Bayesian estimation and model selection of threshold spatial Durbin model

• Published in: Economics letters Vol. 188; p. 108956
• Main Authors: Zhu, Yanli, Han, Xiaoyi, Chen, Ying
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 01.03.2020; Elsevier Science Ltd
• Subjects: Bayes factor; Bayesian analysis; Bayesian estimation; Density; Endogenous; Estimating techniques; Markov analysis; Monte Carlo simulation; Savage–Dickey density ratio; Simulation; Spatial analysis; Threshold spatial Durbin model; C5; C11; Bayesian estimation; Savage–Dickey density ratio; Bayes factor; Threshold spatial Durbin model; C2
• ISSN: 0165-1765; 1873-7374
• DOI: 10.1016/j.econlet.2020.108956

We consider a threshold spatial Durbin model that allows for threshold effects in both endogenous and exogenous spatial interactions among cross-sectional units. We develop a computationally tractable Markov Chain Monte Carlo (MCMC) algorithm to estimate the model. We also propose a nested model selection procedure to test for spatial threshold effects, based upon the Bayes factor computed from the Savage–Dickey Density Ratio in Verdinelli and Wasserman (1995). Simulation studies suggest that the Bayesian estimator is more precise than the spatial 2SLS (S2SLS) estimator in Deng (2018). The model selection procedure works well when the sample size increases and the difference between spatial parameters enlarges. •We consider a threshold spatial Durbin model that allows for threshold effects in both endogenous and exogenous spatial interactions.•We develop a computationally tractable Markov Chain Monte Carlo algorithm to estimate the model.•We propose a nested model selection procedure to test for spatial threshold effects, based upon the Bayes factor.•We also discuss alternative tests for spatial threshold effect.