Chapter 2 Flashcards
What is hindsight bias?
The tendency to overestimate our ability to have foreseen an outcome after learning the outcome.
What is confirmation bias?
The tendency to seek out, pay attention to, and believe only evidence that supports what we are already confident we know.
What is a theory?
An integrated set of related principles that explains and generates predictions about some phenomenon in the world
What is a hypothesis?
A testable prediction about what will happen under specific circumstances if the theory is correct.
What is a variable?
Anything that can take on different values.
What is data?
A set of observations that are gathered to evaluate the hypothesis
What is a measured variable? (dependent)
A variable whose values are simply recorded. These are included in every study.
What is a manipulated variable? (Independent)
A variable whose values the researcher controls, usually by assigning different participants to different levels of that variable.
What is operational definition?
The specific way of measuring or manipulating an abstract variable in a particular study. Operationalizing a variable usually means turning it into a number, which can be recorded and analyzed.
What does self-report consist of?
People describe themselves and/or their behavior in an interview or survey, using a rating scale.
What are the advantages of self-report?
- Easy
- Relatively inexpensive
(May allow us to collect data from more participants, which will make our study stronger)
What are the limitations of self-report?
- Social desirability bias
- Self-deceptive enhancement
What is social desirability bias?
The tendency to answer questions in a manner that will be viewed favorably by others (can be mitigated with anonymous participation)
What is self-deceptive enhancement?
Honestly held but unrealistic selfviews.
-May be difficult to identify and verbalize experience
-Not always aware of why we do the things we do
-Often relies on retrospective report (memories may be inaccurate or biased)
(can be mitigated using eventcontingent recording)
What is eventcontingent recording?
When participants are asked to report their experience right after it happens.
What does direct observation consist of?
Researchers observe and record the occurrence of behavior.
What are the advantages of direct observation?
- More objective than self-report
- May observe real-world behavior, or at least a good approximation of it
What are the limitations to direct observation?
- Expensive
- Time-consuming
- Difficult
- Not able to recruit as many participants
- Staying consistent and objective
What is a population of interest?
The full set of cases the researcher is interested in.
What is a sample?
The group who participated in research, and who belongs to the population of interest.
What is a random sample?
A sample in which every person in the population of interest has an equal chance of being included.
What are many research findings in social psychology often based on?
WEIRD (White, Educated, Industrialized, Rich, and Democratic) samples
What is the acronym WEIRD for?
White, Educated, Industrialized, Rich, Democratic
Is it possible to obtain a random sample of a country?
No
What is descriptive research?
Observing and measuring without manipulating variables. Often the first step in scientific research
What is correlational research?
A type of study that measures two (or more) variables in the same sample of people, and then observes the relationship between them.
How can we interpret a scatterplot?
By looking at:
1. The direction of the relationship (positive = sloping upwards, negative = sloping downwards)
2. The strength of the relationship (are the dots clustered of spread out)
What is the range of the r coefficient?
From -1.0 to 1.0
How is the direction of a relationship indicated?
By + (positive) or - (negative)
The closer to 0, the _____ the relationship.
weaker
The closer to -1 or 1, the _____ the relationship.
stronger
Correlation does not imply _____.
causation
What is needed to establish causality?
- 2 variables must be compared
- One variable must precede the other
- There must be no reasonable alternative explanations for the pattern of correlation
What is the gold standard for establishing causality?
The experiment
What is experimental research?
A study in which one variable is manipulated, and the other is measured.
What is a control group?
A condition comparable to the experimental condition in every way except that it lacks the one “ingredient” hypothesized to produce the expected effect on the dependent variable.
What is a moderator?
A third variable that affects the strength and the direction of the relationship between two related variables.
What is a mediator?
A third variable that explains the relationship between 2 variables.
What does measurement validity or construct validity ask?
Are you measuring what you think you are measuring?
What does reliability ask?
Do you get the same results every time you administer the measure?
What two kinds of reliability are there?
- Test-retest reliability
- Inter-rater reliability
Is it possible that a measure might be reliable, but not valid?
