Univariate Methods

Abstract

The simplest approach to the analysis of repeated measurements is to reduce the vector of multiple measurements from each experimental unit to a single measurement. Thus, a multivariate response is reduced to a univariate response. This avoids the issue of correlation among the repeated measurements from a subject. In the special case of two measurements per subject, well-known methods of this type include the paired t test for continuous responses and McNemar’s test for dichotomous responses.