Experimental design and statistical decisions tutorial: Comments on longitudinal ideomotor apraxia recovery

Abstract

Basso, Burgio, Paulin, and Prandoni (2000) claimed evidence for recovery from ideomotor apraxia within the first year post-cerebrovascular accident. However, concerns about the excessive use of paired t tests and incongruous experimental designs challenge the reported findings. The ideomotor apraxia recovery data should be analysed with a completely within-subjects design one-way analysis of variance (ANOVA). Further, the locus of lesion by clinical examination time data should be analysed in a two-way mixed design ANOVA with repeated measures on the three levels of examination time. In addition, circularity assumptions (i.e., composition of the covariance matrices) should be addressed for the repeated measures in the recommended analyses. In a tutorial approach, using the proper experimental designs and statistics, the ideomotor apraxia data were reanalysed. The one-way results support the recovery improvements between the first and second examinations. However, conflict with the original findings was found in the two-way mixed design results. Thus, the overall conclusions should be amended, especially given that the Locus of Lesion - Clinical Examination Time interaction failed to reach significance.