On composite likelihood in bivariate meta-analysis of diagnostic test accuracy studies

TL;DR

This paper compares composite likelihood and maximum likelihood methods for bivariate meta-analysis of diagnostic test accuracy, highlighting the advantages of ML in terms of computational stability and flexibility in dependence modeling.

Contribution

It provides a thorough evaluation of CL and ML methods, demonstrating ML's superior computational stability and ability to model dependence in diagnostic test accuracy meta-analyses.

Findings

ML method shows no convergence issues and is computationally stable.

ML allows estimation of dependence between sensitivity and specificity.

Simulation and real data illustrate ML's advantages over CL.

Abstract

The composite likelihood (CL) is amongst the computational methods used for estimation of the generalized linear mixed model (GLMM) in the context of bivariate meta-analysis of diagnostic test accuracy studies. Its advantage is that the likelihood can be derived conveniently under the assumption of independence between the random effects, but there has not been a clear analysis of the merit or necessity of this method. For synthesis of diagnostic test accuracy studies, a copula mixed model has been proposed in the biostatistics literature. This general model includes the GLMM as a special case and can also allow for flexible dependence modelling, different from assuming simple linear correlation structures, normality and tail independence in the joint tails. A maximum likelihood (ML) method, which is based on evaluating the bi-dimensional integrals of the likelihood with quadrature methods has been proposed, and in fact it eases any computational difficulty that might be caused by the double integral in the likelihood function. Both methods are thoroughly examined with extensive simulations and illustrated with data of a published meta-analysis. It is shown that the ML method has no non-convergence issues or computational difficulties and at the same time allows estimation of the dependence between study-specific sensitivity and specificity and thus prediction via summary receiver operating curves.