Generalised Test For C- Matched Samples

Abstract This paper proposes a generalized statistical method for the analysis of multiple responses or outcome data in case control studies including situations in which the observations are either continuous or frequency data. Test statistics are proposed for assessing the statistical significance of differences between case-control response scores. The proposed methods are illustrated with some sample data. When there are only three possible response options in which the proposed method and the StuartMaxwell test can be equally used to analyze the data the proposed test statistic is shown to be at least as powerful as the StuartMaxwell test statistic.