Bayesian Semiparametric Regression Analysis of Multicategorical Time-Space Data

摘要: We present a unified semiparametric Bayesian approach based on Markov random field priors for analyzing the dependence of multicategorical response variables time, space and further covariates. The general model extends dynamic, or state space, models categorical time series longitudinal data by including spatial effects as well nonlinear metrical covariates in flexible form. Trend seasonal components, different types are all treated within same framework assigning appropriate with forms degrees smoothness. Inference is fully uses MCMC techniques posterior analysis. this paper latent utility particularly useful probit models. methods illustrated applications to unemployment forest damage survey.