Research Methods Psych 344 Morling
normally distributed
A function that represents the distribution of variables as a symmetrical bell-shaped graph.
Informed consent
-typical elements of consent forms >nature of study, primary investigators >risk and benefits of participation >voluntary nature of participation >information about confidentiality
a census.
A complete enumeration of a population.
Stratified random sampling differs from cluster sampling in two ways.
First, strata are meaningful categories (such as ethnic or religious groups), whereas clusters are more arbitrary (any random set of hockey games or high schools would do). Second, the final sample sizes of the strata reflect their proportion in the population, whereas clusters are not selected with such proportions in mind.
purposive sampling
If researchers want to study only certain kinds of people, they recruit only those particular participants. This is done in a nonrandom way
Is Pretest/Posttest a Repeated-Measures Design?
In a true repeated-measures design, participants are exposed to all levels of a meaningful independent variable ->The levels of such independent variables can also be counterbalanced. In contrast, in a pretest/posttest design, participants see only one level of the independent variable, not all levels
Reasons why people would respond inaccurately
People might give inaccurate answers because they don't make an effort to think about each question, because they want to look good, or because they are simply unable to report accurately about their own motivations and memories.
Do NOT use this word in science
Prove **data support or are consistent with a theory, or they might say that some data are inconsistent with or complicate a theory
How can researchers tell the difference between a respondent who is yea-saying and one who really does agree with all the items?
The most common way is by including reverse-worded items- slows person down A drawback of reverse-wording is that sometimes the result is negatively worded items, which are more difficult to answer.
dependent variable
The outcome factor; the variable that may change in response to manipulations of the independent variable.
predictor variables
The rest of the variables measured in a regression analysis, or independent variables.
Type 1 error
a study might mistakenly conclude, based on the results from a sample of people, that there is an association between two variables, when there really is no association in the full population. Careful researchers try to minimize the chances of making this kind of mistake, known as a "false positive"
unbiased sample, also called a representative sample
all members of the population have an equal chance of being included in the sample.
confederate
an actor playing a specific role for the experimenter.
positive association
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
Data
are a set of observations.
Frequency claims
describe a particular rate or degree of a single variable. **The best way to identify frequency claims is that they focus on only one variable
bimodal
two peaks
A physiological measure
operationalizes a variable by recording biological data, such as brain activity, hormone levels, or heart rate. Physiological measures usually require the use of equipment to amplify, record, and analyze biological data.
Control Variables
researchers control potential third variables (or nuisance variables) in their studies by holding all other factors constant between the levels of the independent variable. *variable that an experimenter holds constant on purpose **Important for establishing internal validity
Ways to get a biased sample
researchers might study only those they can contact conveniently, or only those who volunteer to respond. These two biases can threaten the external validity of a study because people
association claim define
the association between one version of the measure and another, between one coder and another, or between an earlier time and a later time
Bias Reasoning: Being persuaded by what comes easily to mind
the availability heuristic, which states that things that pop up easily in our mind tend to guide our thinking -example: death by shark attack is more memorable so people think about it more and inflate risk **can lead to overestimation
evidence-based treatments
that is, therapies that are supported by research
3 criteria for causality
1. covariance 2. temporal precedence 3. internal validity
experiment
A research method in which an investigator manipulates one or more factors to observe the effect on some behavior or mental process, which another variable is measured
Conditions
A study's independent variable should not be confused with its levels (conditions)
Construct Validity: How Well Were the Variables Measured and Manipulated? (IV and DV)
DV: How well was it measured? IV: How well was it manipulated/operationalized? ->A manipulation check is an extra dependent variable that researchers can insert into an experiment to convince them that their experimental manipulation worked. (more likely to be used when the intention is to make participants think or feel certain ways) ->pilot study is a simple study, using a separate group of participants, that is completed before (or sometimes after) conducting the study of primary interest. ***confirm the effectiveness of their manipulations
Internal Validity: Are There Alternative Explanations for the Results?
Fundamental internal validity questions 1. Did the experimental design ensure that there were no design confounds, or did some other variable accidentally covary along with the intended independent variable? 2. If the experimenters used an independent-groups design, did they control for selection effects by using random assignment or matching? 3. If the experimenters used a within-groups design, did they control for order effects by counterbalancing?
External Validity: To Whom or What Can the Causal Claim Generalize?
GENERALIZING TO OTHER PEOPLE -When you interrogate external validity, you ask about random sampling—randomly gathering a sample from a population. (In contrast, when you interrogate internal validity, you ask about random assignment— randomly assigning each participant in a sample into one experimental group or another.) GENERALIZING TO OTHER SITUATIONS -To decide whether an experiment's results can generalize to other situations, it is sometimes necessary to consider the results of other research. WHAT IF EXTERNAL VALIDITY IS POOR? -in an experiment, researchers usually prioritize experimental control (internal validity) -->To get a clean, confound-free manipulation, they may have to conduct their study in an artificial environment like a university laboratory. Such locations may not represent situations in the real world. Although it's possible to achieve both internal and external validity in a single study, doing so can be difficult. Therefore, many experimenters decide to sacrifice real-world representativeness for internal validity.
DO not believe everything people say, even when authority
However, you should be cautious about basing your beliefs on what everybody says—even when the claim is made by someone who is (or claims to be) an authority. **Did the authority systematically and objectively compare different conditions, as a researcher would do? Or maybe they have read the research and are interpreting it for you; they might be practitioners who are basing their conclusions on empirical evidence. **not all research is equally reliable. The research an expert uses to support his or her argument might have been conducted poorly.
Are the characteristics that make the sample biased actually relevant to what you are measuring?
In certain cases, it's reasonable to trust the reports of unrepresentative samples.
strength of the relationship
In general, the relationship is strong when dots are close to the line; it is weak when dots are spread out.
Step 3: CALCULATE THE PROBABILITY OF GETTING SUCH DATA, OR EVEN MORE EXTREME DATA, IF THE NULL HYPOTHESIS IS TRUE
In making the calculations, we used what we know about the variable—that it is normally distributed with a mean and a standard deviation—to estimate what percentage of people would have each range of values We also used our understanding of chance.
Construct validity of causal claims
In operationalizing manipulated variables, researchers must create a specific task or situation that will represent each level of the variable.
Mediators vs. Third Variables
Mediators appear similar to third-variable explanations. Both of them involve multivariate research designs, and researchers use the same statistical tool (multiple regression) to detect them. However, they are different: -In a third-variable explanation, the proposed third variable is external to the two variables in the original bivariate correlation; it might even be seen as an accident—a problematic "lurking variable" that potentially distracts from the relationship of interest. --> relationship is there only because both of those variables happen to vary with the outside third variable -In contrast, when researchers propose a mediator, they are interested in isolating which aspect of the presumed causal variable is responsible for that relationship. -->A mediator variable is internal to the causal variable and often of direct interest to the researchers, rather than a nuisance.
PsycINFO
One comprehensive tool for sorting through the vast number of psychological research articles is a search engine and database *2.5 million records, mostly peer-reviewed articles. **that it shows other articles that have cited each target article and other articles each target article has cited. If you've found a great article for your project in PsychINFO, the "cited by" and "references" lists can be helpful for finding more papers just like it. *One disadvantage is that you cannot use PsycINFO unless your college or university library subscribes to it. Another challenge—true for any search—is translating your curiosity into the right keywords.
Internal Validity, controlling for Ordering effects
Order effects happen when exposure to one level of the independent variable influences responses to the next level. -An order effect in a within-groups design is a confound, meaning that behavior at later levels of the independent variable might be caused not by the experimental manipulation, but rather by the sequence in which the conditions were experienced. --> Includes practice effects, also known as fatigue effects, in which a long sequence might lead participants to get better at the task, or to get tired or bored toward the end. --> Include carryover effects, in which some form of contamination carries over from one condition to the next. (ex: brushing teeth and then drinking orange juice)
READING WITH A PURPOSE: CHAPTERS AND REVIEW ARTICLES
Read headings: authors of chapters and review articles usually create headings that make sense for their particular topic. Therefore, a way to get a overview of a chapter or review article is by reading each heading.
cross-lag correlations
Show whether the earlier measure of one variable is associated with the later measure of the other variable. Cross-lag correlations thus address the directionality problem and help establish temporal precedence. By inspecting the cross-lag correlations in a longitudinal design, we can investigate how one variable correlates with another one over time—and therefore establish temporal precedence. *ex: In the Brummelman study, the cross-lag correlations show how strongly mothers' overvaluation at Time 1 is correlated with child narcissism later on, compared to how strongly child narcissism at Time 1 is correlated with mothers' overvaluation later on. Results: Because the "overvaluation to narcissism" correlations are significant and the "narcissism to overvaluation" correlations are not, this suggests the overvaluation, not the narcissism, came first.
Bias Reasoning: Failing to think about what we cannot see
The availability heuristic leads us to overestimate events, such as how frequently people encounter red lights or die in shark attacks. A related problem prevents us from seeing the relationship between an event and its outcome. *people don't seek out info that isn't there
independent variable
The experimental factor that is manipulated; the variable whose effect is being studied.
Benefit of Within Groups
The main advantage of a within-groups design is that it ensures the participants in the two groups will be equivalent. After all, they are the same participants! *only difference between the two conditions will be attributable to the independent variable **people act as "their own control" **within-groups designs also give researchers more power to notice differences between conditions. -->power refers to the probability that a study will show a statistically significant result when an independent variable truly has an effect in the population. -->If extraneous differences exist between two groups, too much unsystematic variability may be obscuring a true difference. *generally requires fewer participants overall= more efficient
Mean, Median and Mode... Which to use?
The mean is by far the most common measure of central tendency. However, when a set of scores contains a few extreme scores on one end, the median or mode may be a more accurate measure of central tendency.
Independent variable
The name comes from the fact that the researcher has some "independence" in assigning people to different levels of this variable.
Question Order
The order in which questions are asked can also affect the responses to a survey. The earlier questions can change the way respondents understand and answer the later questions.
Population vs. Sample
The population is the whole group while a sample are parts of the population.
OBSERVING FAMILIES IN THE EVENING
The researchers studied two aspects of family life: the emotional tone of the parents, and the topics of conversation during dinner. To code emotional tone, they watched the videos, rating each parent on a 7-point scale. The rating scale went from 1 (cold/hostile) to 4 (neutral) to 7 (warm/happy) The results from the Campos study showed that emotional tone in the families was slightly positive in the evening hours (around 4.2 on the 7-point scale). The kids were more likely to express distaste at the food, while the parents talked about how healthy it was
Correlation Coefficient r
The sign of r indicates the direction of the relationship. If r is positive, the relationship between the two variables is positive. If r is negative, the relationship between the two variables is negative. If r is zero, or very close to zero, then the relationship between the two variables is essentially zero. Magnitude matters as well= stronger association will have closer closer to + or - 1
Bias Reasoning: Focusing on the evidence we like best
The tendency to look only at information that agrees with what we already believe is called the confirmation bias. We "cherry-pick" the information we take in—seeking and accepting only the evidence that supports what we already think. ***confirmation bias operates in a way that is decidedly not scientific. **when people are asked to test a hypothesis, they tend to seek the evidence that supports their expectations
Beta Value
There will be one beta value for each predictor variable. Beta is similar to r, but it reveals more than r does. A positive beta, like a positive r, indicates a positive relationship between that predictor variable and the criterion variable, when the other predictor variables are statistically controlled for. A negative beta, like a negative r, indicates a negative relationship between two variables (when the other predictors are controlled for). A beta that is zero, or not significantly different from zero, represents no relationship (when the other predictors are controlled for). Betas are similar to correlations in that they denote the direction and strength of a relationship. The higher beta is, the stronger the relationship is between that predictor variable and the criterion variable. The smaller beta is, the weaker the relationship. *Unlike r, there are no quick guidelines for beta to indicate effect sizes that are weak, moderate, or strong. The reason is that betas change, depending on what other predictor variables are being used—being controlled for—in the regression.
validity
Validity refers to the appropriateness of a conclusion or decision, and in general, a valid claim is reasonable, accurate, and justifiable.
Beta steps
We assume there is no relationship in the population (Step 1). We collect some data and calculate beta (Step 2). We estimate the probability of getting the beta we got or one more extreme, if the null hypothesis is true (Step 3). We decide whether to reject or retain the null hypothesis (Step 4). Same as other tests
How do we decribe association between 2 variables?
We use scatterplots and r between two variables that are measured in the same set of cases.
External Validity: To Whom Can the Association Be Generalized?
When interrogating the external validity of an association claim, you ask whether the association can generalize to other people, places, and times. **As you interrogate external validity, recall that the size of the sample does not matter as much as the way the sample was selected from the population of interest. **A bivariate correlational study may not have used a random sample, but you should not automatically reject the association for that reason.
