PUBH 6501 QUIZ #4

What is the Solomon Four-Group Design?

A randomized design with four groups that tests treatment effects and whether pretesting affects outcomes.

What are the four groups in the Solomon Four-Group Design?

Treatment with pretest, control with pretest, treatment without pretest, and control without pretest.

What is the main advantage of the Solomon Four-Group Design?

It evaluates intervention effects while assessing whether pretesting influenced results.

What is a Switching Replications Design?

An experimental design in which groups receive the intervention at different times.

What is a major advantage of Switching Replications?

Both groups can eventually receive the intervention.

How can Switching Replications strengthen internal validity?

Researchers can observe whether treatment effects are replicated when the second group receives the intervention.

What is the defining feature of a quasi-experimental design?

It does not use random assignment to treatment and control groups.

Why are quasi-experimental groups not necessarily equivalent?

Without random assignment, preexisting differences may exist between groups.

What are the three quasi-experimental designs covered in the lecture?

Non-equivalent control group, one-group pretest-posttest, and interrupted time-series.

What is a non-equivalent control group design?

A design with intervention and comparison groups that are not randomly assigned.

What is the notation for a non-equivalent control group design?

N O X O / N O O.

What does N represent in quasi-experimental notation?

Non-random assignment.

Why is baseline equivalence especially important in non-equivalent control group designs?

Groups may differ before the intervention, creating alternative explanations for outcomes.

What can lead to non-equivalent groups?

Self-selection, non-random assignment, and use of existing groups.

What is the goal when choosing a quasi-experimental comparison group?

To replicate the intervention group as closely as possible except for randomization and treatment.

How do quasi-experiments generally affect internal validity?

Internal validity is generally weaker than in randomized experiments.

What is matching?

Constructing comparable groups based on measured characteristics.

What is the purpose of matching?

To find comparison subjects similar to treatment subjects and estimate the counterfactual.

What is a major weakness of matching?

It can only account for measured variables, leaving possible unmeasured confounders.

Why is individual matching difficult?

Finding suitable matches becomes harder as the number of matching variables increases.

What is the key question when establishing a comparison group?

Does the group adequately control for predictors of the outcome or impact?

What is a one-group pretest-posttest design?

One group is measured before and after an intervention without a control group.

What is the notation for a one-group pretest-posttest design?

O1 X O2.

What are the main internal validity threats to one-group pretest-posttest designs?

History, maturation, reactive measures, statistical regression, and mortality/dropout.

What is an interrupted time-series design?

A design using multiple observations before and after an intervention or event.

What is the notation for an interrupted time-series design?

N O1 O2 O3 X O4 O5 O6.

How many groups can an interrupted time-series design include?

One or two groups.

What types of events can interrupted time-series designs evaluate?

Interventions, policy shifts, or uncontrolled events.

What is a major internal validity threat to interrupted time-series designs?

Local history and confounding, particularly in single-group designs.

How can an interrupted time-series indicate an intervention effect?

A shift in the outcome level or a change in its rate of increase or decrease after intervention.