A0279
Title: Estimation and inference for three-dimensional panel data models
Authors: Bin Peng - Monash University (Australia) [presenting]
Abstract: Estimation and inferential methods are developed for three-dimensional (3D) panel data models with homogeneous/heterogeneous coefficients. The 3D panel data models specify the nature of common shocks through the use of a hierarchical factor structure (i.e., global factors and sector factors). Accordingly, an approach to estimating the hierarchy is developed, thus enabling a better understanding of the relative importance of the two types of unobservable shocks. Second, bias-corrected estimators are proposed, and bootstrap procedures are given to construct the confidence intervals for the parameters of interest while allowing for correlation along three dimensions of idiosyncratic errors. The theoretical findings are justified using extensive simulations. In an empirical study, the twin hypotheses of conditional and unconditional convergence are examined for manufacturing industries across countries.
