EFFECTS OF DEPENDENT ERRORS IN THE ASSESSMENT OF DIAGNOSTIC-TEST PERFORMANCE

Latent class models can be used to assess diagnostic test performance when there is no perfectly accurate gold standard test available for c omparison. These models usually assume independent errors between the tests, conditional on the true disease state of the subject. Maximum l ikelihood estimates of the prevalence of the disease and the error rat es of diagnostic tests are then obtained. This paper examines the impa ct of error dependencies between binary diagnostic tests on the parame ter estimates obtained from the latent class models. The independence model often gives parameter estimates having relatively small bias, bu t in some situations (for example, when disease prevalence is low and the tests have low specificity, such as in population screening) the b ias may be more serious. (C) 1997 by John Wiley & Sons, Ltd.