Recognition and variable selection in sparse spatial panel data models with fixed effects

Abstract

This paper is concerned with sparse spatial panel data models under fixed effects and increasing dimensions of covariates. We develop a nonconcave selection approach for spatial effects recognition and covariates selection of the models. Theoretical results show that the proposed method has the oracle property in the sense that the estimators have consistency, sparsity and asymptotic normality under suitable conditions. Furthermore, we present an coordinate descent algorithm to deal with the nonlinearity that arises in the optimization procedure. Numerical experiments show that the recognition and selection procedure can be used to select important covariates, identify spatial effects and estimate unknown parameters simultaneously. At the same time, the benefits of the proposed method is assessed by comparing different analyses of real spatial penal data.