Testing equality of means of correlated variates with missing observations on both responses

Abstract

SUMMARY A statistic is proposed for testing the hypothesis of equality of the means of a bivariate normal distribution when observations are missing on both variates. The distribution of the statistic is approximated by a Student's t distribution under the null hypothesis. The expected squared lengths of the confidence intervals for the mean difference are used to measure the increased precision of our statistic relative to the conventional paired t test.