Within-subjects designs


Table 13-3 (p. 402) can be used to argue that the within-subjects design is a more extreme form of the matched pairs design. That is, within-subjects comparisons are the ultimate form of matching. As an extreme form of the matched pairs design, the within-subjects design has many of the same strengths (power) and weaknesses (results may only generalize to individuals who would get multiple treatments, construct validity may be jeopardized by sensitizing the participant to what the study is about).

Table 13-4 (p. 403) shows that the within-subjects design is also threatened by something that does not affect matched pairs designs: order effects. Specifically, practice, fatigue, carry-over, and sensitization effects can affect the results of a within-subjects experiment.

To give students a clearer picture of the problem with order effects--and to suggest ways of dealing with order effects, go over Table 13-5 (p. 406). Show how order effects could affect the results of a a within-subjects design (such as the one discussed in the text and referred to in Table 13-4). Finally, talk about randomization and counterbalancing combined with randomization as ways of dealing with order effects


Back to Chapter 13 Main Menu