Physical Sciences and Mathematics Commons^™

Hotelling's T2 Approximation For Bivariate Dichotomous Data, Pradeep Singh, Imad Khamis, James Higgins

Conference on Applied Statistics in Agriculture

The comparison of the means of two treatments or populations when more than one variable is measured may be done using Hotelling's T² statistic. In many real world situations the data obtained are dichotomous, and the assumption of multivariate normality upon which Hotelling's T² is based is no longer valid. In this paper, an approximate Hotelling T² test is proposed for bivariate dichotomous data and empirically evaluated in terms of Type I error rate. It is shown that the approximation does a good job of controlling the Type I error rate for a range of bivariate parameters …