Chapter 11 - Single Case, Quasi-Experimental, and Developmental Research
Learning Objectives (pg200)
Describe single case experimental designs and discuss reasons to use this design
Describe the five types of evaluations involved in program evaluation research: needs assessment, program assessment, process evaluation,
outcome evaluation, and efficiency assessment
Describe the one-group post test-only design
Describe the one-group pretest-post test design and the associated threats to internal validity that may occur: history, maturation, testing,
instrument decay, and regression toward the mean.
Describe the non-equivalent control group design and non-equivalent control group pretest-post test design, and discuss the advantages of
having a control group.
Distinguish between the interrupted time series design and the control series design
Describe cross-sectional, longitudinal, and sequential research designs, including the advantages and disadvantages of each design
Define “cohort effect”
Single-Case Experimental Designs
Traditionally know as single-subject; now single-case and single participant designs
Research from these studies often used in applied settings (clinical, educational)
Participant’s behaviour is measured over a baseline period, and then during a treatment period to ensure the manipulated variable is what is
actually having the effect.
o However, there is no guarantee; there can be other explanations for why the change is occurring.
Reversal designs: A (baseline period)à B (treatment) à A (baseline)
o Called an ABA design- again measure behaviour after the treatment has been removed (also called withdrawal designs)
o Data should show that behaviour is reversed during the second baseline period if the manipulation is what was causing the changes in
o Single reversal may not be powerful enough evidence, so ABABAB designs are also used, ensuring the withdrawal does cause a
o Text gives examples of reward systems- rewarded during treatment with tokens for using public transit, removal of tokens causes
transit levels to return to baseline levels.
Multiple Baseline Designs: the effectiveness of treatment is demonstrated when a behaviour change sonly after the manipulation is introduced
o There are certain situations where removal/reversals would be dangerous and unethical (removing barriers to dangerous or illegal
behaviour, for example).
o These changes must be observed under multiple circumstances to rule out the possibility that other events were responsible
o Across subjects- manipulation is given to each member at a different point in time in the study- doing this, it is easier to rule out
changes based on chance or other events.
o Across behaviours (again, reward example is given)
o Across situations- the same behaviour is measured in different settings.
Replications in single-case designs
o Individual data is important; don’t always want to group all of the results together
o Complex statistical analysis is not required for single case designs
Research on programs that are proposed and implemented to achieve some positive effect on a group of individuals (ie- DARE)
Phases of program evaluation research- reference Fig 11.3 on pg 206
o Needs assessment- are there problems in the target population?
Once the need is established, programs can be planned