exam 2 psych research methods
statistical significance
A researcher's assessment of whether a result from a sample (such as an association or a difference between groups) could have come from a population in which there is no association or no difference. When the sample's result is extreme, it would rarely be found in such a population and is said to be statistically significant. (page 214)
outlier
A score that stands out as either much higher or much lower than most of the other scores in a sample. (page 217)
multiple regression
A statistical technique that computes the relationship between a predictor variable and a criterion variable, controlling for other predictor variables. Also called multivariate regression. (page 244
t test
A statistical test used to evaluate the size and significance of the difference between two means. (page 209)
pilot study
A study completed before (or sometimes after) the study of primary interest, usually to test the effectiveness or characteristics of the manipulations. (page 300)
multivariate design
A study designed to test an association involving more than two measured variables. (page 238)
experiment
A study in which one variable is manipulated and the other is measured. (page 276)
design confound
A threat to internal validity in an experiment in which a second variable happens to vary systematically along with the independent variable and therefore is an alternative explanation for the results. (page 282)
selection effect
A threat to internal validity that occurs in an independent-groups design when the kinds of participants at one level of the independent variable are systematically different from those at the other level. (page 284)
practice effect
A type of order effect in which participants' performance improves over time because they become practiced at the dependent measure (not because of the manipulation or treatment). Also called fatigue effect. See also order effect, testing threat. (page 294)
T/F every experiment requires a control group
False (Often a clear control group does not exist or is not possible.)
T/F A multiple regression analysis that accounts for 3rd variables can establish causality
False Accounting for 3rd variables DOES NOT improve temporal precedence
systematic variability
In an experiment, a description of when the levels of a variable coincide in some predictable way with experimental group membership, creating a potential confound. See also unsystematic variability. (page 282)`
unsystematic variability
In an experiment, a description of when the levels of a variable fluctuate independently of experimental group membership, contributing to variability within groups. See also systematic variability. (page 282)`
control variable
In an experiment, a variable that a researcher holds constant on purpose. (page 278)
manipulation check
In an experiment, an extra dependent variable researchers can include to determine how well a manipulation worked. (page 299)
Match each example to the type of variability it represents. Travis is comparing the effects of upbeat music and slow music on task productivity. His research assistants tell him they really enjoy the upbeat music condition.
Systematic variability (It seems the upbeat music is having an unintended effect of causing the research assistants to be in a better mood, which could affect the participants. This change in mood is only associated with one condition.)
random assignment
The use of a random method (e.g., flipping a coin) to assign participants into different experimental groups. (page 284)
criterion variable
The variable in a multiple-regression analysis that the researchers are most interested in understanding or predicting. Also called dependent variable. (page 247)
what is this describing? occurs when a 3rd variable explains association between 2 others
spurious association
condition
One of the levels of the independent variable in an experiment. (page 277)
spurious association
A bivariate association that is attributable only to systematic mean differences on subgroups within the sample; the original association is not present within the subgroups. (page 224)
mean
An arithmethic average; 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. (page 208)
curvilinear association
An association between two variables which is not a straight line; instead, as one variable increases, the level of the other variable increases and then decreases (or vice versa). See also positive association, negative association, zero association.
parsimony
The degree to which a theory provides the simplest explanation of some phenomenon. In the context of investigating a claim, the simplest explanation of a pattern of data; the best explanation that requires making the fewest exceptions or qualifications. (page 256)
power
The likelihood that a study will show a statistically significant result when an independent variable truly has an effect in the population; the probability of not making a Type II error. (page 293)
effect size
The magnitude, or strength, of a relationship between two or more variables. (page 211)
treatment group
The participants in an experiment who are exposed to the level of the independent variable that involves a medication, therapy, or intervention. (page 280)
T/F every experiment requires a comparison group
True (Without comparison, one cannot be sure the independent variable is truly affecting the dependent variable, which hinders internal validity.)
T/F if the manipulation of the independent variable causes a change in the dependent variable covariance is established
True (Without manipulation, change cannot be measured.)
T/F The largest beta in a multiple regression analysis is the predictor that has the strongest relationship with criterion variable
True (the predictor variable with the highest beta explains the most variance associated with the criterion variable and therefore will have the largest influence on it)
T/F A multiple regression analysis can control for more than one variable at once
True (a multiple regression analysis can handle numerous predictor variables but only one criterion)
error associated with systematic variability
Type I error (Systematic variability can often make a manipulation appear to have an effect where there is actually none.)
error associated with unsystematic variability
Type II error (Unsystematic variability can obscure the experiment's effects, but is not considered a confound.)