Type 2 Error
a "false negative" or "miss" Conclude something is false when it is actually true *could also be costly
Type 1 Error
a "false positive." Conclude something is true when it is not true **might be a costly mistake in terms of false hopes, unnecessary side effects, or fruitless follow-up research.
the criterion variable
choose the variable they are most interested in under- standing or predicting; dependent variable.
t test
allows researchers to test whether the difference between two group means in an independent-groups design is statistically significant.
Co-variance with Comparison Group
an experiment is a better source of information than your own experience because an experiment allows you to ask and answer: Compared to what? *if independent variables did not change, a study couldn't establish covariance *Results matter as well; cannot establish covariance if no relationship
mean
average
Empirical Reasoning
based on observation -the "key" to empirical reasoning is careful, logical, organized observation, measurement that is open to the scrutiny of others *authority isn't included Historical figures -Wundt- break down consciousness -Galton and the "power of prayer- pray for one person's health. Mean age of death for royal family was the lowest (not a random sample- could be genetic; small sample size and inbred)
empiricism involves...
basing beliefs on systematic information from the senses. To be an empiricist, you must also strive to interpret the data you collect in an objective way; you must guard against common biases.
Beta goes further than r
beta goes further than r because it usually represents the relationship between a predictor (independent) variable and a dependent variable, controlling for other variables.
Construct Validity:
how well was each variable measured? Ask Qs: good reliability? Is it measuring what it's intended to measure? What is the evidence for its face validity, its concurrent validity, its discriminant and convergent validity?
Statistical validity
called statistical conclusion validity, is the extent to which a study's statistical conclusions are accurate and reasonable. How well do the numbers support the claim? Statistical validity questions will vary depending on the claim.
reverse scoring
can tell if someone is sating yes/no to every question and not paying attention
statistical validity claims
how strong is the relationship?
To manipulate a variable
means to assign participants to be at one level or the other.
Random
occurring without any order or pattern.
Leading question
one whose wording leads people to a particular response because it explains why some people oppose the law.
results of an association with a categorical variable and quantitative variable
plot on a bar graph with the mean value
Animal Care Guidelines and the Three Rs.
•Replacement means researchers should find alternatives to animals in research when possible. -->For example, some studies can use computer simulations instead of animal subjects. • Refinement means researchers must modify experimental procedures and other aspects of animal care to minimize or eliminate animal distress. • Reduction means researchers should adopt experimental designs and procedures that require the fewest animal subjects possible. **In addition, the manual provides guidelines for housing facilities, diet, and other aspects of animal care in research. **The guide indicates which species must be housed in social groups and specifies cage sizes, temperature and humidity ranges, air quality, lighting and noise conditions, sanitation procedures, and enrichments such as toys and bedding.
Signs of Regression Analysis
"controlled for" is one common sign of a regression analysis. "taking into account" means the researchers conducted multiple-regression analyses. "even when other factors were considered" or "adjusting for" indicates the researchers used multiple regression.
multiple regression
(or multivariate regression), which can help rule out some third variables, thereby addressing some internal validity concerns.
Hypothesis-Generating Heurisitcs: paradoxical incident
- a seemingly contradictory event >ex: diffusion of responsibility -->bystander effect of the Genoveso SYndrome: The more bystanders in an emergency, the less likely to help ---> Psychologist Bibb Latane and John Darley
APA guidelines
-5 general principles to govern researchers, educators and practitioners 1. respect for persons 2. beneficence 3. justice 4.integrity- strive to be accurate and honest in one's role 5. fidelity and responsibility- accept responsibility for professional behavior
Deception
-Is deception allowed? >Yes, but it is a debated issues and the APA encourages researchers to avoid using deception procedures -->lies of omission vs commission >in the end, it comes down to the risks versus the benefits >Debriefing is absolutely essential
Peirce's (1877) Foundation "fixation" of Beliefs
-Method of authority >someone in authority said so >teachers, news, parents -Method of Tenacity >it's always been that way >hold onto beliefs even in the face of adversary -A priori method >personal logic and reason >sun revolving around earth (reasonable but wrong) -Scientific method and empirical reasoning >testing logic and reason; self correcting
Design Confound: Systematic Variability Is the Problem.
-Problem for internal validity only if it shows systematic variability with the independent variable. -However, if unsystematic variability (random or haphazard) across both groups, then their attitude would not be a confound. ->it can obscure, or make it difficult to detect differences in, the dependent variable -> shouldn't be called design confound *If individual differences are distributed evenly in both groups, they are not a confound.
Step 4: Reject or Accept Null
-Reject Null: The probability we obtained in Step 3 was so small that we rejected the null hypothesis assumption. (Statistically Significant) -Retain Null: could, in fact, happen by chance -Alpha level—the point at which researchers will decide whether the p is too high (and therefore will retain the null hypothesis) or very low (and therefore will reject the null hypothesis).
Hypothesis-Generating Heurisitcs: Analogical Thinking
-Using imagery to explain phenomena -ex: inoculation and resistance to propaganda
Justice
-a fair balance in terms of who participates in research and who benefits -if studying a specific population, should be appropriate justification
Hypothesis-Generating Heurisitcs: Serendipity
-a felicitous or lucky discovery -cockleburs and velcro -experimenter expectancy effect -rumor and paul-is-dead
History of Human Knowledge
-animism -mythology and religion (not natural forces, but deities) -astrological = human behavior -philosophy: assumption based on what is directly observed physiology and the physical sciences: Louis Pastore disproved that germs are spontaneously generated and Lister said that should perform antiseptic surgery (clean before surgery; Mayo Clinic practiced this)
Institutional review board (IRB)
-committee that ensures research involving human participants is conducted ethically -the IRB perform a risk-benefit analysis of prospective studies -most universities or institutions have their own IRB
Hypothesis-Generating Heurisitcs: account for conflicting results
-conflicts in the literature -ex: social facilitation
Respect for persons
-participants should be respected as individuals >informed consent >risks and benefits of participation >coercion
Research Misconduct
-data fabrication: instead of recording the actual data,inventing data -data falsification: influencing a study's results intentionally -Ex: in 1998, a physician published a study claiming a connection between autism and the measles vaccine >the research was highly respected and led to many parents refusing the shot >coincidentally, there was a significant increase in the number of cases of measles in the US and Europe >During an investigation in 2010, it was found that the author and his colleagues had altered facts about the children in his study
Beneficence
-doing "good" and trying to remove/prevent harm -careful consideration of risks and benefits to participants >are better treatments/interventions available? >wait list conditions in treatment studies >anonymity of participation
Cure and Tuskegee lying
-in 1945, penicillin became approved as the most effective treatment for syphilis -Tuskegee Institute did not provide any information about this new cure to the participats of the study because they wante to see the project to its end. the USPHS agreed -the study went on for decades with many of the participants getting sicker and dying. some of the men infected their wives and in some cases causing congenital syphilis
After effects of Tuskegee study
-in 1972, a whistleblower went to the press and the story became the front page news on the NY times. An investigation began. -they found that while the men voluntarily participated i the study, they weren't told about the real purpose of the study -in 1974, the US government ends up paying 9 million dollars to survivors and families of the Tuskegee experiment -in 1997, the US government issued an official apology on behalf of the nation
The Belmont Report
-in 1976, there was a panel held by a committee at the request of Congress to discuss what the basic tenets of ethical research should be -they outlined 3 overall principles: >respect for persons >beneficence >justice
Hypothesis-Generating Heurisitcs: Intensive case study
-in depth examination >ex: HM and anterograde amnesia >ex: autism -Used in >educational research >policymaking >organizational and management analysis -city and regional planning
Tuskegee Study
-in the 1920s, syphillis was a serious problem in the US, affecting Black men in poorer communities -in 1932, the US Public Health Service (USPHS) decided to collaborate with the Tuskegee Institute on a study of the effects of syphillis on Black men -600 men were recruited for the study, 400 with an existing syphilis infection - the study advertised providing medical treatment in echange for participation -> the men were told that they would be treated for "bad blood" - a local term used to describe physical ailments including syphilis, anemia and fatigue
Hypothesis-Generating Heurisitcs
-intensive case study -paradoxical incidents -analogies, metaphors and imagery -conflicting results -improve old ideas -serendipity -varied replication
Ethics
-moral principles and values that guide our behavior -APA states that it goals include the "welfare and protection of the individuals and groups with whom psychologists work" -what is considered ethical has changed throughout history
Preventing Type 2 errors (power, effect size, and alpha)
-power is the likelihood of not making a Type II error when the null hypothesis is false. *Alpha level: When researchers set alpha lower in a study, it will be more difficult for them to reject the null hypothesis. But if it is harder to reject the null hypothesis, it is also more likely that they will retain the null hypothesis even if it deserves to be rejected. Therefore, when researchers set the alpha level low (usually to avoid Type I errors), they increase the chances of making a Type II error. *Sample Size: a study that has a larger sample will have more power to reject the null hypothesis if there really is an effect in the population. *Effect Size: A third factor that influences power is the size of the effect in the population. All else being equal, when there is a large effect size in the population, there is a greater chance of conducting a study that rejects the null hypothesis. (larger effect size= easier to detect effects) *Sample Size and Effect Size: First, large samples are necessary when researchers are trying to detect a small effect size. In contrast, if researchers are confident in advance that they are trying to detect a large effect size, a small sample may be all that is necessary. (The second issue is that a small sample is more likely to return a fluke result that cannot be replicated.) *Degree of Unsystematic Variability: when a study's design introduces more unsystematic variability into the results, researchers have less power to detect effects that are really there. - caused by measurement error, irrelevant individual differences, and situation noise. -->Measurement error occurs when the variables are measured with a less precise instrument or with less careful coding. -->Irrelevant individual differences among study participants can obscure the difference between two groups and thus weaken power. Using a repeated- measures design in an experiment reduces the impact of individual differences and strengthens the study's power. -->Situation noise can weaken power by adding extraneous sources of variability into the results. *Statistical Choice: A researcher selects a statistical test (e.g., a sign test, a chi-square test, a t test, an F test, analysis of covariance, or multiple regression) to compute the results from a sample of data. Some of these tests make it more difficult to find significant results and thus increase the chance of Type II errors. Also "one-tailed" or a "two-tailed" test is an effecting choice.
What the Tuskegee Institute actually did
-the researcher decided to follow each man who was infected until they died in order to collect "valuable" information on the progression of the disease if left untreated -the only 'treatment" provided were medical tests to collect information on how symptoms were progressing -study went on for 40 years -during the project, 250 men registered to join the US military in WW2, but were told they needed to be treated for syphilis to be able to enlist
Questionnaire Design Consideration
-use simple wording (think about who will be reading the question) -specific questions are better than overly general or vague ones -leading questions and desirability bias -avoid bias language; questions that frame behavior in a positive or negative way -avoid double-barrel questions ("Do you have anxiety when you interact with your classmates or professors?") -double negatives ("Do you oppose not allowing the new law to pass?") -ask different questions, not essentially the same question reworded
Questionnaire design
-we have a construct we want to measure, typically one that we cannot get at with just one question >EX: anxiety, religiosity and self esteem -want to have multiple questions that we hypothesize are related to construct **if its a good question, then they will all be correlated with each other
Within-groups design establishing a claim?
1. Because within-groups designs enable researchers to manipulate an independent variable and incorporate comparison conditions, they provide an opportunity for establishing covariance. 2. The experimenter controls the independent variable and can ensure that it comes first, so temporal precedence 3. With a within-groups design, researchers don't have to worry about selection effects because participants are exactly the same in the two conditions. They might be concerned about design confounds.
Formula to Calculate r
1. Converts values into Z Score first 2. Multiply the Z-scores: when both above average or both below average, if you multiply, you will get a positive number. One above and one below, if you multiply you get a negative number so accounts for the association
to establish causation, a study has to satisfy three criteria:
1. Covariance of cause and effect. The results must show a correlation, or association, between the cause variable and the effect variable. 2. Temporal precedence. The cause variable must precede the effect variable; it must come first in time. 3. Internal validity. There must be no plausible alternative explanations for the relationship between the two variables.
How can experiments support causal claims?
1. Covariance. Do the results show that the causal variable is related to the effect variable? Are distinct levels of the independent variable associated with different levels of the dependent variable? 2. Temporal precedence. Does the study design ensure that the causal variable comes before the outcome variable in time? 3. Internal validity. Does the study design rule out alternative explanations for the results?
Longitudinal Studies and the Three Criteria for Causation
1. Covariance. Significant relationships in longitudinal designs help establish covariance. When two variables are significantly correlated, there is covariance. 2. Temporal precedence. A longitudinal design can help researchers make inferences about temporal precedence. Because each variable is measured in at least two different points in time, they know which one came first. By comparing the relative strength of the two cross-lag correlations, the researchers can see which path is stronger. If only one of them is statistically significant, the researchers move a little closer to determining which variable comes first, thereby causing the other. 3. Internal validity. When conducted simply—by measuring only the two key variables—longitudinal studies do not help rule out third variables. (ex= socioeconomical status) However, researchers can sometimes design their studies or conduct subsequent analyses in ways that address some third variables.
