1/59
Looks like no tags are added yet.
What criterion for causation asks whether the cause occurred before the effect?
Temporal precedence
Which design best supports causal claims?
True experiment
What is it called when a second variable systematically varies with the IV?
Design confound
What is the best method for reducing selection effects?
Random assignment
What is a within-groups design?
A design in which each participant experiences every level of the IV
Practicing a task multiple times improves performance due to what?
Practice effect
What is the primary purpose of counterbalancing?
To reduce order effects
What design assigns participants to Treatment A or B and measures them only once afterward?
Posttest-only design
What threat occurs when participants are selected because of extremely high or low scores?
Regression to the mean
Using different raters at pretest and posttest creates what threat?
Instrumentation
What is required for a factorial design?
Two or more independent variables
How many cells are in a 4 × 3 factorial design?
12 cells
How many cells are in a 3 × 4 × 2 factorial design?
24 cells
What is a participant variable?
A variable that is measured but not manipulated
Age is usually considered what type of variable?
Participant variable
What is the overall effect of one IV averaged across another IV called?
Main effect
What is an interaction in a factorial design?
When the effect of one IV depends on the level of another IV
When interpreting factorial results, what should be examined first?
Interactions
What do parallel lines on a graph usually indicate?
No interaction
What do crossing lines on a graph usually indicate?
Crossover interaction
How many cells are in a 2 × 5 factorial design?
10 cells
In the Milkman study, how were ethnicity and sex manipulated?
Through names used in emails
What was the dependent variable in the Milkman study?
Whether professors responded
What was the primary problem in the smartphone water bottle study?
Selection effect
In the distributed studying study, spacing was confounded with what?
Total study time
What did the rear visibility automobile study demonstrate?
No major internal validity problem
Assigning entire classrooms to conditions most directly creates what problem?
Selection effects
Assigning the first consent forms returned to one condition creates what problem?
Selection effects
Having Julie run one condition and Matthew run the other creates what problem?
Design confound
Moving weaker readers from ABCmouse to Pig Pile violates what principle?
Random assignment
What feature is missing in all quasi-experiments?
Random assignment
How are groups typically defined in quasi-experiments?
By preexisting characteristics or events
Which quasi-experimental design includes only posttest measurements?
Nonequivalent control group posttest-only design
Which quasi-experimental design includes repeated measurements before and after an event?
Interrupted time-series design
Which quasi-experimental design is typically strongest?
Nonequivalent control group interrupted time-series design
What is the major remaining threat in interrupted time-series designs?
History
Why is the school start time study considered a quasi-experiment?
Start times occur naturally and schools are not randomly assigned
What can a quasi-experiment support?
Evidence consistent with causation but not proof
A comparison group helps control for what threats?
Maturation and history
Which design best supports causal claims overall?
True experiments
What are the three criteria for establishing causation?
Covariance, temporal precedence, and internal validity
What is covariance?
When two variables are related or change together
What is internal validity?
The extent to which an experiment supports a causal conclusion
What is attrition?
Participants dropping out of a study over time
What is maturation?
Changes in participants due to natural growth or development
What is a history threat?
An outside event affects participants during a study
What are order effects?
Changes in responses caused by the order of conditions
What is random assignment?
A process that gives every participant an equal chance of being placed in any condition
What is a posttest-only design?
A design with treatment conditions and measurement only after the treatment
What is a design confound?
An alternative explanation that varies systematically with the IV
What is a selection effect?
A preexisting difference between groups that may explain results
What is a true experiment?
A study with manipulation, random assignment, and control of confounds
What is a quasi-experiment?
A study with manipulation but without random assignment
What is a correlational study?
A study that measures variables without manipulating them
What is a main effect?
The independent effect of one IV on the DV
What is a crossover interaction?
An interaction where the direction of an effect reverses across levels of another IV
How do you calculate the number of cells in a factorial design?
Multiply the number of levels of all IVs together
What is a comparison group?
A group used as a benchmark to evaluate the effects of a treatment or event
Why are true experiments superior for causal inference?
They control confounds through random assignment and manipulation
Why can't quasi-experiments prove causation?
They lack random assignment, making alternative explanations possible