Rebecca is interested in how solving different types of puzzles influences creativity. She will have participants try four different puzzles (word, 3-D, 2-D, and number) and measure creativity after each puzzle. To prevent order effects, Rebecca will sort participants into groups and have each group do the puzzles in a different sequence. The first sequence will be word, 3-D, 2-D, number; while the second will be 3-D, 2-D, number, word; and so forth, until each possible condition falls in each position in the experiment. What technique has Rebecca used to prevent order effects?
latin square (In this example, the puzzles were ordered so that each level of the independent variable appears in each position at least once.)
Match each example to the type of variability it represents. Marcos is testing how performance in video games affects aggression; he randomly assigns participants to play either an easy video game or a difficult video game. Some of his participants have never played video games before.
unsystematic variability (As long as the novice players are not concentrated in one condition, there is no systematic error being introduced. Random assignment should distribute any individual differences evenly between the conditions.)
The larger the sample size....
(1,000 or more) the less likely it is that findings may have resulted from chance
One way to test an association claim is with a __1__ ___1__. This test compares _2___ varaibles, and the results of the test have 2 primary components. The first component, often referred to as, _3___ tells you whether the association is positive or negative. The second component relates to how closely the variables are associated and is referred to as __4__.
1. bivariate correlation 2. two 3. direction 4. strength
When an independent variable is manipulated, the experiment uses several different groups. A ___1___ group is a group that is not changed or manipulated in any way. Any group where something is changed or altered is known as a ___2__ group. A group in which participants are given an inert manipulation is known as a __3__group. These groups help reduce alternative explanations for experimental results, or _4___.
1. control 2.treatment 3. placebo 4.confounds
In a __1___, a measure recorded earlier is associated with different variable measured later. In a __2____, two measured variables recorded at the same time are associated. If one variable measured earlier is associated with the measurement of the same variable taken later, this is called an __3____. These three types of correlations are usually found in _4____ designs.
1. cross lag correlation 2.cross sectional correlation 3. autocorrelation 4. longitudnial
When researchers inadvertently create a flaw in their experiment that is a threat to internal validity, it is known as a __1___. If these flaws coincide with the experimental manipulation and call into question whether or not the manipulation or the flaws affected the dependent variable, this is known as __2___. If the flawed part of the experiment does not coincide with a specific group, and is introduced at random, this is known as __3___ and does not necessarily pose a threat to internal validity.
1. design confound 2. systematic variability 3. unsystematic variability (While researchers should be as careful as possible when designing an experiment, not all variability is a threat to internal validity.)
A(n) _1___ _1___ describes the strength of an association between variables, and in correlations it is typically measured by the _2_ _2__. The term __3___ __3__ refers to the conclusion a researcher makes on whether or not results were due to chance, and it is measured by the _4__ __4__.
1. effect size 2. r- value 3. statistical significance 4. p-value
Fill in the blanks to complete the passage. { A within-groups design is when each participant experiences all levels of the _1___. There are two types of this design. The _2___ design is where participants are exposed to various levels of the independent variable and tested on the dependent variable after each exposure. The second is the _3___ design where participants interact with the various levels of the independent variable simultaneously.
1. independent variable 2. repeated measures 3. concurrent measures
A ___1___ is conducted over a longer period of time than a typical association claim and can help establish _2____. A __3___ considers more than two variables in the same analysis and can help improve __4_.
1. longitudinal study 2. temporal evidence 3. multiple regression analysis 4. internal validity
An __1__ is an extreme data point that can often inaccurately alter effect size. A ___2___ is when all scores are not accounted for, which can often inaccurately decrease effect size. A _3_____ is when a set of data is not well represented by a straight line and can often result in a __4___ effect size. All three of these issues can decrease.
1. outlier 2. restriction of range 3. curvilinear relationship 4. zero
Multiple regression can help eliminate internal validity problems by __1__ potential third variables. It also sets a _2___ variable that acts as the independent variable, or the variable that will influence another variable; and a _3__ variable acts as a dependent variable, or the variable that is hypothesized to be affected by another variable. Effect sizes in multiple regression analyses are represented by __4_, which is a standardized effect size, and _5__, which is an unstandardized effect size.
