Chapter 13 Flashcards
(25 cards)
What is the definition of a quasi-experiment?
Select an IV and a DV and study participants who are exposed to each level of the IV
Not a true experiment as the researchers do not have full experimental control and can be used where random assignment is impossible or unethical.
What are the four types of quasi-experimental designs?
- Nonequivalent control group posttest-only design
- Nonequivalent control group pretest/posttest design
- Interrupted time-series design
- Nonequivalent control group interrupted time-series design
What is a Nonequivalent Control Group Posttest-Only Design?
Participants are not randomly assigned to groups and are tested only once after exposure to one level of the IV or the other
An example is studying the effect of default consent options for organ donation on the rate of organ donation.
What is a Nonequivalent Control Group Pretest/Posttest Design?
Participants are not randomly assigned to groups and are tested both before and after some intervention
An example is comparing self-esteem, life satisfaction, and attractiveness before and after cosmetic surgery.
What is an Interrupted Time-Series Design?
Measures a variable repeatedly before, during, and after the interruption caused by some event
An example includes measuring suicide rates before, during, and after the release of the TV show ‘13 Reasons Why.’
What is a Nonequivalent Control Group Interrupted Time-Series Design?
Participants are not randomly assigned to groups and measures a variable repeatedly before, during, and after an interruption
It is one of the strongest quasi-experimental designs.
What are the eight threats to internal validity in quasi-experimental designs?
- Selection effects
- Design confounds
- Maturation threat
- History threat
- Regression to the mean
- Attrition threat
- Test and instrument threats
- Observer bias, demand characteristics, and placebo effects
What is a selection effect?
Applied when the kinds of participants at one level of the IV are systematically different from those at the other level
It is relevant for nonequivalent control group posttest-only and pretest/posttest designs.
What is a design confound?
An outside variable that accidentally and systematically varies with the level of the targeted IV
Example: differences in public awareness between opt-in and opt-out organ donation policies.
What is a maturation threat?
Occurs when an observed change could have emerged more or less spontaneously over time
Typically occurs in pretest-posttest designs.
What is a history threat?
Occurs when an external, historical event happens for everyone in the study at the same time as the treatment
It can obscure whether the outcome is due to the treatment or the external event.
What is regression to the mean?
Occurs when an extreme outcome is caused by random factors that are unlikely to happen in the same combination again
It is only a threat for pretest/posttest designs when a group is selected because of its initially extreme scores.
What is an attrition threat?
Occurs when people drop out over time
It poses a threat when systematic kinds of people drop out.
What are test and instrumentation threats?
Can occur when participants are measured more than once
Testing threat is a type of order effect.
What is observer bias?
Occurs when experimenters’ expectations influence their interpretation of the results
It relates to human subjectivity.
What are demand characteristics?
When participants guess what the study is about and change their behavior in the expected direction
This can affect the validity of the results.
What is the placebo effect?
When participants improve only because they believe they are receiving an effective treatment
This phenomenon must be accounted for in experimental designs.
What are the advantages of quasi-experiments?
- Real-world opportunities
- Enhanced external validity
- Ethical options for studying certain questions
- Excellent construct validity for the quasi-IV
- Ability to evaluate statistical validity through effect size
What is a small-N design?
Obtain a lot of information from just a few cases
‘N’ refers to the number of participants in the study.
What are the three types of small-N designs?
- Stable-baseline design
- Multiple-baseline design
- Reversal design
What is a stable-baseline design?
A study in which behavior is observed for an extended baseline period before beginning a treatment
A stable baseline increases the internal validity of the study.
What is a multiple-baseline design?
Researchers stagger the introduction of an intervention across individuals, times, or situations to rule out alternative explanations
This design helps establish a stable baseline before treatment.
What is a reversal design?
Researchers observe a problem behavior both with and without treatment, removing the treatment to see if the behavior returns
This design tests for internal validity by observing changes as the treatment is reintroduced.
What are the four validities to evaluate in small-N designs?
- Internal validity
- External validity
- Construct validity
- Statistical validity
