Bayesian Heterogeneity Pursuit Regression Models for Spatially Dependent Data
share
Most existing spatial clustering literatures discussed the cluster algorithm for spatial responses. In this paper, we consider a Bayesian clustered regression for spatially dependent data in order to detect clusters in the covariate effects. Our proposed method is based on the Dirichlet process which provides a probabilistic framework for simultaneous inference of the number of clusters and the clustering configurations. A Markov chain Monte Carlo sampling algorithm is used to sample from the posterior distribution of the proposed model. In addition, Bayesian model diagnostic techniques are developed to assess the fitness of our proposed model, and check the accuracy of clustering results. Extensive simulation studies are conducted to evaluate the empirical performance of the proposed models. For illustration, our methodology is applied to a housing cost dataset of Georgia.
READ FULL TEXT