regression Equation
yi = bxi + a yi = Predicted value of yi b = Estimated slope of Y (b) times value of xi a = Estimated intercept of Y If we know the slope and intercept of Y, we can predict different Y-values from their corresponding X-values
Suppose we have a sample of participants, and each reported their height and weight. We correlate their height with weight twice, first time using foot as the unit and second time using inch as the unit. We use weight to predict height twice, first time using foot as the unit and second time using inch as the unit. Second slope will be 12 x of the first slope. Weight + 1 pound = height + 0.04 foot should translate into height + 0.48 inch. What is the predicted score at x = 40 using the regression prediction line: yi = (1,91(xi + 1.18?
yi' = (1.01 * 40) + 1.18 = 41.5
What is the calculation for z-scores?
z = (Xi — X̅)/s z = Z-score Xi = Score needed to be converted to a z-score (raw scores of interest) X̅ = Mean of the distribution s = Standard deviation of the distribution
In a standard normal curve, about 68% of values lie between what two z-scores? A. -3 and 3 B. -2 and 2 C. -1 and 1 D. -0.5 and 0.5
-1 and 1
In the correlation matrix, what is the pearson r between "Fruit Per Day" and "Steps Per Day"? A. .025 B. .698 C. 1 D. 250
.025
Why is it important to be cautious about basing beliefs on what authorities say?
1. Authorities can also be biased and base their advice on their own experience or intuition, presenting only studies that support their own side 2. It is difficult to determine what is considered "expert" enough for the truth 3. Authority in one domain does not often transfer to others, which can trick us 4. Not all research is equally reliable because the study may have been conducted poorly
How can being swayed by a good story or accepting a conclusion just because it makes sense be problematic?
1. Empirical evidence may contradict what your common sense tells you 2. While a good story may be convincing, it is not always an accurate source of information
Why can't studies prove theories?
1. Empiricists avoid inferences they can't support with direct observation Ex: Every raven a person has ever seen is black; however, that does not prove that all ravens are black because that person has not observed all possible ravens, so there is a possibility that a nonblack raven exists 2. If a single study's data supports a theory, we do not say that that the data proves the theory; we say that the data supports or are consistent with a theory 3. If a single study's data does not support a theory, we say that the data are inconsistent with a theory, and the study would be revised instead of rejected 4. A single confirming finding cannot prove a theory, just as a single disconfirming finding cannot allow researchers to scrap a theory 6. Scientists require a diverse and convincing set of observations before they completely abandon a viable theory
Why is basing conclusions on your experiences problematic?
1. Experience is a small set of possibilities with no comparison group 2. Daily life does not usually include comparison experiences 3. Experiences is confounded, which means that even if a change has occurred, the cause is not always known or identified because there can be several explanations for an outcome 4. In personal experiences, it is hard to isolate variables 5. One's own experience is only one point in that overall pattern and may not always align with the scientific conclusion
How can being misled by the media be prevented?
1. Find the original source and read it thoroughly 2. Maintain a skeptical mindset regarding popular sources and ask the right questions before accepting a writer's claim
How is research better than experience?
1. In a research setting, scientists can use careful controls to make sure they are changing only one factor at a time 2. The results of a single study is better evidence than experience 3. The results of behavioral research are probabilistic 4. Scientific conclusions are based on patterns that emerge only when researchers set up comparison groups and test many people
What is the role of a consumer of psychological science?
1. Read printed or online news stories based on research 2. Listen to talk shows or podcasts about research 3. Apply findings to own life 4. Interpret research data with a critical eye
What are some ways to avoid falling for disinformation?
1. Slow down 2. Cross-check 3. Read critically 4. Research the source
How can believing our own biases about being biased be problematic?
1. The bias blind spot makes us trust our faulty reasoning more, which can make it hard to initiate the scientific theory-data cycle 2. We tend to believe that we are less biased than we actually are
What is the variable and levels for the following example: "Most students don't know when news is fake"?