1.controlling for 2.predictor 3. criterion 4.beta 5. b
placebo group
A control group in an experiment that is exposed to an inert treatment, such as a sugar pill. Also called placebo control group. (page 280)
demand characteristic
A cue that leads participants to guess a study's hypotheses or goals; a threat to internal validity. Also called experimental demand. (page 297)
Latin square
A formal system of partial counterbalancing to ensure that every condition in a within-groups design appears in each position at least once. (page 296)
confound
A general term for a potential alternative explanation for a research finding; a threat to internal validity. (page 281)
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. (page 279)
control group
A level of an independent variable that is intended to represent "no treatment" or a neutral condition. Also called control condition. (page 280)
full counterbalancing
A method of counterbalancing in which all possible condition orders are represented. See also counterbalancing, partial counterbalancing. (page 295)
partial counterbalancing
A method of counterbalancing in which some, but not all, of the possible condition orders are represented. See also counterbalancing, full counterbalancing. (page 296)
longitudinal design
A study in which the same variables are measured in the same people at different points in time. (page 239)
carryover effect
A type of order effect, in which some form of contamination carries over from one condition to the next. (page 294)
measured variable
A variable in a study whose levels (values) are observed and recorded. See also manipulated variable. (page 277)
manipulated variable
A variable in an experiment that a researcher controls, such as by assigning participants to its different levels (values). See also measured variable. (page 276)
predictor variable
A variable in multiple-regression analysis that is used to explain variance in the criterion variable. Also called independent variable. (page 248)
mediator
A variable that helps explain the relationship between two other variables. Also called mediating variable. (page 259)
moderator
A variable that, depending on its level, changes the relationship between two other variables. (page 228)
bivariate correlation
An association that involves exactly two variables. Also called bivariate association. (page 204)
one-group, pretest/posttest design
An experiment in which a researcher recruits one group of participants; measures them on a pretest; exposes them to a treatment, intervention, or change; and then measures them on a posttest. (page 313)
concurrent-measures design
An experiment using a within-groups design in which participants are exposed to all the levels of an independent variable at roughly the same time, and a single attitudinal or behavioral preference is the dependent variable. (page 291)
repeated-measures design
An experiment using a within-groups design in which participants respond to a dependent variable more than once, after exposure to each level of the independent variable. (page 290)
pretest/posttest design
An experiment using an independent-groups design in which participants are tested on the key dependent variable twice: once before and once after exposure to the independent variable. (page 288)
posttest-only design
An experiment using an independentgroups design in which participants are tested on the dependent variable only once. Also called equivalent groups, posttest-only design. (page 287)
independent-groups design
An experimental design in which different groups of participants are exposed to different levels of the independent variable, such that each participant experiences only one level of the independent variable. Also called between-subjects design or between-groups design. (page 287)
within-groups design
An experimental design in which each participant is presented with all levels of the independent variable. Also called within-subjects design. (page 287)
matched groups
An experimental design technique in which participants who are similar on some measured variable are grouped into sets; the members of each matched set are then randomly assigned to different experimental conditions. Also called matching. (page 286)
Read the study and determine whether or not each description applies. Mariah is testing whether or not loud music causes people to drive more recklessly. Mariah flips a coin for each participant and places everyone who got heads into one group and everyone who got tails into the other. All participants complete a driving simulator course that measures their speeds and number of mistakes. Mariah then has one group listen to a rock song at a very loud volume, and the other at a lower volume. After listening to the song, participants once again complete the driving simulator course.
Applies: -random assignment (Using the results of a coin toss to place participants in a group is a form of random assignment.) -independent groups design (Different participants were placed in each level of the independent variable.) -pretest/posttest design (Mariah pretested participants' driving ability to look for change in response to the level of music.) Does Not Apply: -within groups design (No participant experienced all levels of the independent variable.) -matched groups (The participants were randomly assigned and not matched on any one attribute.) -posttest-only design (The dependent variables of driving behavior were measured before and after the manipulation)
Rhonda recently collected survey data and was curious about the association claim between gender and externalizing symptoms of mental illness. She found the following correlation between the two variables: r- -.47, p=.02 Pick what applies and what does not apply to this -significant -nonsignificant -strong -negative -categorical -positive -moderate
Applies: -significant (This result is significant; it did not happen by chance) -strong (A large effect shows that the two variables are closely related.) -negative (In this case, the relationship shows that as externalizing symptoms increase in one gender, they likely decrease in the other.) -categorical (In this example, gender is a categorical variable, while symptoms are a measured variable.) Does Not Apply: -nonsignificant (Because the p value is less than .05, this result would be considered significant.) -positive (In this example, the r value is a negative .47.) -moderate (An effect size around .5 is typically considered strong. A correlation has multiple different aspects, each of which points out an important part of the relationship.)
Clarissa has collected some longitudinal data at two time points, one year apart, to measure self esteem and social media usage. She finds the following correlations: Correlation 1: Social media usage at Time 1 was negatively correlated with self-esteem at Time 1. Correlation 2: Social media usage at Time 1 was positively correlated with self-esteem at Time 2. Correlation 3: Social media usage at Time 1 was positively correlated with social media usage at Time 2. Match each of Clarissa's correlations to the type of correlation it represents.