2 ways of counterbalancing
1. Full counterbalancing= all possible condition orders are represented. -easier for smaller groups because as the group size increases, the amount of orders that must be accounted for increases dramatically 2. Partial counterbalancing= only some of the possible condition orders are represented. -One way to partially counterbalance is to present the conditions in a randomized order for every subject. -Latin square= a formal system to ensure that every condition appears in each position at least once.
Steps of t-test
1. State null 2. Compute t test for independent groups: The t test helps us estimate whether the difference in scores between two samples is significantly greater than zero. --> One is the difference between the two means themselves, and the other is how much variability there is within each group. The t test is a ratio of these two values. 3. Calculating the probability of the rest or if null hypothesis is true -> most common way to estimate this probability is to use a sampling distribution of t. This method estimates the probability of obtaining the t we got, just by chance, from a null hypothesis population. *In null hypothesis significance testing, sampling distributions of t are always centered at zero because they are always created based on the assumption that the null hypothesis is true. *sampling Distribution based on df *the critical value of t—the t value that is associated with our alpha level. 4. Decide whether to reject the null *When we use a table of critical values of t, we compare the t we obtained to the critical value of t we looked up *Because the t we obtained is greater than the critical t associated with the alpha level of .05, we conclude that the result is statistically significant. (reject null) *Larger values of t are associated with smaller probabilities.
Steps of ANOVA
1. State null (means are the same) 2. Find F Ratio 3. CALCULATING THE PROBABILITY OF THE F VALUE WE OBTAINED, OR AN EVEN LARGER VALUE, IF THE NULL HYPOTHESIS IS TRUE *If there is no difference between means in the population, then most of the time the variance between the groups will be about the same as the variance within the groups. When these two variances are about the same, the F ratio will be close to 1 most of the time. Therefore, most of the F values we get from the null hypothesis population will be close to 1.0. *Usually we use the computer to tell us the exact probability of getting the F we got if the null hypothesis is true. * F cannot be lower than 0 4. Reject or Retain: Reject when F Ratio calculated is larger than the value we looked up
Three Possible Patterns from a Cross-Lag Study. (ex= Brummelman)
1. The study did show that parental overpraise (overvaluation) at earlier time periods was significantly correlated with child narcissism at the later time periods. Such a pattern was consistent with the argument that overpraise leads to increases in narcissism over time. 2. However, the study could have shown the opposite result—that narcissism at earlier time periods was significantly correlated with overpraise later. Such a pattern would have indicated that the childhood narcissistic tendency came first, leading parents to change their type of praise later. 3.Finally, the study could have shown that both correlations are significant—that overpraise at Time 1 predicted narcissism at Time 2 and that narcissism at Time 1 predicted overpraise at Time 2.
How to reduce Reactivity
1. make unobtrusive observations—that is, make yourself less noticeable. 2. Another solution is to wait out the situation. (get used to presence) 3. Another way to avoid reactivity is to use unobtrusive data. Instead of observing behavior directly, researchers measure the traces a particular behavior leaves behind.
PREVENTING OBSERVER BIAS AND OBSERVER EFFECTS
1. rating instructions, often called codebooks, so the observers can make reliable judgments with less bias. Codebooks are precise statements of how the variables are operationalized, and the more precise and clear the codebook statements are, the more valid the operationalizations will be. 2. Researchers can assess the construct validity of a coded measure by using multiple observers. Doing so allows the researchers to assess the interrater reliability of their measures. 3. Even when an operationalization has good interrater reliability, it still might not be valid. When two observers agree with each other, they might share the same biases, so their common observations are not necessarily valid.
Disadvantages of within-groups design
1. repeated-measures designs have the potential for order effects, which can threaten internal validity (but can usually control for order effects by using counterbalancing) 2. a within-groups design might not be possible or practical. Ex: teaching kid how to ride a bike with two different methods= cannot teach same kid how to ride a bike 2x 3. when people see all levels of the independent variable and then change the way they would normally act- changing their spontaneous behavior ***A cue that can lead participants to guess an experiment's hypothesis is known as a demand characteristic, or an experimental demand; which creates an alternative explanation for a study's results.
Control, Treatment and Comparison Groups
A control group is a level of an independent variable that is intended to represent "no treatment" or a neutral condition. When a study has a control group, the other level or levels of the independent variable are usually called the treatment group(s). When the control group is exposed to an inert treatment such as a sugar pill, it is called a placebo group, or a placebo control group. *Ways to design IV to establish covariance **All experiments need a comparison group so the researchers can compare one condition to another, but the comparison group does not need to be a control group.
Falsifiablility
A theory must lead to hypotheses that, when tested, could actually fail to support the theory.
kappa
Although r can be used to evaluate interrater reliability when the observers are rating a quantitative variable, a more appropriate statistic, called kappa, is used when the observers are rating a categorical variable
Test for statistical Significance
Although they occasionally use r, it is more common to test whether the difference between means (group averages) is statistically significant, usually by using a statistic called the t test, or other statistical tests.
CHAPTERS IN EDITED BOOKS
An edited book is a collection of chapters on a common topic; each chapter is written by a different contributor. a book chapter is not the first place a study is reported; instead, the scientist is summarizing a collection of research and explaining the theory behind it. Edited book chapters can therefore be a good place to find a summary of a set of research a particular psychologist has done. ***NOT as much peer review but author of book recruits experts only **The audience for these chapters is usually other psychologists and psychology students
zero-acquaintance accuracy
An entire line of research on this phenomenon finds that most people are fairly accurate at judging traits such as extroversion, agreeableness, and intelligence just by looking at other people for a few seconds.
Combining Techniques
As long as clusters or individuals were selected at random, the sample will represent the population of interest. It will have good external validity.
Difference between quota and stratified sampling
As you can see, both quota sampling and stratified random sampling specify subcategories and attempt to fill targeted percentages or numbers for each subcategory. However, in quota sampling the participants are selected nonrandomly (perhaps through convenience or purposive sampling), and in stratified random sampling they are selected using a random selection technique.
Hypothesis-Generating Heurisitcs: Improving older ideas
Bem's self-perception theory -Previous theory: attitudes shape behavior -New theory: behavior shapes attitudes Skinner's operant conditioning -Previous theory: classical conditioning and "trial and error learning" -New Theory: response and reinforcement
Internal Validity
Can We Make a Causal Inference from an Association? **Even though it's not necessary to formally interrogate internal validity for an association claim, we must guard against the powerful temptation to make a causal inference from any association claim we read. **third-variable problem: When we can come up with an alternative explanation for the association between two variables, that alternative is some lurking third variable.
Preventing Type 1 errors
Caused by the level of probability (or p) at which we decide whether or not to reject the null hypothesis. *is less than alpha, they will reject the null hypothesis. If the probability of their result happening just by chance (assuming the null hypothesis is true) is greater than alpha, they will retain the null hypothesis. **In psychological science research, the convention is to set the alpha level at 5%, or alpha = .05.
How to study an item's internal consistency?
Cronbach's alpha
Which Error Type is the worst?
Depends on the context.
slope direction
Direction of the relationship can be positive, negative, or zero—that is, sloping up, sloping down, or not sloping at all.
Reporting Mean and Standard Deviation in Journal Articles
Either in a table or within the text
Experience is confounded
Even if a change has occurred, we often can't be sure what caused it. **hard to isolate variables in personal life
Adding More Predictors to a Regression
Even when there are many more predictor variables in the table, beta still means the same thing. 1. Adding several predictors to a regression analysis can help answer two kinds of questions. First, it helps control for several third variables at once. 2. By looking at the betas for all the other predictor variables, we can get a sense of which factors most strongly predict chance of pregnancy.
Bleeding or Bloodletting cure for illness
Every patient's recovery from yellow fever after bloodletting seemed to support Rush's theory that the treatment worked. But Dr. Rush never set up a systematic comparison because doc- tors in the 1700s were not collecting data on their treatments. To test the bleeding cure, doctors would have had to systematically count death rates among patients who were bled versus those who received some comparison treatment (or no treatment). *But you need to know all the numbers—the number of bled patients who died and the number of untreated patients who died, in addition to the number of patients in each group who recovered. **Because Dr. Rush bled every patient, he never had the chance to see how many would recover without the bleeding treatment. Similarly, when you rely on personal experience to decide what is true, you usually don't have a systematic comparison group because you're observing only one "patient": yourself. ***In contrast, basing conclusions on systematic data collection has the simple but tremendous advantage of providing a comparison group.
Example: Eating Pasta
Half = "large bowl" and half= "medium bowl" session. serve themselves pasta from a bowl at the buffet. The bowl was continually refilled when about half the pasta was gone, so nobody felt the food was getting scarce. Weighed the plates to measure the amount they took. Participants were allowed to eat their pasta lunches at a comfortable pace. When they were finished, the assistants weighed each plate again, to determine how much food each person had actually eaten. **On average, the participants took more pasta from the large serving bowl than the medium one. Large-bowl participants had eaten about 140 calories more than the medium-bowl ones
Alternatives to Cohen's d
Hedge g The conventions for small, medium, and large for Hedge's g are the same as they are for Cohen's d. Eta Squared This effect size may be used when researchers describe differences among several groups (i.e., more than two means), or when they describe the effect sizes of interaction effects.
Statistical Validity
How Well Do the Data Support the Conclusion? Ask Qs: What is the effect size? Is the correlation statistically significant? Could there be outliers affecting the association? Is there a restriction of range? Is the association curvilinear?
dependent variable, or outcome variable
How a participant acts on the measured variable depends on the level of the independent variable. Researchers have less control over the dependent variable; they manipulate the independent variable and then watch what happens to people's self-reports, behaviors, or physiological responses. A dependent variable is not the same as its levels, either. *when measured on different scales, they are presented on different graphs
generalizability:
How did the researchers choose the study's participants, and how well do those participants represent the intended population?
Statistical Validity: How Well Do the Data Support the Causal Claim?
IS THE DIFFERENCE STATISTICALLY SIGNIFICANT? -when a result is statistically significant, it is unlikely to have been obtained by chance from a population in which nothing is happening. In other words, a statistically significant result suggests covariance exists between the variables in the population from which the sample was drawn. -->covariance—that the independent variable had a detectable effect on the dependent variable. -no covariance= the study does not support a causal claim. HOW LARGE IS THE EFFECT? -if a study used a very large sample, even tiny differences might be statistically significant. -Therefore, asking about effect size can help you evaluate the strength of the covariance (i.e., the difference). *In general, the larger the effect size, the more important, and the stronger, the causal effect. **correlational=r; experimental=d -->When d is larger, it usually means the independent variable caused the dependent variable to change for more of the participants in the study. -->When d is smaller, it usually means the scores of participants in the two experimental groups overlap more.
null hypothesis significance testing (NHST)
NHST follows a set of steps to determine whether the result from a study is statistically significant.
a semantic differential format.
Instead of degree of agreement, respondents might be asked to rate a target object using a numeric scale that is anchored with adjectives
Four ways of knowing
Intuition: feel it in bones Logic: assume it was since it did yesterday Authority: Looking at news Observation: directly seeing it Religion: Authority, Intuition, Logic and Observation Government: Authority, Intuition, Logic and Observation Philosophy: Logic, Observation, Intuition, Authority Science: Observation, Logic, Intuition and Authority
Ethical to watch people?
It depends. Most psychologists believe it is ethical to watch people in museums, classrooms, hockey games, or even at the sinks of public bathrooms because in those settings people can reasonably expect their activities to be public, not private. More secretive methods, such as one-way mirrors and covert video recording, are also considered ethical in some conditions. In most cases, the reseacher must get advanced permission
observer effects, or expectancy effects
It is even worse when the observers inadvertently change the behavior of those they are observing, such that participant behavior changes to match observer expectations. this phenomenon can occur even in seemingly objective observations. Rats: This study showed that observers not only see what they expect to see; sometimes they even cause the behavior of those they are observing to conform to their expectations. Hans the Horse: Hans was correct only when his questioner saw the card. As it turned out, the horse was extremely clever—but not at math. He was smart at detecting the subtle head movements of the questioner.
Google scholar
It works like the regular Google search engine, except the search results are only in the form of empirical journal articles and scholarly books. In addition, by visiting the User Profile for a particular scientist, you can see all of that person's publications. One disadvantage of Google Scholar is that it doesn't let you limit your search to specific fields (such as the abstract). In addition, it doesn't categorize the articles it finds, for example, as peer-reviewed or not, whereas PsycINFO does. And while PsycINFO indexes only psychology articles, Google Scholar contains articles from all scholarly disciplines.
