Suntory and Toyota International Centres for Economics and Related Disciplines (STICERD) LSE RSS Contact Us YouTube Twitter

Abstract:

Econometrics Paper
Improved Tests for Spatial Correlation
Peter M Robinson and Francesca Rossi
May 2013
Paper No' EM/2013/565:
Full Paper (pdf)

JEL Classification: C12; C21


Tags: spatial autocorrelation; ordinary least squares; hypothesis testing; edgeworth expansion; bootstrap.

We consider testing the null hypothesis of no spatial autocorrelation against the alternative of first order spatial autoregression. A Wald test statistic has good first order asymptotic properties, but these may not be relevant in small or moderate-sized samples, especially as (depending on properties of the spatial weight matrix) the usual parametric rate of convergence may not be attained. We thus develop tests with more accurate size properties, by means of Edgeworth expansions and the bootstrap. The finite-sample performance of the tests is examined in Monte Carlo simulations.