Desktop version

Home arrow Economics

  • Increase font
  • Decrease font

<<   CONTENTS   >>

Case Study Analysis: Five Trials in Schizophrenia

The schizophrenia dataset combines the data that were collected in five double-blind randomized clinical trials (for details, see Section 2.2.2). In each of these trials, the efficacy of the experimental treatment risperidone was compared to an active control. Schizophrenic symptomatology was assessed using the Brief Psychiatric Rating Scale (BPRS), the Positive and Negative Syndrome Scale (PANSS), and the Clinical Global Impression (CGI). The main endpoints of interest were the change in the BPRS (= BPRS posttreatment score — BPRS baseline score), PANSS, and CGI scores. These endpoints can be analyzed as (semi)continuous normally distributed variables, but they are also often dichotomized to reflect clinically relevant change. In the latter case, the BPRS/PANSS scores are dichotomized as 1 = 20% reduction in posttreatment scores relative to baseline scores and 0 = otherwise, and CGI is dichotomized as 1 = a change of more than 3 points on the original CGI scale and 0 = otherwise. The results of the case study are discussed without reference to the software tools that can be used to conduct the analyses. Sections

13.4 and 13.5 provide details on how the analyses in the binary-binary and continuous-binary settings can be conducted in R, respectively.

<<   CONTENTS   >>

Related topics