Event Details

This Seminar is hosted by the Economics Department

Yongcheol Shin will present a seminar on

Title “Estimation and Inference in Heterogeneous Spatial Panel Data Models with a Multifactor Error Structure”

Abstract In this paper, we develop a unifying econometric framework for the analysis of heterogeneous panel data models that can account for both spatial dependence and common factors. To tackle the challenging issues of endogeneity caused by both the spatial lagged term and the correlation between regressors and factors, we propose to approximate common factors by cross-section averages of independent variables only, and deal with the spatial endogeneity via the instrumental variables. We develop the individual estimators as well as the Mean Group and the Pooled estimators, and establish their consistency and asymptotic normal distributions. Monte Carlo simulations confirm that the finite sample performance of our proposed estimators is quite satisfactory. We demonstrate the usefulness of our approach with an application to a gravity model of bilateral trade flows for 190 pairs of 14 European Union (EU) and 6OECD countries, and find that the trade flows between the U.K. and EU members would fall substantially following a hard Brexit.