Correlation 1 -> cross sectional correlation (this correlation shows how the 2 variables are related to each other at one point in time) Correlation 2-> cross-lag correlation (correlation shows how social media usage in the past would be related to variables in the future) Correlation 3-> Autocorrelation (This correlation shows how a variable might be related to itself at a different point in time)
T/F manipulating the independent variable establishes temporal precedence
False (The manipulated variable must also come before the dependent variable is measured in order to establish temporal precedence, manipulation alone will not surfice. The requirements of causality can be satisfied by an experiment, but the experiment must be designed correctly.)
T/F Multiple regression can establish temporal precedence as long as the predictor variable was collected before the criterion variable
Falso (the order of collection CANNOT assure temporal precedence) (multiple regression can improve the case for causality, but it CANNOT assure it)
control for
Holding a potential third variable at a constant level (statistically or experimentally) while investigating the association between two other variables. See also control variable, multiple regression. (page 245)
restriction of range
In a bivariate correlation, the absence of a full range of possible scores on one of the variables, so the relationship from the sample underestimates the true correlation. (page 218)
third-variable problem
In a correlational study, the existence of a plausible alternative explanation for the association between two variables. See also internal validity. (page 222)
directionality problem
In a correlational study, the occurrence of both variables being measured around the same time, making it unclear which variable in the association came first. See also temporal precedence. (page 221)
cross-lag correlation
In a longitudinal design, a correlation between an earlier measure of one variable and a later measure of another variable. (page 241)
cross-sectional correlation
In a longitudinal design, a correlation between two variables that are measured at the same time. (page 239)
autocorrelation
In a longitudinal design, the correlation of one variable with itself, measured at two different times. (page 240)
order effect
In a within-groups design, a threat to internal validity in which exposure to one condition changes participant responses to a later condition. See also carryover effect, practice effect, testing threat. (page 294)
independent variable
In an experiment, a variable that is manipulated. In a multiple-regression analysis, a predictor variable used to explain variance in the criterion variable. See also dependent variable. (page 277
dependent variable
In an experiment, the variable that is measured. In a multiple-regression analysis, the single outcome, or criterion variable, the researchers are most interested in understanding or predicting. Also called outcome variable. See also independent variable. (page 277)
Match each type of validity to how important it is when interrogating an association claim. (Least, very, and somewhat important) internal validity construct validity external validity statistical validity
Least Important -> Internal validity (IV is not relevant in an association claim unless someone is attempting to turn it into a causal claim) Very Important -> Construct Validity (understanding how well the variables were measured is critical to understanding how strong the claim is) Very Important-> Statistical Validity (bc many different aspects can affect the statistics of an association claim, it is important to closely scrutinize results) Somewhat Important -> External Validity (is important in verifying if a claim generalizes to other populations, but not the nature of the claim itself)
Large sample sizes protects against....
abnormalities like outliers
What are these descriptions describing? -describes strength of a relationship between 2 or more variables -indicator of how important a relationship is
effect size
Yoshi is testing how being exposed to pictures of different types of foods affects sleepiness. Yoshi is showing each of his participants ten pictures of dessert, ten pictures of entrees, and ten pictures of salads, and he measures sleepiness after each group of ten pictures. To eliminate order effects, Yoshi is presenting all three types of food as well as all ten pictures in each group in a random order to each participant. What technique has Yoshi used to prevent order effects?
full counterbalancing (All three conditions are represented in some way to each participant)
counterbalancing
in a repeated-measures experiment, presenting the levels of the independent variable to participants in different sequences to control for order effects. See also full counterbalancing, partial counterbalancing. (page 295)
what does a strong effect size mean?
means that most data points will likely be near the prediction line, increasing the likelihood of an accurate prediction
what is this describing? add nuance to association claims without challenging the internal validity of those claims
moderators
Match each example to the type of variability it represents. Shilpa wants to measure the positive effects of shopping online versus shopping in person. She recruits participants from a message board focused on online shopping and randomly assigns them to either buy three things online or three things in a store and then complete her shopping attitude scale..
systematic variability (As all of the participants were already members of an online shopping group is likely that they will be more enthusiastic about online shopping than in-person shopping. She is only gathering confirmatory evidence.)
Match each example to the type of variability it represents. I Imani is doing a study on sociability in college students,with participants either one-on-one or in small groups. She later finds out that one of her research assistants is much chattier than the others.
unsystematic variability (While this still could be an issue, it would be systematic variability only if this RA conducts one condition but not the other.)
can a moderate correlation with a small sample size still be nonsignificant?
yes it can, as the sample is not big enough to guarantee that the results were not due to chance