Quasi-experimental designs

Question 1

What is an experiment?

Answer 1

• Participants are randomly assigned to more than one condition.
• Need a control group and random assignment.
• Medical discipline calls experiments RCTs.

Question 2

What are the two definitions of quasi-experiments?

Answer 2

• Quasi- experimental designs are those in which participants cannot be randomly assigned to conditions.
• A quasi-experiment exists whenever causal conclusion cannot be drawn because there is less than complete control over the variables in the study.

Question 3

What are the differences and similarities between experiments and quasi-experiments?

Answer 3

Similarities: both have independent variables.
Differences: There is no random assignment and the conditions are not equivalent for a quasi-experiment

Question 4

What are some important things to note about quasi-experiments?

Answer 4

• Try to manually create equal groups
• Eliminate other differences as well as explanations for observed effects.

Question 5

What are the threats to internal validity for quasi-experiments?

Answer 5

• History
• Maturation
• Selection bias
• Regression to the mean

Question 6

What are the advantages of quasi-experiments?

Answer 6

1. Increased external validity
2. Very useful for policy decisions/evaluation.

• Experiments are held under carefully controlled, artificial environments that may not
  generalise outside of these settings (i.e. in the real world)
• Quasi-experiments are held under naturally occurring conditions

Question 7

What two types of quasi experimental designs are we focusing on?

Answer 7

• Non-equivalent control group design
• Interrupted time series designs

Question 8

What is the purpose of non-equivalent control group designs?

Answer 8

• To evaluate the effectiveness of a treatment group by
  including a time series component along with a “control group”
  that’s not exposed to the intervention
• These are used when you cannot properly randomly assign.
• Sample size = 2
• The 2 groups differ, they’re not randomly assigned. Validity therefore compromised.
  Therefore important to try match the groups as closely as possible prior to the study. Also
  vulnerable to regression to the mean and maturation.
• Measure the two groups before and after the intervention
  o E (experiment group): O1 > T > O2
  o C (control group): O1 > > O2

Question 9

What is the interrupted time series design?

Answer 9

• Its purpose is to observe behaviour over time prior to and
  immediately after introducing an intervention
• Advantage: allows for the evaluation of trends
• Often used in media or policy evaluation
• Need a lot of data points to actually understand the effect of the intervention. Important to
  measure the DV before as well as after the treatment.
• O1 O2 O3 O4 >T> O5 O6 O7 O8