Comparison of the Predictive Values of Multiple Binary Diagnostic Tests in the Presence of Ignorable Missing Data

Abstract

The comparison of the predictive values of binary diagnostic tests is an important topic in the study of statistical methods applied to medical diagnosis. In this article, we study a global hypothesis test to simultaneously compare the predictive values of multiple binary diagnostic tests in the presence of ignorable missing data. The global hypothesis test deduced is based on the chi-squared distribution. Simulation experiments were carried out to study the type I error probability and the power of global hypothesis test and of other alternative methods when comparing the predictive values of two and three binary diagnostic tests respectively.