Ch.6: Surveys & Observations
A survey question that asks two questions in one, leading to issues in construct validity.
What is a double-barreled question?
When participants select themselves to be a part of a study.
What is self-selection?
A type of study has all measured variables.
What is a correlational study?
The variable that predicts another variable in a multiple regression analysis.
What is a predictor variable?
A variable that an experimenter holds constant on purpose.
What is a control variable?
Participants who respond "yes" or "strongly agree" to every item in a survey.
What is acquiescence?
Researchers asking participants to recommend people they know to participate in their study.
What is snowball sampling?
A relationship between two variables that exists, but is not linear.
What is a curvilinear relationship?
A multivariate design that runs a variety of correlational studies that all point in a single causal direction.
What is the pattern and parsimony approach?
A technique to avoid order effects in within-groups designs.
What is counterbalancing?
When an observer inadvertently changes the behavior of those they are observing.
What are observer (expectancy) effects?
What is systematic sampling?
The significance value (p) must be less than this value to be considered statistically significant.
What is 0.05?
The only causal criteria that longitudinal studies do not meet.
What is internal validity?
Two techniques to avoid selection effects.
What is random assignment and matched groups?
Research designs where neither the participants nor the researchers are aware of which condition participants are assigned to.
What is a double-masked (blind) design?
A random sampling technique that purposefully selects demographic categories and randomly selects from each.
What is stratified random sampling?
A variable that changes the relationship between two variables.
What is a moderator (moderating variable)?
A variable that explains why two variables are related.
What is a mediator?
When differences between the treatment and control group exists because of the manipulation of the IV and not due to potential confounds.
What is unsystematic variability?
Four ways to prevent socially desirable responding in your survey.
What are participant anonymity, conducing an online survey, having participants respond quickly, and discarding participant data from the final set?
The validity that is most important when making a frequency claim.
What is external validity?
A correlation coefficient r of -0.31.
What is a negative moderate correlation?
A coefficient that shows the relationship between the predictor and criterion variables when other predictor variables are controlled for and is interpreted similarly to the correlation coefficient r.
What is coefficient beta (β)?
When systematic differences between groups exist, not because of the successful manipulation of the IV, but because of the presence of confounds.
What is a selection effect?