JOURNAL ARTICLES: PSYCHOLOGY'S MOST IMPORTANT SOURCE
Journal articles are written for an audience of other psychological scientists and psychology students. They can be either empirical articles or review articles. Empirical journal articles report, for the first time, the results of an (empirical) research study. Empirical articles contain details about the study's method, the statistical tests used, and the results of the study. Review journal articles provide a summary of all the published studies that have been done in one research area. a quantitative technique called meta-analysis, which combines the results of many studies and gives a number that summarizes the magnitude, or the effect size, of a relationship. **Before being published in a journal, both empirical articles and review articles must be peer-reviewed
Example: Taking notes
Laptop: students can easily transcribe the exact words and phrases a professor is saying, resulting in seemingly more complete notes. But, students might not have to think about the material when they're typing. Notes Students can summarize, paraphrase, or make drawings to connect ideas—even if fewer words are used than on a computer. Longhand notes could result in deeper processing of the material and more effective comprehension.
Role of longitudinal and multivariate
Longitudinal designs help establish temporal precedence Multiple-regression analysis helps rule out third variables, thus providing some evidence for internal validity. (When researchers use multivariate designs, they need to take precautions to look for subgroups, outliers, and curvilinear associations, all of which can be more complicated to detect when there are more than two variables.)
"Justification Phase" of Science
Must provide principle rationale for: -Plan of study -Data analysis -Conclusions Controversies -Exploratory research and hunches
Step 1: Null Hypothesis
Null means "nothing," and colloquially, a null hypothesis means "assume that nothing is going on." Depending on the research question, the null hypothesis can mean that a person does not have special abilities, that an independent variable does not have an effect on the dependent variable, or that two variables are not correlated with each other.
OBSERVATIONS CAN BE BETTER THAN SELF-REPORTS
Observations can sometimes tell a more accurate story than self-reporting Observational research is a way to operationalize a conceptual variable, so when interrogating a study we need to ask about the construct validity of any observational measure. --> The construct validity of observations can be threatened by three problems: observer bias, observer effects, and reactivity.
Regression Does Not Establish Causation
One problem is that even though multivariate designs analyzed with regression statistics can control for third variables, they are not always able to establish temporal precedence. Even when a study takes place over time (longitudinally), another very important problem is that researchers cannot control for variables they do not measure. But since those possible third variables were not measured (or even considered), there is no way of knowing *A randomized experiment is the gold standard for determining causation. Multiple regression, in contrast, allows researchers to control for potential third variables, but only for the variables they choose to measure.
RATING PRODUCTS
One study found little correspondence between five-star ratings on Amazon.com and the ratings of the same products by Consumer Reports, an independent product rating firm The researchers found that consumers' ratings were, instead, correlated with the cost of the product and the prestige of its brand.
producers of research
People such as psychologists or professors that conduct research
REACTIVITY: WHEN PARTICIPANTS REACT TO BEING WATCHED
Reactivity is a change in behavior when study participants know another person is watching. They might react by being on their best behavior—or in some cases, their worst—rather than displaying their typical behavior. Happens with human AND animal studies
Step 2: Collect Data
Related to study
Type 2 error
Second, a study might mistakenly conclude from a sample that there is no association between two variables, when there really is an association *"false negative"/"miss"
PEOPLE CAN GIVE MEANINGFUL RESPONSES
Self reports are usually ideal is meaningful and effective to ask people to self-report on their own subjective experiences
Statistical Significance vs Effect Size
Statistical significance is related to effect size; usually, the stronger a correlation (the larger its effect size), the more likely it will be statistically significant.
b value
Sometimes a regression table will include the symbol b instead of beta. The coefficient b represents an unstandardized coefficient. A b is similar to beta in that the sign of b—positive or negative—denotes a positive or negative association (when the other predictors are controlled for). But unlike two betas, we cannot compare two b values within the same table to each other. The reason is that b values are computed from the original measurements of the predictor variables, whereas betas are computed from predictor variables that have been changed to standardized units. *A predictor variable that shows a large b may not actually denote a stronger relationship to the criterion variable than a predictor variable with a smaller b. **that when a table presents b values, or unstandardized coefficients, it is not appropriate to compare their relative strength. We can only do so with beta, and even then, remember that betas change depending on what other predictor variables are used.)
Bushman's anger experiment
Steve insulted the political essays "worst essay I've ever read" into three groups, to systematically compare the effects of venting and not venting anger. Group 1 was instructed to sit quietly in the room for 2 minutes. Group 2 was instructed to punch a punching bag for 2 minutes, having been told it was a form of exercise. Group 3 was instructed to punch a punching bag for 2 minutes while imagining Steve's face on it. The catharsis hypothesis predicts that Group 3 should have calmed down the most, and as a result, this group should not have blasted Steve with very much noise. This group, however, gave Steve the loudest noise blasts of all! Compared with the other two groups, those who vented their anger at Steve through the punching bag continued to punish him when they had the chance. In contrast, Group 2, those who hit the punching bag for exercise, subjected him to less noise (not as loud or as long). Those who sat quietly for 2 minutes punished Steve the least of all. *****When you are the one acting in the situation, yours is a view from the inside, and you only see one possible condition. ****Research results have repeatedly indicated that people who physically express their anger at a target actually become more angry than when they started.
survey and poll
Survey is often used when people are asked about a consumer product Poll is used when people are asked about their social or political opinions. However, these two terms can be interchangeable both mean the same thing: a method of posing questions to people on the phone, in personal interviews, on written questionnaires, or online.
correction for restriction of range.
The formula is beyond the scope of this text, but it estimates the full set of scores based on what we know about an existing, restricted set, and then recomputes the correlation.
socially desirable responding, or faking good.
The idea is that because respondents are embarrassed, shy, or worried about giving an unpopular opinion, they will not tell the truth on a survey or other self-report measure. -To avoid socially desirable responding, a researcher might ensure that the participants know their responses are anonymous -In one study, anonymous respondents were more likely to start using response sets in long surveys. -In addition, anonymous people were less likely to accurately report a simple behavior, such as how many candies they had just eaten, which suggests they were paying less attention to things -If people agree with many such items, researchers may discard that individual's data from the final set, under suspicion that they are exaggerating on the other survey items, or not paying close attention in general. --> may ask their friends about them *Faking bad (less common)
Effect Size Conventions for Cohen's d
The larger the effect size, the less overlap between the two experimental groups; the smaller the effect size, the more overlap. If the effect size is zero, there is full overlap between the two groups
OBSERVING HOW MUCH PEOPLE TALK
The published data demonstrate that on average, women speak 16,215 words per day, while men speak 15,669 words per day This difference is not statistically significant, so despite stereotypes of women being the chattier gender, women and men showed the same level of speaking.
Important point:
The validity of a measure is not the same as its reliability **Although a measure may be less valid than it is reliable, it cannot be more valid than it is reliable. Intuitively, this statement makes sense. Reliability has to do with how well a measure correlates with itself. Validity, however, has to do with how well a measure is associated with something else
Construct Validity and testing theories
Therefore, interrogating the construct validity of an experiment requires you to evaluate how well the measures and manipulations researchers used in their study capture the conceptual variables in their theory.
THE RETAIL BOOKSHELF
They are written to help people, to inform, to entertain, and to make money for their authors. The language in trade books is much more readable than the language in most journal articles. Trade books can also show how psychology applies to your everyday life, and in this way they can be useful. LOOK IF REFERENCES
margin of error of the estimate.
This is a statistical figure, based on sample size for the study, that attempts to include the true value in the population.
Construct validity
refers to how well a conceptual variable is operationalized. **construct validity of a frequency claim, the question is how well the researchers measured their variables.
Avoiding Selection Effects with Matched Groups
To create matched groups from a sample, the researchers would first measure the participants on a particular variable that might matter to the dependent variable. Then, of the two people who score the highest, each would go in one group and it would continue downwards like that **Matching has the advantage of randomness. Because each member of the matched pair is randomly assigned, the technique prevents selection effects. This method also ensures that the groups are equal on some important variable *The disadvantage is that the matching process requires an extra step—more time and resources
construct validity of associated claims
To support an association claim, a researcher measures two variables, so you have to assess the construct validity of each variable. **assess how well such measurements were conducted.
Example: Taking notes- set up of the study and results
Took notes on 5 TED talks in their assigned method, did a 30 minute activity to distract them and then tested their knowledge. The essay questions asked about straightforward factual information as well as conceptual information ***Students in both the laptop and the longhand groups scored about equally on the factual questions, but the longhand group scored higher on the conceptual questions. *(The two other studies, unlike the first, showed that longhand notetakers did better on factual questions)
Construct validity definition
refers to how well a study's variables are measured or manipulated.
observational research
When a researcher watches people or animals and systematically records how they behave or what they are doing *Some scientists believe observing behavior is better than collecting self-reports through surveys, because people cannot always report on their behavior or past events accurately, **basis for frequency claims ***Observations can also be used to operationalize variables in association claims and causal claims. ****But if you want to know what people are really doing or what really influences behavior
F Test
When a study compares two or more groups to each other, the appropriate test is the F test, obtained from an analysis of variance, (ANOVA).
causal claim
goes even further, arguing that one of the variables is responsible for changing the other. **either based on covariants or NO ASSOCIATION **A causal claim that contains tentative language—could, may, seem, suggest, sometimes, potentially—is still considered a causal claim.
Journalist ignore pattern and parsimony
When journalists write about science, they do not always fairly represent pattern and parsimony in research. Instead, they may report only the results of the latest study. *Ideally, journalists should report on the entire body of evidence, as well as the theoretical background, for a particular claim.
Procedures behind counterbalancing
When researchers counterbalance conditions (or levels) in a within-groups design, they have to split their participants into groups; each group receives one of the condition sequences. Assign through random assignment
Mediators vs. Moderators
When researchers test for mediating variables, they ask: Why are these two variables linked? When they test for moderating variables, they ask: Are these two variables linked the same way for everyone, or in every situation? Mediators ask: Why? Moderators ask: Who is most vulnerable? For whom is the association strongest? As the name implies, the mediating variable comes in the middle of the other two variables. The word moderate can mean "to change," and a moderating variable can change the relationship between the other two variables (making it more intense or less intense).
moderator
When the relationship between two variables changes depending on the level of another variable, that other variable **In correlational research, moderators can inform external validity. When an association is moderated by residential mobility, type of relationship, day of the week, or some other variable, we know it does not generalize from one of these situations to the others.
Experimental research
has an independent variable and a dependent variable
Meaning of the alpha level
When we set alpha in advance at alpha = .05, we are admitting that 5% of the time, when the null hypothesis is true, we will end up rejecting the null hypothesis anyway. **If they prioritize being conservative, they might set alpha lower than 5%—perhaps at 1%, or .01. By setting alpha lower, they are trying to minimize the chances of making a Type I error—of accidentally concluding there is a true effect or relationship when there actually is none. In contrast, there may be situations in which researchers choose to set alpha higher—say, .10. In this case, they would be comfortable making false conclusions 10% of the time if, in truth, there is no effect.
Design Confound
an experimenter's mistake in designing the independent variable; it is a second variable that happens to vary systematically along with the intended independent variable and therefore is an alternative explanation for the results. **Classic threat to internal validity -Ex: Treating people in a more friendly manner or serving more appetizing pasta -Can control for these
WIKIS AS A RESEARCH SOURCE
Wikis can provide quick, easy-to-read facts about almost any topic. Anybody can create a new entry, anybody can contribute to the content of a page, and anybody can log in and add details to an entry. Theoretically, wikis are self-correcting: If one user posts an incorrect fact, another user would come along and correct it. First, wikis are not comprehensive in their coverage: You cannot read about a topic if no one has created a page for it. Second, although wiki pages might include references, these references are not a comprehensive list; they are idiosyncratic, representing the preferences of wiki contributors. Third, the details on the pages might be incorrect, and they will stay incorrect until somebody else fixes them. Finally, vandalism is a potential problem (sometimes people intentionally insert errors into pages); however, Wikipedia has developed digital robots to detect and delete the most obvious errors—often within seconds
Dual relationships
any interaction other than the client -professional relationship (babysitting, bartering for services, going into business with client) >Researcher-participant >Clinician-patient >Teacher-student
Bias Reasoning" Bias about being Bias
a bias blind spot, the belief that we are unlikely to fall prey to the other biases previously described **it can make it difficult for us to initiate the scientific theory-data cycle.
a correlational result is an early step in establishing
a causal relationship between two variables.
scatterplot
a graph in which one variable is plotted on the y-axis and the other variable is plotted on the x-axis; each dot represents one participant in the study, measured on the two variables.
central tendency
a measure of what value the individual scores tend to center on. Three values are commonly used to determine central tendency: the mode, the median, and the mean.
correlational study.
a research project designed to discover the degree to which two variables are related to each other
inferential Statistics
a set of techniques that uses the laws of chance and probability to help researchers make decisions about the meaning of their data and the inferences they can make from that information. **goal of estimation. ***Inferential statistical thinking involves theories about how chance operates
Establishing internal validity
a study must ensure that the causal variable (the active ingredient), and not other factors, is responsible for the change in the outcome variable. ***Having several possible explanations= confounds
frequency distribution
a table that gives a visual picture of the observations on a particular variable. It clearly shows how many of the cases scored each possible value on the variable. (can be made into a frequency histogram)
self-selection
a term used when a sample is known to contain only people who volunteer to participate.
