Identifying Latent Groups in Spatial Panel Data Using a Markov Random Field Constrained Product Partition Model

DOI10.5705/SS.202021.0247MaRDI QIDQ6069477zbMATH OpenWikidataFDO

Authors Tianyu Pan, Guanyu Hu, Weining Shen

Publication date 14 November 2023

Published in STATISTICA SINICA (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2012.10541

zbMATH Keywords

marginal likelihoodnonparametric Bayesian methodposterior consistencyspatial homogeneity

Mathematics Subject Classification ID

Statistics (62-XX)

Abstract: Understanding the heterogeneity over spatial locations is an important problem that has been widely studied in many applications such as economics and environmental science. In this paper, we focus on regression models for spatial panel data analysis, where repeated measurements are collected over time at various spatial locations. We propose a novel class of nonparametric priors that combines Markov random field (MRF) with the product partition model (PPM), and show that the resulting prior, called by MRF-PPM, is capable of identifying the latent group structure among the spatial locations while efficiently utilizing the spatial dependence information. We derive a closed-form conditional distribution for the proposed prior and introduce a new way to compute the marginal likelihood that renders efficient Bayesian inference. We further study the theoretical properties of the proposed MRF-PPM prior and show a clustering consistency result for the posterior distribution. We demonstrate the excellent empirical performance of our method via extensive simulation studies and applications to a US precipitation data and a California median household income data study.

Cites work

• A Panel Analysis of Liquidity Constraints and Firm Investment
• Analysis of panel data
• Bayesian Clustering and Product Partition Models
• Bayesian generalized product partition model
• Bayesian space-time partitioning by sampling and pruning spanning trees
• Bayesian spatial homogeneity pursuit for survival data with an application to the SEER respiratory cancer data
• Estimation of panel data models with parameter heterogeneity when group membership is unknown
• Grouped patterns of heterogeneity in panel data
• scientific article; zbMATH DE number 3731304 (Why is no real title available?)
• scientific article; zbMATH DE number 509150 (Why is no real title available?)
• scientific article; zbMATH DE number 5245019 (Why is no real title available?)
• Identifying latent structures in panel data
• Marginal Likelihood and Bayes Factors for Dirichlet Process Mixture Models
• Markov random fields for vision and image processing
• Mixture models with a prior on the number of components
• Modelling heterogeneity with and without the Dirichlet process
• Nonparametric Bayesian image segmentation
• Panel threshold regressions with latent group structures
• Predictions based on the clustering of heterogeneous functions via shape and subject-specific covariates
• Probability
• Spatial Econometrics
• Spatial product partition models
• Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images
• Testing homogeneity in panel data models with interactive fixed effects
• Time series and panel data econometrics

Cited in

(1)

• Identifying local differences with fused-MCP: an apartment rental market case study on geographical segmentation detection

This page was built for publication: Identifying Latent Groups in Spatial Panel Data Using a Markov Random Field Constrained Product Partition Model

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6069477)