oConstruction of multivariate models to cover various types of dependence structuresUse of stochastic representations, mixtures, and latent variables to construct parametric models with desirable dependence propertiesUse of the copula as a summary of the dependence in a multivariate distribution - independent of the univariate marginsFrechet classes with given marginal distributionsTime series models with given univariate marginsEmphasis on properties of multivariate models to decide their applicabilityEstimation method consisting of parameter estimates from likelihoods of marginal distributions of a multivariate model - together with the jackknife methods for standard error estimatesComparison of models in data analysis examples, including multivariate and longitudinal response data
This book on multivariate models, statistical inference, and data analysis contains deep coverage of multivariate non-normal distributions for modeling of binary, count, ordinal, and extreme value response data. It is virtually self-contained, and includes many exercises and unsolved problems.
Table of Contents
Introduction. Aspects of Interpretation. Technical Considerations. Statistical Analysis. Special Methods for Joint Responses. Some Examples. Strategical Aspects. More Specialized Topics. Appendices.
"Both mathematical and applied researchers in multivariate dependence concepts would benefit from reading this rigorous book, which is designed as graduate level textbook… Some notable features of the book include the construction of non-normal multivariate distributions, copulas Fréchet classes, unsolved problems, and exhaustive reference list, and a three-page description of notation and abbreviations… The book is a good collection of ideas and formulas… certainly valuable for researchers in dependency concepts since it deals with several unsolved problems."
-Ramalingam Shanmugam in Journal of Mathematical Psychology, Vol. 46 (2002)