Posttest Only Design
also known as an equivalent groups, posttest- only design, participants are randomly assigned to independent variable groups and are tested on the dependent variable once ex: Note-taking study Posttest-only designs satisfy all three criteria for causation. 1. Covariance= detecting differences in the dependent variable. (Having at least two groups makes it possible to do so.) 2. Temporal precedence= independent variable comes first in time. 3. Internal Validity= When researchers use appropriate control variables, there should be no design confounds, and random assignment takes care of selection effects.
Manipulation of variables can control for
alternative explanations
confounds
alternative explanations in research *a confound occurs when you think one thing caused an outcome but in fact other things changed, too, so you are confused about what the cause really was.
negative association
an association in which high levels of one variable go with low levels of the other variable, and vice versa
Response sets, also known as nondifferentiation
are a type of shortcut respondents can take when answering survey questions. **Although response sets do not cause many problems for answering a single, stand-alone item, people might adopt a consistent way of answering all the questions—especially toward the end of a long questionnaire acquiescence, or yea-saying; this occurs when people say "yes" or "strongly agree" to every item instead of thinking carefully about each one. (the survey could be measuring the tendency to agree, or the lack of motivation to think carefully.)
Conceptual variables
are abstract concepts, such as "spending time socializing" and "school achievement." A conceptual variable is sometimes called a construct. Conceptual variables must be carefully defined at the theoretical level, and these definitions are called conceptual definitions.
Negatively worded questions
are another way survey items can be unnecessarily complicated. Whenever a question contains negative phrasing, it can cause confusion, thereby reducing the construct validity of a survey or poll
Frequency claims definition
are claims about how often something happens in a population. *In most cases, researchers are not able to check the accuracy of their samples' estimates because they hardly ever complete a full census of a population on the variable of interest.
Bigger samples...
are not necessarily better **the size of a sample is in fact much less important than how that sample was selected. ***the larger the sample size, the smaller the margin of error—that is, the more accurately the sample's results reflect the views of the population.
An association claim
argues that one level of a variable is likely to be associated with a particular level of another variable.
A variable
as the word implies, is something that varies, so it must have at least two levels, or values.
Implicit Association Test
asks people to respond quickly to positive and negative words on the right and left of a computer screen Intermixed with the positive and negative words may be faces from different social groups, such as Black and White faces. People respond to all possible combinations, including positive words with Black faces, negative words with White faces, negative words with Black faces, and positive words with White faces. When people respond more efficiently to the White-positive/Black-negative combination than to the White-negative/Black-positive combination, researchers infer that the person may hold negative attitudes on an implicit, or unconscious, level.
random assignment
assigning participants to experimental and control conditions by chance, thus minimizing preexisting differences between those assigned to the different groups
Poll sample size
at most 2K
external validity of associated claim
by asking whether it can generalize to other populations, as well as to other contexts, times, or places.
A longitudinal design
can provide evidence for temporal precedence by measuring the same variables in the same people at several points in time. Longitudinal research is used in developmental psychology to study changes in a trait or an ability as a person grows older. In addition, this type of design can be adapted to test causal claims. **researchers measured the same variables in the same group of people across time **When an experiment is not practical or ethical, a longitudinal correlational design is a good option.
With an association claim, the two most important validities to interrogate are
construct validity and statistical validity.
USING STATISTICS TO CONTROL FOR THIRD VARIABLES
control for another variable. *recognize that testing a third variable with multiple regression is similar to identifying subgroups. Ex: Researchers are asking whether, after they take the relationship between age and pregnancy into account, there is still a portion of variability in pregnancy that is attributable to watching sexy TV.
Avoiding ordering effects by counterbalancing
counterbalancing: they present the levels of the independent variable to participants in different sequences; causes any order effects to cancel each other out when all the data are collected. ** not relevant in independent groups design
effect size
describes the strength of a relationship between two or more variables. *One meaning of "strong" when applied to effect size is that strong effect sizes enable predictions that are more accurate. *When all else is equal, a larger effect size is often considered more important than a small one. However, there are exceptions to this rule. Depending on the context, even a small effect size can be important.
Z Score
describes whether an individual's score is above or below the mean and how far it is from the mean in standard deviation units. *it lets us compare the relative standing of individual cases on variables that might have been measured in different units. *referred to as the standardized score
Repeated Measures
design is a type of within-groups design in which participants are measured on a dependent variable more than once, after exposure to each level of the independent variable. **participants experience both levels of the IV
READING WITH A PURPOSE: EMPIRICAL JOURNAL ARTICLES
don't read every word-read with purpose (1) What is the argument? (2) What is the evidence to support the argument? The obvious first step toward answering these questions is to read the abstract, which provides an overview of the study. Next is introduction to find the primary goals and hypotheses of the study. Another place to find information about the argument of the paper is the first paragraph of the Discussion section, where most authors summarize the key results of their study and state how well the results supported their hypotheses. Once you have a sense of what the argument is, you can look for the evidence. In an empirical article, the evidence is contained in the Method and Results sections.
Scatterplots
dots plotted that represent 2 values of the variables tells us the direction of the relationship between two variables (positive, negative, or zero) and the strength of the positive or negative relationship (strong or weak).
Cohen's d
effect size in terms of how far apart the two means are, in standard deviation units. This will also tell us how much overlap there is between the two sets of scores.
comparison group
enables us to compare what would happen both with and without the thing we are interested in *experience doesn't have a comparison group
In probability sampling, also called random sampling
every member of the population of interest has an equal and known chance of being selected for the sample, regardless of whether they are convenient or motivated to volunteer.
Is posttest only or pretest/posttest better?
ex: Pasta study couldn't have done pretest/posttest bc the participants would have gotten too full in the pretest
What If Beta Is Not Significant?
ex: although frequency of family meals and academic success are significantly related in their bivariate relationship, that relationship goes away when potential third variables, such as parental involvement, are controlled for.
external validity of causal claims
generalize?
When interrogating external validity, we ask whether the results of a particular study can be...
generalized to some larger population of interest. **concerns both samples and settings.
Correlational Research
has predictor (independent variable) and criterion variables (dependent variables) -cannot draw cause and effect but can make predictions -this type of research utilizes a lot of questionnaires and surveys -cannot manipulate specific things >ex: gender, race, age, life expectancy and brain damage (cannot randomly assign these things) ex: cohabitation before marriage and divorce rate Ex of predictions: HS GPA/SAT scores and college performance (Linear regression used to make predictions)
When we think of a reasonable third variable explanation for an association claim, how do we know if it's an internal validity problem?
have to test it
external validity
how well the results of a study generalize to, or represent, people or contexts besides those in the original study.
Weighting
if responses contain fewer members of a subgroup than it should (such as fewer wireless-only respondents or fewer young adults), they adjust the data so responses from members of underrepresented categories count more, and overrepresented members count less.
Independent Groups Design
in which different groups of participants are placed into different levels of the independent variable. This type of design is also called a between-subjects design or between-groups design. *2 types: posttest only and pretest/posttest
snowball sampling
in which participants are asked to recommend a few acquaintances for the study. *unrepresentative because people are recruited via social networks, which are not random.
forced-choice questions
in which people give their opinion by picking the best of two or more options. *are often used in political polls,
masked design, or blind design
in which the observers are unaware of the purpose of the study and the conditions to which participants have been assigned.
curvilinear association
in which the relationship between two variables is not a straight line; it might be positive up to a point, and then become negative.
oversampling
in which the researcher intentionally overrepresents one or more groups. *A survey that includes an oversample adjusts the final results so members in the oversampled group are weighted to their actual proportion in the population.
stratified random sampling
in which the researcher purposefully selects particular demographic categories, or strata, and then randomly selects individuals within each of the categories, proportionate to their assumed membership in the population.
OBSERVING HOCKEY MOMS AND DADS
investigated popular media stories about parents who had acted violently at youth ice hockey games *After sitting in the stands at 69 boys' and girls' hockey games in one Canadian city, the researchers found that 64% of the parents' comments were positive, and only 4% were negative. **Media Exaggerated
multivariate designs
involving more than two measured variables. **longitudinal designs, multiple-regression designs, and the pattern and parsimony approach ***a multivariate design gives several individual correlations, referred to as cross-sectional correlations, auto-correlations, and cross-lag correlations.
Standard Deviation
is a computation that captures how far, on average, each score in a data set is from the mean. **The standard deviation is more commonly reported than the variance because it better captures how far, on average, each score is from the mean. When the standard deviation is large, there is a great deal of variability in the set; the scores are spread out far from the mean, either above or below. When the standard deviation is small, there is less variability in the set; most of the scores are closer to the mean, above or below.
present/present bias
is a name for our failure to consider appropriate comparison groups *easier to notice what is present Ex: earlier). Dr. Rush may have fallen prey to the present/present bias when he was observing the effects of bloodletting on his patients. He focused on patients who did receive the treatment and did recover Ex:In other words, we notice the times when both the treatment (venting) and the desired outcome (feeling better) are present but are less likely to notice the times when we didn't express our anger and just felt better anyway; in other words, the treatment was absent but the outcome was still present
sample
is a smaller set, taken from that population.
a manipulated variable
is a variable a researcher controls, usually by assigning study participants to the different levels of that variable. **Some variables cannot be manipulated—they can only be measured (whether you cannot change it or it is unethical). ex- age
manipulated variable
is a variable that is controlled, such as when the researchers assign participants to a particular level (value) of the variable. *each participant is assigned to a specific level within this variable
Bias Reasoning: Being swayed by good story
is accepting a conclusion just because it makes sense or feels natural. We tend to believe good stories—even ones that are false. **neurologist Sigmund Freud, whose models of mental distress focused on the harmful effects of suppressing one's feelings and the benefits of expressing them (used the familiar example of pressure to appeal to ppl) *Scared Straight Program has the opposite effect than people thought
A claim
is an argument someone is trying to make.
A bivariate correlation, or bivariate association
is an association that involves exactly two variables. *looks at only two variables at a time.
An outlier
is an extreme score; a single case (or a few cases) that stands out from the pack. *In a bivariate correlation, outliers are mainly problematic when they involve extreme scores on both of the variables.
internal validity
is an indication of a study's ability to eliminate alternative explanations for the association
Cluster sampling
is an option when people are already divided into arbitrary groups. Clusters of participants within a population of interest are randomly selected, and then all individuals in each selected cluster are used.
A measured variable
is one whose levels are simply observed and recorded.
A constant
is something that could potentially vary but that has only one level in the study in question.
narcissism
is studied as a personality trait in which people feel superior to others, believe they deserve special treatment, and respond strongly when others put them down; narcissists are difficult relationship partners. Parental overpraise, the other variable discussed in this example, is telling kids they are exceptional or more special than other children. 1. Is there covariance? One study did find covariance. Adults who were narcissistic remembered their parents praising them for almost everything they did. 2. Is there temporal precedence? No;Adults reflected on their parents' behavior during childhood, so their current self-views could have colored their recall of the past. 3. Is there internal validity? The association between parental praise and child narcissism might be explained by a third variable.
parsimony
is the degree to which a scientific theory provides the simplest explanation of some phenomenon. In the context of investigating a causal claim, parsimony means the simplest explanation of a pattern of data—the theory that requires making the fewest exceptions or qualifications. **Because many diverse predictions are tied back to one central principle, there is a strong case for parsimony
A population
is the entire set of people or products in which you are interested.
The p value
is the probability that the sample's association came from a population in which the association is zero. *"not statistically significant." This means we cannot rule out the possibility that the result came from a population in which the association is zero.
mode
is the value of the most common score—the score that was received by more members of the group than any other.
statistical significance
refers to the conclusion a researcher reaches regarding the likelihood of getting a correlation of that size just by chance, assuming there's no correlation in the real world.
Random assignment
is used only in experimental designs. When researchers want to place participants into two different groups (such as a treatment group and a comparison group), they usually assign them at random. ***Enhancing internal validity: by helping ensure that the comparison group and the treatment group have the same kinds of people in them, thereby controlling for alternative explanations. **priority over random sampling
Double-barreled question
it asks two questions in one. Double-barreled questions have poor construct validity because people might be responding to the first half of the question, the second half, or both. (ask separately)
association claim
it describes a relationship between variables
Which is best?
it's best when self-report, observational, and physiological measures show similar patterns of results.
