Analyzing Spatial Panel Data of Cigarette Demand: A Bayesian Hierarchical Modeling Approach

10.6339/JDS.2008.06(4).428

Yan-Bing Zheng；Jun Zhu；Dong Li

Autoregressive model ； demand equation ； longitudinal data ； Markov chain Monte Carlo ； spatial econometrics ； spatial-temporal process

Journal of Data Science

6卷4期（2008 / 10 / 01）

467 - 489

英文

Analysis of spatial panel data is of great importance and interest in spatial econometrics. Here we consider cigarette demand in a spatial panel of 46 states of the US over a 30-year period. We construct a demand equation to examine the elasticity of per pack cigarette price and per capita disposable income. The existing spatial panel models account for both spatial autocorrelation and state-wise heterogeneity, but fail to account for temporal autocorrelation. Thus we propose new spatial panel models and adopt a fully Bayesian approach for model parameter inference and prediction of cigarette demand at future time points using MCMC. We conclude that the spatial panel model that accounts for state-wise heterogeneity, spatial dependence, and temporal dependence clearly outperforms the existing models. Analysis based on the new model suggests a negative cigarette price elasticity but a positive income elasticity.