文章基本信息

标题：Improved Lagrange Multiplier Tests in Spatial Autoregressions
本地全文：下载
作者：Peter M Robinson ; Francesca Rossi
期刊名称：Japanese Studies Programme Papers
出版年度：2013
出版社：Suntory Toyota International Centres for Economics and Related Disciplines
摘要：For testing lack of correlation against spatial autoregressive alterna- tives, Lagrange multiplier tests enjoy their usual computational advantages, but the (2) rst-order asymptotic approximation to critical values can be poor in small sam- ples. We develop rened tests for lack of spatial error correlation in regressions, based on Edgeworth expansion. In Monte Carlo simulations these tests, and bootstrap ones, generally signicantly outperform 2􀀀 based tests.
关键词：Spatial autocorrelation; Lagrange multiplier test; Edgeworth expansion;bootstrap; nite-sample corrections.