Association claims help us to...
make predictions
Establishing Temporal Precedence
manipulating the IV in order to be sue that it came before the DV (Control which variable comes first) ***Makes experiments superior to correlational studies
Small effect size...
may not be insignificant
Correlate
meaning that when one variable changes, the other variable tends to change, too. (related) **An association claim states a relationship between at least two variables.
temporal precedence
means it comes first in time, before the other variable.
operationalize
means to turn a concept of interest into a measured or manipulated variable.
Mediation / Mediator
mediator, or mediating variable. Researchers may propose a mediating step between two of the variables. A study does not have to be correlational to include a mediator; experimental studies can also test them. However, mediation analyses often rely on multivariate tools such as multiple regression, so it makes sense to learn about mediators here. *They would propose an overall relationship. However, this overall relationship exists only because there are two other relationships *Mediation is definitively established only when the proposed causal variable is measured or manipulated first in a study, followed some time later by the mediating variable, followed by the proposed outcome variable.
Counterbalance
mix up the order to control for order effects
multimodal
more than two modes
Question wording matters
must be clear and straightforward or else a person may misinterpret question
2 variables = Correlational
no matter what kind of graph you see, when the method of the study measured both variables, the study is correlational, and therefore it can support an association claim.
Observer bias
occurs when observers' expectations influence their interpretation of the participants' behaviors or the outcome of the study. Instead of rating behaviors objectively, observers rate behaviors according to their own expectations or hypotheses.
pretest/posttest design
or equivalent groups, pretest/posttest design, par- ticipants are randomly assigned to at least two different groups and are tested on the key dependent variable twice—once before and once after exposure to the independent variable Ex: GRE score effects based on mindfulness training *use this design when they want to demonstrate that random assignment made groups equal. Researchers can be absolutely sure there is no selection effect in a study. *Researchers can track down change in performance overtime
Hypothesis
or prediction, is the specific outcome the researcher expects to observe in a study if the theory is accurate
Within-groups design
or within-subjects design, there is only one group of participants, and each person is presented with all levels of the independent variable. *2 types: repeated and concurrent measures
concurrent-measures design
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. -exposed to all levels of the IV simultaneously and preference is observed
fence sitting
playing it safe by answering in the middle of the scale, especially when survey items are controversial. It can be difficult to distinguish those who are unwilling to take a side from those who are truly ambivalent. One approach is to take away the neutral option. *The drawback of this approach is that sometimes people really do not have an opinion or an answer, so for them, having to choose a side is an invalid representation of their truly neutral stance.
THE POPULAR MEDIA
popular media coverage is good for psychology. Journalists play an important role in telling the public about exciting findings in psychological science. *Journalists who are not trained in science writing might not correctly summarize a journal article. They may oversimplify things and even make claims that the study did not support. When you read popular media stories, plan to use your skills as a consumer of information to read the content critically.
Why not just do experiment instead of causation study?
problem is that in some cases people cannot be randomly assigned to a causal variable of interest. Ex: we cannot manipulate personality traits, such as narcissism in children. Similarly, while parents might be able to learn new ways to praise their children, they can't easily be assigned to daily parenting styles, so it's hard to manipulate this variable. it could be unethical to assign some people, especially children, to a condition in which they receive a certain type of praise, especially over a long time period. Particularly if we suspect that one type of praise might make children narcissistic, it would not be ethical to expose children to it in an experimental setting.
Confidence Interval
provides a range which is likely to include the true population value *By convention, confidence intervals correspond to the traditional alpha level of .05 and provide us with 95% confidence that our interval contains the true population value.
SELF-REPORTING MEMORIES OF EVENTS
psychological research has shown that people's memories about events in which they participated are not very accurate. **The other important finding from these studies is that people's confidence in the accuracy of their memories is virtually unrelated to how accurate the memories actually are. Three years later, people who are extremely confident in their memories are about as likely to be wrong as people who report their memories with little or no confidence.
FULL-LENGTH BOOKS
psychologists do not write many full-length scientific books for an audience of other psychologists. Those books that have been published are most likely to be found in academic libraries.
Causal Claim
replaces verb phrases such as related to, is associated with, or linked to with powerful verbs such as makes, influences, or affects.
Avoiding Selection Effects with Random Assignment
so each person must have an equal chance of being in each group randomly choosing where people are assigned makes it very unlikely that all of the same type of person will be placed in the same group **Random assignment is a way of desystematizing the types of participants who end up in each level of the independent variable.
In a biased sample, also called an unrepresentative sample
some members of the population of interest have a much higher probability of being included in the sample compared to other members.
Variance
standard deviation squared measure of how spread out the scores are
statistical validity of associated claims
statistical validity is the extent to which the statistical conclusions are accurate and reasonable. One aspect of statistical validity is strength: How strong is the association? Another question worth interrogating is the statistical significance of a particular association.
Measured variables
take the form of records of behavior or attitudes, such a self-reports, behavioral observations, or physiological measures
nonprobability sampling
techniques involve nonrandom sampling and result in a biased sample.
directionality problem
temporal precedence is called this because we don't know which variable came first.
experiment (specific meaning)
that the researchers manipulated at least one variable and measured another *must have at least one independent variable and one dependent variable, but they often have more than one dependent variable. *the independent variable is almost always on the x-axis, and the *independent variable must come first in time dependent variable is almost always on the y-axis **Experiments can take place in a laboratory and just about anywhere else: movie theaters, conference halls, zoos, daycare centers, and even online environments—anywhere a researcher can manipulate one variable and measure another.
spurious association
the bivariate correlation is there, but only because of some third variable.
population of interest.
the entire collection of individuals or objects about which information is desired
Covariance
the extent to which two variables are observed to go together, is determined by the results of a study.
median
the middle score in a distribution; half the scores are above it and half are below it
Statistical Significance of Beta
the p value gives the probability that the beta came from a population in which the relationship is zero. When p is less than .05, the beta (i.e., the relationship between that predictor variable and the criterion variable, when the other predictor variables are controlled for) is considered statistically significant. When p is greater than .05, the beta is considered not significant, meaning we cannot conclude beta is different from zero.
The sampling distribution of r is developed based on
the probable values of r we would get if we ran the study many times on random samples from a population in which the null hypothesis is true. **A larger r (a stronger r) is more likely to be statistically significant. However, the statistical significance of a value of r depends heavily on the sample size.
quota sampling
the researcher identifies subsets of the population of interest and then sets a target number for each category in the sample **the researcher samples from the population of interest nonrandomly until the quotas are filled.
Interpreting beta
the value given is the relationship between two variables are accounted for even when controlling for a variable *In sum, the beta that is associated with a predictor variable represents the relationship between that predictor variable and the criterion variable, when the other predictor variables in the table are controlled for.
SELF-REPORTING "MORE THAN THEY CAN KNOW"
they also ask whether people are capable of reporting accurately on their own feelings, thoughts, and actions. *In some cases, however, self-reports can be inaccurate, especially when people are asked to describe why they are thinking, behaving, or feeling the way they do. When asked, most people willingly provide an explanation or an opinion to a researcher, but sometimes they unintentionally give inaccurate responses. (Formulate answers that have nothing to do with the reason)
autocorrelations
they determine the correlation of one variable with itself, measured on two different occasions.
cross-sectional correlations
they test to see whether two variables, measured at the same point in time, are correlated.
Effect size
to describe the strength of the relationship between two variables. *Effect sizes are especially useful when we're not familiar with the scale on which a variable is measured. *In addition, the effect size from one study can be compared to the effect size from another study—even a study using different variables.
multistage sampling
two random samples are selected: a random sample of clusters, then a random sample of people within those clusters.
Likert Scale
typical five level example: 1 2 3 4 5 (strongly disagree to strongly agree) distance between each number should be equal can be questions or statements consider if you want points to have a neutral/middle option -may be hard to find concentration if no middle option -also don't want to force people to make a decision
descriptive statistics
used for organizing and summarizing the properties of a set of data.
Stemplot
used to display quantitative data, generally from small data sets (50 or fewer observations). *The values on the left of the line are called stems, and the values on the right are called leaves. To make a stemplot, we would first decide the units for the stems—tens, hundreds, thousands—using the most appropriate level for the data.
systematic sampling
using a computer or a random number table, the researcher starts by selecting two random numbers—say, 4 and 7. If the population of interest is a roomful of students, the researcher would start with the fourth person in the room and then count off, choosing every seventh person until the sample was the desired size.
convenience sampling
using a sample of people who are easy to contact and readily available to participate
data matrix
we usually enter the data in a grid format
Selection Effects
when the kinds of participants in one level of the independent variable are systematically different from those in the other They can also happen when the experimenters let participants choose (select) which group they want to be in. *A selection effect may result if the experimenters assign one type of person to one condition, and another type of person to another condition. **Threat to internal validity
no association
when the points in a scatter plot do not have any pattern
Behavioral Research is probabilistic
which means that its findings are not expected to explain all cases all of the time. **the conclusions of research are meant to explain a certain proportion (preferably a high proportion) of the possible cases. - test for a pattern **prediction is not perfect
COMPONENTS OF AN EMPIRICAL JOURNAL ARTICLE
written in standard format Abstract. The abstract is a concise summary of the article, about 120 words long. It briefly describes the study's hypotheses, method, and major results. Introduction. The introduction is the first section of regular text, and the first paragraphs typically explain the topic of the study. The middle paragraphs lay out the background for the research. What theory is being tested? What have past studies found? Why is the present study important? Pay attention to the final paragraph, which states the specific research questions, goals, or hypotheses for the current study. Method. The Method section explains in detail how the researchers conducted their study. It usually contains subsections such as Participants, Materials, Procedure, and Apparatus. Need repeat-ability Results. The Results section describes the quantitative and, as relevant, qualitative results of the study, including the statistical tests the authors used to analyze the data. Discussion. The opening paragraph of the Discussion section generally summarizes the study's research question and methods and indicates how well the results of the study supported the hypotheses. Next, the authors usually discuss the study's importance: Perhaps their hypothesis was new, or the method they used was a creative and unusual way to test a familiar hypothesis, or the participants were unlike others who had been studied before. In addition, the authors may discuss alternative explanations for their data and pose interesting questions raised by the research. References
internal reliability
(also called internal consistency), a study participant gives a consistent pattern of answers, no matter how the researcher has phrased the question. *applies only to self-report scales with multiple items. Suppose a sample of people take Diener's five-item subjective well-being scale. The questions on his scale are worded differently, but each item is intended to be a measure of the same construct. Therefore, people who agree with the first item on the scale should also agree with the second item
OPERATIONALIZING "HAPPINESS"
-"subjective well-being" (or well-being from a person's own perspective). -they chose to operationalize subjective well-being, in part, by asking people to report on their own happiness in a questionnaire format. The researchers decided people should use their own criteria to describe what constitutes a "good life" -These researchers operationally defined, or measured, subjective well-being by asking people to respond to five items about their satisfaction with life using a 7-point scale; 1 corresponded to "strongly disagree" and 7 corresponded to "strongly agree": 1. In most ways my life is close to my ideal. 2. The conditions of my life are excellent. 3. I am satisfied with my life. 4. So far I have gotten the important things I want in life. 5. If I could live my life over, I would change almost nothing. *The unhappiest people would get a total score of 5 on this self-report scale because they would answer "strongly disagree," or 1, to all five items. The happiest people would get a total score of 35 on this scale because they would answer "strongly agree," or 7, to all five items. Those at the neutral point would score 20—right in between satisfied and dissatisfied
Belmont Plus Two: APA's Five General Principles
-3 of the APA principles (A, D, and E in the table) are identical to the three main principles of the Belmont Report (beneficence, justice,and respect for persons). -Another principle is fidelity and responsibility (e.g., a clinical psychologist teaching in a university may not serve as a therapist to one of his or her classroom students, and psychologists must avoid sexual relationships with their students or clients). -The last APA principle is integrity (e.g., professors are obligated to teach accurately, and therapists are required to stay current on the empirical evidence for therapeutic techniques).
IRB rules
-An IRB panel in the U.S. includes five or more people, some of whom must come from specified backgrounds: -->At least one member must be a scientist -->one has to have academic interests outside the sciences, and -->one (or more) should be a community member who has no ties to the institution (such as a local pastor, a community leader, or an interested citizen). -In addition, when the IRB discusses a proposal to use prison participants, one member must be recruited as a designated prisoner advocate. -The IRB must consider particular questions for any research involving children. *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. *In most institutions, though, any study that poses risks to humans or that involves vulnerable populations must be reviewed by an in-person IRB meeting. *An effective IRB should not permit research that violates people's rights, research that poses unrea- sonable risk, or research that lacks a sound rationale. However, an effective IRB should not obstruct research, either. It should not prevent controversial—but still ethical—research questions from being investigated.
