Sample size determination for equivalence test using rate ratio of sensitivity and specificity in paired sample data

Before implementing a new diagnostic test, we may wish to study whether thi s test is noninferior to a reference test with respect to the sensitivity a nd/or the specificity. This paper discusses sample size determination for o ne-sided equivalence (or noninferiority) testing of the rate ratio using pa ired-sample data. Using large sample theory, this paper derives asymptotic sample size formulae for the required number of subjects giving a desired p ower 100(1 - beta)% at a specified a-level. To evaluate the accuracy of the se formulae, this paper considers several test statistics and uses Monte Ca rlo simulation to estimate the corresponding type I error and power with th e given resulting sample sizes in a variety of situations. Finally, this pa per notes those situations for which the asymptotic sample size formulae de veloped here are of limited use and suggests a simple empirical adjustment to alleviate this limitation. (C) Elsevier Science Inc. 2001.