Yes
What does internal validity ask?
Can we rule out alternative explanations in an experiment?
What is internal validity threatened by?
The presence of confounds.
What is a confound in a research experiment?
An alternative explanation for a relationship between two variables.
When can confounds occur?
When 2 experimental groups accidentally differ on more than just the independent variable.
How can you avoid threats to internal validity?
- Make sure your experimental conditions only vary on the variable you are interested in
- Use random assignment (+ differential attrition)
- Standardize study scripts/instructions
- Do not reveal hypotheses
- Make the study double-blind if possible
(3,4,5: limits problems related to experimenter bias and/or demand characteristics)
What does external validity ask?
- Can our results be generalized to other samples?
- Can our results be generalized to other situations?
Is it difficult to establish high internal and external validity in the same study?
Yes
How can we get a study that has the most external validity?
Collect more data!
What is the null hypothesis?
The hypothesis of no effect.
What do we do in statistical significance testing?
We compare our results against the null hypothesis
What is a statistically significant finding?
A finding that provides sufficient evidence against the
null hypothesis.
What do p-values tell us?
The probability of getting a result as extreme as the one we observed if there really were no difference between the two groups (or no relationship between two variables)
What happens when the p-value is < .05?
We reject the null
What happens when the p-value is > .05?
We do not reject the null
What values can p-values take?
Anything between 0 and 1
What is the threshold for the p-value to determine if something is statistically significant?
.05
What do p-values not mean?
- That the hypothesis is “true” or “false”
- That the finding is important from a practical point of view
What does the p-value indicate regarding the null hypothesis?
The likelihood of the sample data occurring under the null hypothesis
What are the factors that affect the size of p-values?
- The size of the observed effect (larger effects are more likely to be statistically significant)
- The number of participants in our study (the more participants we have, the more likely the results will be significant)
- With very large samples, even small effects may be statistically significant (remember that statistical significance =/= practical significance)
What does statistical significance not mean?
Practical significance
Can a study prove anything?
No!
What is a replication study?
A study that repeats a previous study with identical or similar methods but different participants to see if the original finding can be repeated
What do direct replications attempt to do?
Recreate the original experiment exactly
What do conceptual replications try to do?
Recapture the original finding using different methods or measures
What are the 2 kinds of replication studies?
- Direct replications
- Conceptual replications
What could a fake replication mean?
-Original result was a fluke
-Original research was faulty
-Replication result was a fluke
-Replication research was faulty or did not capture the dynamics of the original study
What can unsuccessful replications lead us to do?
They can lead us to re-evaluate our methods, our theories, or lead us to identify important contextual effects.
What is an IRB?
An Institutional Review Board
What is a REB?
A Research Ethics Board
What do IRBs and REBs do?
They review research proposals and ensure that research complies with provincial, national, and international guidelines for ethics in research
Is it true that research involving psychological or physical discomfort or pain never allowed?
No. But the costs must be outweighed by the benefits of the research
What is informed consent?
An individual’s signed agreement to participate in a research study.
When can informed consent only be given?
After all relevant aspects of the study have
been explained to the individual
What is deception?
The act of causing someone to accept as true or valid what is false or invalid
What are 2 reasons for deception?
- It may be required to create the conditions necessary to test the hypothesis
- Participants’ knowledge of true purpose of the study may affect their responses
What is debriefing?
When a researcher explains the purpose of a study at the end of it, the use of deception (if any was used), and encourages the participant to ask questions about the study. The opportunity to withdraw data is given, and there is an attempt to restore a sense of well-being. Debriefing can serve as a useful source of information for researchers, and may even indicate need for adjustments. It provides a sense of the participants’s experience; may inform interpretation of results and inform future research.
What is the Milgram’s obedience study?
The study where a teacher would allegedly give electric shocks to a student when he would get something wrong.
How do ethical guidelines determine whether a study can have place or not?
-Costs vs. benefits
-Informed consent
-Deception must be justified
-Adequate debriefing
-Confidentiality