Measurement & Validity
What is the difference between a conceptual variable and its operational definition?
A conceptual variable is the idea or construct; the operational definition is how it is measured in a study.
What is a longitudinal design?
A study that measures variables in the same people at multiple time points.
What is the purpose of random assignment?
To control for confounding variables and increase internal validity.
What does a 2 × 2 design indicate?
Two independent variables with two levels each.
What is a mediator?
A variable that explains the relationship between an independent and dependent variable.
Name three ways to operationalize a variable.
Self-report, observational, physiological.
What is an autocorrelation?
The correlation of a variable with itself over time.
What are design confounds?
Flaws in the experiment that provide alternative explanations for the results.
What is an interaction effect?
When the effect of one variable depends on the level of another.
What’s the difference between a mediator and a third variable?
Mediators are part of the causal pathway; third variables are confounds.
What kind of variable is temperature in degrees Fahrenheit?
Quantitative, interval scale.
What is a cross-lag correlation and why is it important?
It assesses whether earlier measures of one variable predict later measures of another, helping infer directionality.
What is the difference between posttest-only and pretest/posttest designs?
Posttest-only measures outcomes after manipulation; pretest/posttest measures before and after.
What is a main effect?
The overall effect of one independent variable, averaging over levels of the other.
What is a moderating variable?
A variable that changes the strength or direction of a relationship.
What type of validity is tested by comparing a measure with an outcome (e.g., job performance)?
Criterion validity.
What is a criterion variable in regression?
The dependent variable being predicted.
What does the effect size “d” represent?
The strength of the difference between group means in an experiment.
In a graph, how can you tell if there’s an interaction?
If the lines are not parallel.
A study finds that exercise is related to better sleep, and this relationship is explained by a reduction in stress levels. What role does stress play in this relationship?
Stress is a mediator because it explains how exercise leads to better sleep.
What does a high correlation (r) between items on a scale suggest about the measure?
High internal reliability.
Why are experiments superior to regression in controlling for third variables?
Because experiments use random assignment to eliminate confounds.
Name three internal validity threats that can occur over time in within-subjects or repeated-measures designs.
Varies; Maturation, History, Regression to the Mean, Attrition, Testing, Instrumentation, Design Confounds, Selection Effects, Order Effects, Observer Bias, Demand Characteristics, Placebo Effect
What does a three-way interaction mean?
That the two-way interaction differs depending on the level of a third variable.
A researcher finds that social support reduces anxiety, but only for students living on campus, not for commuters. What kind of variable is “living situation”?
A moderator; it changes the strength or direction of the relationship between social support and anxiety.