Use of PROC MIXED in the analysis of repeated measures data from a clinical trial in obsessive compulsive disorder

The subject of this paper is the analysis of data from a randomized, parallel group, multicenter clinical trial in patients with Obsessive Compulsive Disorder (OCD). The purpose of the study was to evaluate the efficacy and safety of three dose levels of Paxil(TM)* (paroxetine HCl) versus placebo. The level of the patients' illness was measured using the Yale Brown Obsessive Compulsive Scale (YBOCS) at baseline and at weeks 1, 2, 3, 4, 6, 8, 10, and 12. The data set included data points which were missing due to skipped visits and patient dropouts. PROC MIXED of the SAS System was used in two alternative approaches to the analysis of the data from this study. The first is a repeated measures analysis. Secondly, PROC MIXED was used in a random coefficient regression analysis. In this analysis the hypothesis of interest was the differences in slopes (rates of improvement) for the doses of Paxil and placebo.