A SEMIPARAMETRIC PANEL DATA MODEL WITH SPATIAL-VARYING TEMPORAL EFFECTS
To relax the additive assumption on individual effect and temporal effect of traditional two-way panel data models, this paper proposes a novel semiparametric spatial panel data model, in which the temporal effects are individual heterogeneity and specified as nonparametric functions of spatial locations. Based on the fact that the proposed model is a mixed geographically weighted regression model, we apply the profile least-squares estimate approach to estimate the regression coefficients and temporal effect functions. Some simulations are conducted to examine the performance of our proposed method and the results are satisfactory.
spatial panel data, geographically weighted regression, profile least-squares estimation, temporal effects.
Received: October 4, 2023; Accepted: November 6, 2023; Published: December 6, 2023
How to cite this article: Yu Zhao, Jiahui Wang and Chuanhua Wei, A semiparametric panel data model with spatial-varying temporal effects, Far East Journal of Theoretical Statistics 68(1) (2024), 41-51. http://dx.doi.org/10.17654/0972086324003
This Open Access Article is Licensed under Creative Commons Attribution 4.0 International License
References:[1] C. R. Ai and Y. Q. Zhang, Estimation of partially specified spatial panel data models with fixed-effects, Econometric Rev. 36 (2017), 6-22.[2] L. Anselin, J. Le Gallo and H. Jayet, Spatial panel econometrics, The Econometrics of Panel Data, Fundamentals and Recent Developments in Theory and Practice, L. Matyas and P. Sevestre, eds., 3rd ed., Berlin, Springer-Verlag, 2008, pp. 627-662.[3] Y. Bai, J. H. Hu and J. H. You, Panel data partially linear varying-coefficient model with both spatially and time-wise correlated errors, Statist. Sinica 35 (2015), 275-294.[4] C. Brunsdon, A. S. Fotheringham and M. Charlton, Geographically weighted regression: a method for exploring spatial nonstationarity, Geographical Analysis 28 (1996), 281-298.[5] J. P. Elhorst, Specification and estimation of spatial panel data models, International Regional Science Review 26 (2003), 223-243.[6] J. P. Elhorst, Spatial Econometrics: From Cross-sectional Data to Spatial Panels, Springer, 2014.[7] A. S. Fotheringham, C. Brunsdon and M. Charlton, Geographically Weighted Regression the Analysis of Spatial Varying Relationships, Wiley, West Sussex, 2002.[8] J. H. Hu, F. X. Liu and J. H. You, Panel data partially linear model with fixed effects spatial autoregressive error components and unspecified inter temporal correlation, J. Multivariate Anal. 130 (2014), 64-89.[9] J. A. Rice and B. W. Silverman, Estimating the mean and covariance structure nonparametrically when the data are curves, Journal of the Royal Statistical Society, Series B 53 (1991), 233-243.[10] C. H. Wei and F. Qi, On the estimation and testing of mixed geographically weighted regression models, Economic Modelling 29(6) (2012), 2615-2620.[11] Y. Q. Zhang and D. M. Shen, Estimation of semi-parametric varying-coefficient spatial panel data models with random-effects, J. Statist. Plann. Inference 159 (2015), 64-80.[12] Y. Q. Zhang and Y. Q. Sun, Estimation of partially specified dynamic spatial panel data models with fixed-effects, Regional Science and Urban Economics 51 (2015), 37-46.
