Multivariate distributions of correlated binary variables generated by pair-copulas

Abstract Correlated binary data are prevalent in a wide range of scientific disciplines, including healthcare and medicine. The generalized estimating equations (GEEs) the multivariate probit (MP) model two popular methods for analyzing such data. However, both have some significant drawbacks. GEEs may not an underlying likelihood MP fail to generate distribution with specified marginals bivariate correlations. In this paper, we study distributions that based on D-vine pair-copula models as superior alternative these methods. We elucidate construction three dimensions numerical examples. For higher dimensions, provide method constructing multidimensional equicorrelated correlation matrix. present real-life analysis illustrate application our results.