Refinements in maximum likelihood inference on spatial autocorrelation in panel data

Robinson, Peter and Rossi, Francesca (2015) Refinements in maximum likelihood inference on spatial autocorrelation in panel data. Journal of Econometrics, 189 (2). pp. 447-456. ISSN 0304-4076

Preview

PDF - Published Version Available under License Creative Commons Attribution. Download (534Kb) | Preview

• LSE expert's profile

• Published item via DOI

Abstract

In a panel data model with fixed effects, possible cross-sectional dependence is investigated in a spatial autoregressive setting. An Edgeworth expansion is developed for the maximum likelihood estimate of the spatial correlation coefficient. The expansion is used to develop more accurate interval estimates for the coefficient, and tests for cross-sectional independence that have better size properties, than corresponding rules of statistical inference based on first order asymptotic theory. Comparisons of finite sample performance are carried out using Monte Carlo simulations.

Item Type:	Article
Official URL:	http://www.sciencedirect.com/science/journal/03044...
Additional Information:	© 2015 The Authors © CC BY 4.0
Library of Congress subject classification:	H Social Sciences > HB Economic Theory
Journal of Economic Literature Classification System:	C - Mathematical and Quantitative Methods > C1 - Econometric and Statistical Methods: General > C12 - Hypothesis Testing C - Mathematical and Quantitative Methods > C2 - Econometric Methods: Single Equation Models; Single Variables > C21 - Cross-Sectional Models; Spatial Models; Treatment Effect Models C - Mathematical and Quantitative Methods > C3 - Econometric Methods: Multiple; Simultaneous Equation Models; Multiple Variables; Endogenous Regressors > C31 - Cross-Sectional Models; Spatial Models; Treatment Effect Models
Sets:	Departments > Economics Collections > Economists Online
Funders:	Economic and Social Research Council
Projects:	ES/J007242/1
Date Deposited:	01 Apr 2015 09:23
URL:	http://eprints.lse.ac.uk/61432/

Actions (login required)

Record administration - authorised staff only