Refinements in maximum likelihood inference on spatial autocorrelation in panel data
针对固定效应面板数据模型中的空间自相关，利用Edgeworth展开改进了最大似然估计的区间估计和检验方法，蒙特卡洛模拟显示其有限样本性能优于传统渐近理论。
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.