1. Variable: Knowing when news is fake 2. Levels: Knowing when news is fake and not knowing when news is fake
How is a good theory supported by data?
1. Without support from data, there is no evidence for an explanation 2. A single piece of evidence is poor support 3. Supporting data from multiple studies, multiple labs, and replication are crucial
Edited Book
A collection of chapters on a common topic, each chapter of which is written by a different contributor
Confounds
A general term for a potential alternative explanation for a research finding; a threat to internal validity; when more than one thing changes at a time that may have caused an outcome, and because they happened together and could have both caused the outcome, the cause is not known
Comparison Group
A group in an experiment whose levels on the independent variable differ from those of the treatment group in some intended and meaningful way; also called comparison condition
Preregistered
A term referring to a study in which, before collecting any data, the researcher has stated publicly what the study's outcome is expected to be
Constructs/Conceptual Variables
A variable of interest, stated at an abstract level, usually defined as part of a formal statement of a psychological theory (the name of the concept being studied)
Review Journal Articles
An article that summarizes all of the studies that have been published in one research area
Andrew and Olivia just finished their research project for class. They found that people with morning classes have a lower quality of sleep than those who have night classes; they conclude that morning classes are linked to poor sleep quality. Little did they know, everyone who takes morning classes in their sample drinks massive amounts of caffeine all day long and everyone with night classes never drink caffeine. What is wrong with their conclusion? A. They operationalized sleep quality poorly B. Caffeine intake is a confound C. They cherry-picked their data D. They do not have a comparison group
Caffeine intake is a confound
Dimitri is interested in understanding the effects of sleep deprivation on memory. Which of the following is an empirical approach Dimitri could take to answer this question? A. Ask his psychology teacher for his opinion on the effects of sleep deprivation on memory B. Design and execute a study that measures memory following different amounts of sleep C. Watch several fictional movies about sleep deprivation and use the characters' experiences to develop a story that makes sense D. Consider his own experiences with sleep and memory
Design and execute a study that measures memory following different amounts of sleep
Which of the following is true of the relationship between hypotheses and theories? A. Hypotheses are steps taken to determine if the theory is accurate B. Theories are used to determine if hypotheses are accurate C. Multiple theories are needed to test if a hypothesis is accurate D. Hypotheses and theories are synonymous terms E. None of the above
Hypotheses are steps taken to determine if the theory is accurate
Which of the following is not an example of being a producer of research? A. Administering a questionnaire of PTSD symptoms B. Conducting a study that involves observing the behavior of adolescents who have been bullied on social media C. Interpreting research about education for your local school board D. Measuring where the neurotransmitter dopamine is low in brains of patients with schizophrenia
Interpreting research about education for your local school board
Barry is studying the effects of a major natural disaster on people living nearby. He finds that many of the victims are depressed and show stress-related symptoms. Why can't Barry conclude that the natural disaster caused the depression and stress-related symptoms? A. No comparison group B. Depression and stress are confounds C. His explanation is a story with no data D. All of the above
No comparison group
Universalism
Scientific claims are evaluated according to their merit, independent of the researcher's credentials or reputation; the same preestablished criteria apply to all scientists and all research
Communality
Scientific knowledge is created by a community and its findings belong to the community
Organized Skepticism
Scientists question everything, including their own theories, widely accepted ideas, and ancient wisdom
Disinterestedness
Scientists strive to discover the truth; they are not swayed by conviction, idealism, politics, or profit
Vanessa claims that she sleeps better when she falls asleep to music. She has a comparison condition because she noticed that she does not listen to music every night, only when she remembers to plug in her ipod. She typically remembers to plug in her ipod on nights when she is able to finish studying earlier. What problem do you see in Vanessa's reasoning about sleeping better to music? A. Vanessa's belief that she sleeps better with music is not falsifiable B. Vanessa may be sleeping better because she is less distracted by studying/going to bed sooner C. Vanessa is biased because she sleeps in the same bed every night D. There is no problem with her reasoning
Vanessa may be sleeping better because she is less distracted by studying/going to bed sooner