INFORMED CONSENT (STANDARD 8.02)
-As mentioned earlier, informed consent is the researcher's obligation to explain the study to potential participants in everyday language and give them a chance to decide whether to participate. -In most studies, informed consent is 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. -obtaining informed consent also involves informing people whether the data they provide in a research study will be treated as private and confidential. Nonconfidential data might put participants at some risk.
THE PRINCIPLE OF RESPECT FOR PERSONS
-First, individuals potentially involved in research should be treated as autonomous agents: They should be free to make up their own minds about whether they wish to participate in a research study. --->Applying this principle means that every partici- pant is entitled to the precaution of informed consent; each person learns about the research project, considers its risks and benefits, and decides whether to participate. (not allowed to be misleading or coercive) -The second application of respect for persons states that some people have less autonomy, so they are entitled to special protection when it comes to informed consent. --->For example, children, people with intellectual or developmental disabilities, and prisoners should be protected, according to the Belmont Report.
UNETHICAL CHOICES
-First, the men were not treated respectfully. The researchers lied to them about the nature of their participation and withheld information (such as penicillin as a cure for the disease); in so doing, they did not give the men a chance to make a fully informed decision about participating in the study. -Second, the men in the study were harmed. They and their families were not told about a treatment for a disease that, in the later years of the study, could be easily cured. -Third, the researchers targeted a disadvantaged social group in this study. Syphilis affects people from all ethnicities and social backgrounds, yet all the men in this study were poor and African American
ETHICAL PRINCIPLES IN PRACTICE
-Most universities and research hospitals have committees who decide whether research and practice are complying with ethical guidelines. -In the United States, federally funded agencies must follow the Common Rule, which describes detailed ways the Belmont Report should be applied in research -CITI Program
Attitudes of Scientists and Students Toward Animal Research.
-Nationally, about 47% of Americans favor the use of animals in research; the more education people have, the more likely they are to back it -when people read about the requirements stated in the AWA, they become more supportive of animal research *In other words, people seem to favor animal research more if they know it protects the welfare of animal subjects.
Legal Protection for Laboratory Animals.
-Psychologists who use animals in research must care for them humanely, must use as few animals and must be sure the research is valuable enough to justify using animal subjects. -In addition to these APA standards, psychologists must follow federal and local laws for animal care and protection. In the United States, the Animal Welfare Act (AWA) outlines standards and guidelines for the treatment of animals -the IACUC must approve any animal research project before it can begin -It must contain at least three members: a veterinarian, a practicing scientist who is familiar with the goals and procedures of animal research, and a member of the local community who is unconnected with the institution. -The IACUC requires researchers to submit an extensive protocol specifying how animals will be treated and protected. -Applicants must demonstrate that the proposed study has not already been done and explain why the research is important. **The AWA does not cover mice, rats, and birds, but such species are included in the oversight of IACUC boards.
DECEPTION (STANDARD 8.07)
-Researchers withheld some details of the study from participants—deception through omission; in some cases, they actively lied to them—deception through commission. -Deceiving research participants by lying to them or by withholding information is, in many cases, necessary in order to obtain meaningful results. -In a deception study, researchers must still uphold the principle of respect for persons by informing participants of the study's activities, risks, and benefits. -Results indicate students usually tolerate minor deception and even some discomfort or stress, considering them necessary parts of research. -When students do find deception to be stressful, these negative effects are diminished when the researchers fully explain the deception in a debriefing session
The Tuskegee Syphilis Study Illustrates Three Major Ethics Violations
-The researchers wanted to study the effects of untreated syphilis on the men's health over the long term. At the time, no treatment was a reasonable choice because the risky methods available in 1932 were not likely to work -Infected men were told they had "bad blood" instead of syphilis. -The researchers told them they were being treated, and all of them were required to come to the Tuskegee clinic for evaluation and testing. But they were never given any beneficial treatment. -At one point, in fact, the researchers had to conduct a painful, potentially dangerous spinal tap procedure on every participant, in order to follow the progression of the disease. To ensure that they would come in for the procedure, the researchers lied, telling the men it was a "special free treatment" for their illness -the researchers interfered by preventing the men from being treated. As a result, they could not serve in the armed forces or receive subsequent G. I. benefits -In 1943, the PHS approved the use of penicillin for treating syphilis, yet the Tuskegee Institute did not provide information about this new cure to the participants in their study.
SCATTERPLOTS CAN SHOW INTERRATER AGREEMENT OR DISAGREEMENT
-The two observers do not show perfect agreement, but there are no great disagreements about the happiest and least happy kids. Again, the points are scattered around the plot a bit, but they hover close to the sloping line that would indicate perfect agreement -One reason could be that the observers did not have a clear enough operational definition of "happiness" to work with. Another reason could be that one or both of the coders has not been trained well enough yet. *A scatterplot can thus be a helpful tool for visualizing the agreement between two administrations of the same measurement (test-retest reliability) or between two coders (interrater reliability).
DEBRIEFING (STANDARD 8.08)
-When researchers have used deception, they must spend time after the study talking with each participant in a structured conversation. In a debriefing session, the researchers describe the nature of the deception and explain why it was necessary. -Nondeceptive studies often include a debriefing session
The Milgram Obedience Studies Illustrate a Difficult Ethical Balance
-You are told there are two participants: you, the "teacher," and another participant, the "learner." As teacher, your job is to punish the learner when he makes mistakes in a learning task. The learner slips into a cubicle where you can't see him, and the session begins -As the study goes on, you are told to punish the learner for errors by administering electric shocks at increasingly higher intensities, as indicated on an imposing piece of equipment in front of you: the "shock generator." -If you protest (and you probably would), the experimenter behind you says calmly, "Continue." If you protest again, the experimenter says, again calmly, "The experiment requires that you continue" -a paid actor playing a role, and he did not actually receive any shocks. The participants did not know this; they thought the learner was an innocent, friendly man. -variations: a heart condition; this made no difference, and the level of obedience remained at about 65%. the learner sat right in the room with the teacher- participant; this time the obedience level dropped to 40% the experimenter supervised the situation from down the hall, over the phone. The obedience level also dropped, and only 20% of participants delivered all the shocks.
THE PRINCIPLE OF JUSTICE
-calls for a fair balance between the kinds of people who participate in research and the kinds of people who benefit from it. -When the principle of justice is applied, it means that researchers might first ensure that the participants involved in a study are representative of the kinds of people who would also benefit from its results. **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 they are studying is especially prevalent in that ethnic group or in that type of institution.
Research Misconduct: Plagiarism (Standard 8.11).
-defined as representing the ideas or words of others as one's own. - A formal definition, provided by the U.S. Office of Science and Technology Policy, states that plagiarism is "the appropriation of another person's ideas, processes, results, or words without giving appropriate credit" -Academics and researchers consider plagiarism a violation of ethics because it is unfair for a researcher to take credit for another person's intellectual property: It is a form of stealing. -a writer must cite the sources of all ideas that are not his or her own, to give appropriate credit to the original authors. -When a writer describes or paraphrases another person's ideas, the writer must cite the original author's last name and the year of publication. Writers must be careful not to paraphrase the original text too closely; failure to put the original source in one's own words is a form of plagiarism.
convergent validity
-ex: If the BDI really quanitfies depression, the researchers reasoned, it should be correlated with (should converge with) other self-report measures of depression *Testing for convergent validity can feel circular. Even if researchers validate the BDI with the CES-D, for instance, there is no assurance that the CES-D measure is a gold standard.
dicriminant vaidity
-ex: The BDI should not correlate strongly with measures of constructs that are very different from depression; it should show discriminant validity with them **Instead, researchers focus on discriminant validity when they want to be sure their measure is not accidentally capturing a similar but different construct.
When informed consent forms aren't necessary:
-if the study is not likely to cause harm and if it takes place in an educational setting. -when participants answer a completely anonymous questionnaire in which their answers are not linked to their names in any way. -the study involves naturalistic observation of participants in low-risk public settings, such as a museum, classroom, or mall—where people can reasonably expect to be observed by others anyway.
An institutional review board (IRB)
-is a committee responsible for interpreting ethical principles and ensuring that research using human participants is conducted ethically -IRBs are mandated by federal law. If an institution uses federal money (such as government grants) to carry out research projects, a designated IRB is required. -However, in the United States, research conducted by private businesses does not have to use an IRB or follow any particular ethical guidelines
BALANCING RISK TO PARTICIPANTS WITH BENEFIT TO SOCIETY
-it was extremely stressful to the teacher-participants -the participants were debriefed; they were carefully informed about the study's hypotheses. -They shook hands with the learner, who reassured them he was unharmed. However, in order to avoid influencing potential future participants, the debriefing never mentioned that the learner did not receive shocks -some worried about the learners well being for weeks after -Experts at the time predicted that only 1-2% of people would obey the experimenter up to 450 volts. After the first variation of the study, however, Milgram knew what kind of behavior to expect - Benefits: -crucial lessons about obedience to authority and the "power of the situation"—lessons we would not have learned without his research -Milgram had an associate call some of the participants at home, months later, to ask about their current state of well-being. Some of them felt they had learned something important.
THE PRINCIPLE OF BENEFICENCE
-researchers must take precautions to protect participants from harm and to ensure their well-being. To apply this principle, researchers need to carefully assess the risks and benefits of the study they plan to conduct. In addition, they must consider how the community might benefit or be harmed. -In an anonymous study, researchers do not collect any potentially identifying information, including names, birthdays, photos, and so on. Anonymous online surveys will even strip away the identifiers of the computer used. -In a confidential study, researchers collect some identifying information (for contacting people at a later date if needed), but prevent it from being disclosed. -Just as it's hard to evaluate emotional or psychological harm, it is difficult to evaluate how damaging a study like Milgram's might be. However,the principle of beneficence demands that researchers consider such risks (and benefits) before beginning each study. **As a point of reference, some institutions ask researchers to estimate how stressful a study's situation would be compared with the normal stresses of everyday life. -The other side of the balance—the benefits of psychological research to the community—may not be easy to assess either.
Attitudes of Animal Rights Groups.
-some groups have increased their visibility and have assumed a more extreme position—arguing for animal rights, rather than animal welfare -Two main arguments: -->First, they may believe animals are just as likely as humans to experience suffering. They feel humans should not be elevated above other animals: Because all kinds of animals can suffer, all of them should be protected from painful research procedures. According to this view, a certain type of research with animals could be allowed, but only if it might also be permitted with human participants. -->Second, some groups also believe animals have inherent rights, equal to those of humans. These activists argue that most researchers do not treat animals as creatures with rights; instead, animals are treated as resources to be used and discarded. In a way, this argument draws on the principle of justice, as outlined in the Belmont Report and the APA Ethical Principles: Animal rights activists do not believe animals should unduly bear the burden of research that benefits a different species (humans).
Research Misconduct: Data Fabrication (Standard 8.10) and Data Falsification.
1. Data fabrication occurs when, instead of recording what really happened in a study (or sometimes instead of running a study at all), researchers invent data that fit their hypotheses. 2. Data falsification occurs when researchers influence a study's results, perhaps by selectively deleting observations from a data set or by influencing their research subjects to act in the hypothesized way. -Scientists use data to test their theories, and they can do so only if they know that previously reported data are true and accurate. -When people fabricate data, they mislead others about the actual state of support for a theory. Fabricated data might inspire other researchers to spend time (and, often, grant money) following a false lead or to be more confident in theories than they should be.
Reliability of 3 types of tests
1. Test-Retest: we would measure the same set of participants on that measure at least twice If r turns out to be positive and strong (for test-retest, we might expect .5 or above), we would have very good test-retest reliability. If r is positive but weak, we would know that participants' scores on the test changed from Time 1 to Time 2. A low r would be a sign of poor reliability if we are measuring something that should stay the same over time. 2. Interrater: To test interrater reliability of some measure, we might ask two observers to rate the same participants at the same time, and then we would compute r. If r is positive and strong (according to many researchers, r = .70 or higher), we would have very good interrater reliability. If r is positive but weak, we could not trust the observers' ratings. We would retrain the coders or refine our operational definition so it can be more reliably coded. A negative r would indicate a big problem 3. Internal: Internal reliability is relevant for measures that use more than one item to get at the same construct researchers need to assess the scale's internal reliability to evaluate whether people responded consistently to each item
THE CUPBOARD THEORY VS. THE CONTACT COMFORT THEORY
1. The cupboard theory of mother-infant attachment, is that a mother is valuable to a baby mammal because she is a source of food. 2. Instead, babies are attached to their mothers because of the comfort of cozy touch. This is the contact comfort theory The contact comfort theory would be supported if the babies spent most of their time clinging to the cloth mother. The cupboard theory would be supported if the babies spent most of their time clinging to the wire mother. Neither theory would be supported if monkeys divided their time equally between the two mothers ***the evidence in favor of the contact comfort theory was overwhelming Theory-data cycle
Ways psychologists approach their work
1. act as empiricists to systematically observe the world. 2. they test theories through research and, in turn, revise their theories based on the resulting data. 3.they take an empirical approach to both applied research, which directly targets real-world problems, and basic research, which is intended to contribute to the general body of knowledge. 4. Once they have discovered an effect, scientists plan further research to test why, when, or for whom an effect works. 5. They submit their results to journals for review and respond to the opinions of other scientists. Another aspect of making work public involves sharing findings of psychological research with the popular media, who may or may not get the story right.
