Categorizing Skewed, Limited Dependent Variables

Publisher Website
Google Scholar
Abstract
Probit analysis is applied in a situation where analysis of covariance (ANCOVA) would customarily be used. The dichotomous dependent variables arise from dichotomizations of skewed continuous variables recorded as the proportion of time certain activities are observed. The probit approach avoids the biases of ordinary A NCO VA that arise due to skewness (limited variation). To illustrate this, data from 225 experiments and 214 control subjects in a drug treatment program was analyzed. It was found that the probit approach was able to reveal more substantial treatment effects than the ordinary A NCO VA.

This publication has 5 references indexed in Scilit: