A Weighted Generalized Score Statistic for Comparison of Predictive Values of Diagnostic Tests

• Activity Number: 359
• Type: Contributed
• Date/Time: Tuesday, August 6, 2013 : 10:30 AM to 12:20 PM
• Sponsor: Section on Statistics in Epidemiology
• Author(s): Andrzej Kosinski*+
• Companies: Duke University
• Keywords: correlated data ; diagnostic test ; paired design ; positive and negative predictive values ; score statistic

Abstract

We consider testing equality of two positive or two negative predictive values within a paired design in which all patients receive two diagnostic tests. The existing statistical tests include multinomial distribution based Wald tests and a generalized score (GS) test within the generalized estimating equations (GEE) framework. As is seen with a new intuitive re-formulation we present, the GS statistic does not always reduce to the commonly used score statistic in the independent samples case. To alleviate this, we introduce a weighted generalized score (WGS) test statistic that incorporates empirical covariance matrix with the newly proposed weights. This statistic is simple to compute and preserves type I error better than the GS or Wald statistics as demonstrated by simulations (Kosinski AS. "A weighted generalized score statistic for comparison of predictive values of diagnostic tests". Statistics in Medicine, 2013). We believe that the proposed WGS statistic is the preferred statistic for testing equality of two predictive values.