Ethically Balancing Animal Welfare, Animal Rights, and Animal Research.
Animal researchers defend their use of animal subjects with three primary arguments. 1. Animal research has resulted in numerous benefits to humans and animals alike. Animal research has contributed countless valuable lessons about psychology, biology, and neuroscience; discoveries about basic processes of vision, the organization of the brain, the course of infection, disease prevention, and therapeutic drugs. 2.Animal researchers are sensitive to animal welfare. They think about the pain and suffering of animals in their studies and take steps to avoid or reduce it. The IACUC oversight process and the Guide for the Care and Use of Laboratory Animals help ensure that animals are treated with care. 3. Researchers have successfully reduced the number of animals they need to use because of new procedures that do not require animal testing. Some animal researchers even believe animal rights groups have exaggerated (or fabricated, in some cases) the cruelty of animal research and that some activists have largely ignored the valuable scientific and medical discoveries that have resulted from animal research.
construct validity
Before using particular operationalizations in a study, researchers not only check to be sure the measures are reliable; they also want to be sure they get at the conceptual variables they were intended for. **Measurement reliability and measurement validity are separate steps in establishing construct validity. It may not measure what it's supposed to measure. **esp important when a construct is not directly observable
r vs slope
Notice that when the slope is positive, r is positive; when the slope is negative, r is negative. The value of r can fall only between 1.0 and -1.0. When the relationship is strong, r is close to either 1 or -1; when the relationship is weak, r is closer to zero. An r of 1.0 represents the strongest possible positive relationship, and an r of -1.0 represents the strongest possible negative relationship. If there is no relationship between two variables, r will be .00 or close to .00
Peer Review
Peer reviewers are kept anonymous, so even if they know the author of the article professionally or personally, they can feel free to give an honest assessment of the research. They comment on how interesting the work is, how novel it is, how well the research was done, and how clear the results are. Ultimately, peer reviewers are supposed to ensure that the articles published in scientific journals contain innovative, well-done studies. When the peer-review process works, research with major flaws does not get published. However, the process continues even after a study is published. Other scientists can cite an article and do further work on the same subject. Moreover, scientists who find flaws in the research (perhaps overlooked by the peer reviewers) can publish letters, commentaries, or competing studies
OPERATIONALIZING OTHER CONCEPTUAL VARIABLES
They start by stating a definition of their construct (the conceptual variable) and then create an operational definition Any conceptual variable can be operationalized in a number of ways. In fact, operationalizations are one place where creativity comes into the research process, as researchers work to develop new and better measures of their constructs.
content validity
a measure must capture all parts of a defined construct
simple random sampling.
a probability sampling procedure in which every sampling unit has a known and equal chance of being selected -ex: everyone numbered and random number generator picks as many people as how big the population should be
Theory
a set of statements that describes general principles about how variables relate to one another.
facial electromyography (EMG)
a way of electronically recording tiny movements in the muscles in the face. Facial EMG can be said to detect a happy facial expression because people who are smiling show particular patterns of muscle movement around the eyes and cheeks
the levels of quantitative variables
are coded with meaningful numbers. Ex: Height and weight are quantitative because they are measured in numbers Diener's scale of subjective well-being is quantitative too, because a score of 35 represents more happiness than a score of 7. IQ score, level of brain activity, and amount of salivary cortisol are also quantitative variables.
The levels of categorical variables
as the term suggests, are categories. (Categorical variables are also called nominal variables.)
Validity
concerns whether the operationalization is measuring what it is supposed to measure
interrater reliability
consistent scores are obtained no matter who measures the variable *With interrater reliability, two or more independent observers will come up with consistent (or very similar) findings. Interrater reliability is most relevant for observational measures
Cronbach's alpha (or coefficient alpha)
correlational-based stat to see if their measurement scales have internal reliability. 1. collect data on the scale from a large sample of participants, and then they compute all possible correlations among the items. The formula for Cronbach's alpha returns one number, computed from the average of the inter-item correlations and the number of items in the scale. The closer the Cronbach's alpha is to 1.0, the better the scale's reliability. (For self-report measures, researchers are looking for Cronbach's alpha of .70 or higher.) If Cronbach's alpha is high, there is good internal reliability and researchers can sum all the items together. If Cronbach's alpha is less than .70, then internal reliability is poor and the researchers are not justified in combining all the items into one scale
Criterion validity
evaluates whether the measure under consideration is associated with a concrete behavioral outcome that it should be associated with, according to the conceptual definition (empirical evidence)-looks good face value but then can actually back it up
Producer role is important
even if you do not conduct your own research, you will at least have to write papers. important to know how research works (To succeed, you will need to know how to randomly assign people to groups, how to measure attitudes accurately, or how to interpret results from a graph)
Parsimony
having a simple theory *As long as a simple theory predicts the data well, there should be no need to make the theory more complex
face validity
if it is subjectively considered to be a plausible operationalization of the conceptual variable in question *their opinion on how reasonable the scale is as a way of estimating
Journalism
in contrast, includes the kinds of news and commentary that most of us read or hear on television, in magazines and newspapers, and on Internet sites—articles in Psychology Today and Men's Health, topical blogs, relationship advice columns, and so on. These sources are usually written by journalists or laypeople, not scientists, and they are meant to reach the general public; they are easy to access, and understanding their content does not require specialized education. **sometimes not good because can tell the public inaccurate information (if study wasn't peer-reviewed) **may not understand the scientific language and write false information
known-groups paradigm
in which researchers see whether scores on the measure can discriminate among two or more groups whose behavior is already confirmed ex: If skin conductance and heart rate are valid measures of lying, we could conduct a known-groups test in which we know in advance which of a person's statements are true and which are false. The physiological measures should be elevated only for the lies, not for the true statements. -ex: BDI and SWB **can also be used to validate self-report measures.
Applied Research
is done with a practical problem in mind; the researchers conduct their work in a particular real-world context. An applied research study might ask, for example, if a school district's new method of teaching language arts is working better than the former one. It might test the efficacy of a treatment for depression in a sample of trauma survivors. Applied researchers might be looking for better ways to identify those who are likely to do well at a particular job, and so on
Basic Research
is not intended to address a specific, practical problem; the goal is to enhance the general body of knowledge. Basic researchers might want to understand the structure of the visual system, the capacity of human memory, the motivations of a depressed person, or the limitations of the infant attachment system. Basic researchers do not just gather facts at random; in fact, the knowledge they generate may be applied to real-world issues later on
The most important feature of a scientific theory
is that it is supported by data from research studies
The conceptual definition, or construct
is the researcher's definition of the variable in question at a theoretical level.
translational research
is the use of lessons from basic research to develop and test applications to health care, psychotherapy, or other forms of treatment and intervention. Translational research represents a dynamic bridge from basic to applied research. For example, basic research on the biochemistry of cell membranes might be translated into a new drug for schizophrenia. Or basic research on how mindfulness changes people's patterns of attention might be translated into a study skills intervention
empiricist
means basing one's conclusions on systematic observations aim to be systematic, rigorous, and to make their work independently verifiable by other observers or scientists
A self-report
measure operationalizes a variable by recording people's answers to questions about themselves in a questionnaire or interview. **In research on children, self-reports may be replaced with parent reports or teacher reports
A physiological way to operationalize stress
might be to measure the amount of the hormone cortisol released in saliva because people under stress show higher levels of cortisol Skin conductance, an electronic recording of the activity in the sweat glands of the hands or feet, is another way to measure stress physiologically. People under more stress have more activity in these glands. Another physiological measure used in psychology research is the detection of electrical patterns in the brain using electroencephalography (EEG).
Measurements
must pick measurements that are relevant or else data is useless *Many of the phenomena psychologists are interested in— motivation, emotion, thinking, reasoning—are difficult to measure
Consumer role is also important
need to know how to read and process information
An interval scale
of measurement applies to the numerals of a quantitative variable that meet two conditions: First, the numerals represent equal intervals (distances) between levels, and second, there is no "true zero" (a person can get a score of 0, but the 0 does not really mean "nothing") -IQ test, Temp.
A ratio scale
of measurement applies when the numerals of a quantitative variable have equal intervals and when the value of 0 truly means "none" or "nothing" of the variable being measured -Ex: how many times blinked eyes
An ordinal scale
of measurement applies when the numerals of a quantitative variable represent a ranked order For example, a bookstore's website might display the top 10 best-selling books. We know that the #1 book sold more than the #2 book, and that #2 sold more than #3, but we don't know whether the number of books that separates #1 and #2 is equal to the number of books that separates #2 and #3. In other words, the intervals may be unequal
correlation coefficient
or r, to indicate how close the dots, or points, on a scatterplot are to a line drawn through them.
fMRI
people engage in a carefully structured series of psychological tasks (such as looking at three types of photos or playing a series of rock-paper-scissors games) while lying in an MRI machine. The MRI equipment records and codes the relative changes in blood flow in particular regions of the brain *Specifically, the brains of people with higher intelligence are more efficient at solving complex problems; their fMRI scans show relatively less brain activity for complex problems
Reliability
refers to how consistent the results of a measure are
The operational definition
represents a researcher's specific decision about how to measure or manipulate the conceptual variable.
open-ended questions
respondents to answer any way they like. *The drawback is that the responses must be coded and categorized, a process that is often difficult and time-consuming. In the interest of efficiency, therefore, researchers in psychology often restrict the answers
the Nuremberg Trials
revealed the horror of medical experiments conducted on concentration camp victims in Nazi-occupied Europe after WWII and resulted in the Nuremberg Code.
Likert Scale vs Likert Type Scale
scale contains more than one item and each response value is labeled with the specific terms strongly agree, agree, neither agree nor disagree, disagree, and strongly disagree, it is often called a Likert scale If it does not follow this format exactly (e.g., if it has only one item, or if its response labels are a bit different from the original Likert labels) it may be called a Likert-type scale.
Researchers may use two statistical devices for data analysis:
scatterplots and the correlation coefficient r
theory-data cycle
scientists collect data to test, change, or update their theories. First, you asked a particular set of questions, all of which were guided by your theories. Your theory set you up to ask certain questions and not others. Next, your questions led you to specific predictions, which you tested by collecting data
weight of the evidence
scientists look at their study this way to see how much data is for or against it
As researchers decide how they should operationalize each variable in a study, they choose among three common types of measures:
self-report, observational, and physiological.
It's important to be a good consumer
should look into research and be able to interpret the findings to see if something actually is true
An observational measure
sometimes called a behavioral measure, operationalizes a variable by recording observable behaviors or physical traces of behaviors. *Observational measures may record physical traces of behavior.
The Belmont Report: Principles and Applications
the Belmont Report, which outlines three main principles for guiding ethical decision making: respect for persons, beneficence, and justice. Each principle has standard applications.
operationalization
the process of turning a construct of interest into a measured or manipulated variable
testretest reliability
the researcher gets consistent scores every time he or she uses the measure **The highest-scoring Time 1 people should still be the highest scoring people at Time 2. Test-retest reliability can apply whether the operationalization is self-report, observational, or physiological, but it's most relevant when researchers are measuring constructs (such as intelligence, personality, or gratitude) they expect to be relatively stable
convergent and discriminant validity
there is a meaningful pattern of similarities and differences among self-report measures. A self-report measure should correlate more strongly with self-report measures of similar constructs than it does with those of dissimilar constructs
consumers of research
those who read and evaluate studies
empiricism
to answer psychological questions with direct, formal observations, and to communicate with others about what they have learned. *involves using evidence from the senses (sight, hearing, touch) or from instruments that assist the senses (such as thermometers, timers, photographs, weight scales, and questionnaires) as the basis for conclusions.
Journal
usually come out every month and contain articles written by various qualified contributors. But unlike popular newsstand magazines, the articles in a scientific journal are peer-reviewed. The journal editor sends the submission to three or four experts on the subject. The experts tell the editor about the work's virtues and flaws, and the editor, considering these reviews, decides whether the paper deserves to be published in the journal
