ON THE SAMPLE-SIZE FOR ONE-SIDED EQUIVALENCE OF SENSITIVITIES BASED UPON MCNEMARS TEST

In this paper we formalize the problem of testing the one-sided equiva lence in the sensitivities of two medical diagnostic tests under a mat ched-pair study design. We derive conditional and unconditional sample size formulae which are decreasing functions of the probability of be ing diagnosed by both tests. We calculate upper boundary and midpoint sample sizes. Results of a Monte Carlo simulation study that compares the proposed sample size formulae with that of Lachenbruch suggest tha t our midpoint conditional sample size is the best choice to obtain th e desired power for the type of equivalence studies discussed in the p aper.