Conditionally specified continuous distributions

A distribution is conditionally specified when its model constraints are expressed conditionally. For example, Besag's (1974) spatial model was specified conditioned on the neighbouring states, and pseudolikelihood is intended to approximate the likelihood using conditional likelihoods. There are three issues of interest: existence, uniqueness and computation of a joint distribution. In the literature, most results and proofs are for discrete probabilities; here we exclusively study distributions with continuous state space. We examine all three issues using the dependence functions derived from decomposition of the conditional densities. We show that certain dependence functions of the joint density are shared with its conditional densities. Therefore, two conditional densities involving the same set of variables are compatible if their overlapping dependence functions are identical. We prove that the joint density is unique when the set of dependence functions is both compatible and complete. In addition, a joint density, apart from a constant, can be computed from the dependence functions in closed form. Since all of the results are expressed in terms of dependence functions, we consider our approach to be dependence-based, whereas methods in the literature are generally density-based. Applications of the dependence-based formulation are discussed. Copyright 2008, Oxford University Press.

[1]  B. Arnold,et al.  Conditionally Specified Distributions: An Introduction (with comments and a rejoinder by the authors) , 2001 .

[2]  T. Speed,et al.  Characterizing a joint probability distribution by conditionals , 1993 .

[3]  H. Joe.  Multivariate models and dependence concepts , 1998 .

[4]  J. Besag.  Spatial Interaction and the Statistical Analysis of Lattice Systems , 1974 .

[5]  Noel A Cressie,et al.  The Construction of Multivariate Distributions from Markov Random Fields , 2000 .

[6]  George Casella,et al.  Functional Compatibility, Markov Chains and Gibbs Sampling with Improper Posteriors , 1998 .

[7]  B. Arnold,et al.  Compatible Conditional Distributions , 1989 .

[8]  D. Cox,et al.  A note on pseudolikelihood constructed from marginal densities , 2004 .

[9]  J. F. C. Kingman,et al.  Information and Exponential Families in Statistical Theory , 1980 .

[10]  Enrique Castillo,et al.  Conditionally specified distributions: An introduction - Comments and rejoinders , 2001 .

[11]  Yuchung J. Wang.  Multivariate normal integrals and contingency tables with ordered categories , 1997 .

[12]  P. Holland,et al.  Regional dependence for continuous bivariate densities , 1987 .

[13]  Michel Mouchart,et al.  Discussion on "Conditional independence in statistitical theory" by A.P. Dawid , 1979 .

[14]  G. Grimmett.  A THEOREM ABOUT RANDOM FIELDS , 1973 .

[15]  M. C. Jones.  The local dependence function , 1996 .

[16]  Nanny Wermuth,et al.  A general condition for avoiding effect reversal after marginalization , 2003 .

[17]  H. Y. Chen.  Nonparametric and Semiparametric Models for Missing Covariates in Parametric Regression , 2004 .

[18]  M. C. Jones.  Marginal Replacement in Multivariate Densities, with Application to Skewing Spherically Symmetric Distributions , 2002 .

[19]  B. C. Arnold,et al.  Bivariate Distributions with Conditionals in Prescribed Exponential Families , 1991 .

[20]  Julian Besag,et al.  Discussion: Markov Chains for Exploring Posterior Distributions , 1994 .

[21]  G. Molenberghs,et al.  Pseudolikelihood Modeling of Multivariate Outcomes in Developmental Toxicology , 1999 .

[22]  N. L. Johnson,et al.  Continuous Multivariate Distributions, Volume 1: Models and Applications , 2019 .