考虑截面相关条件下的异质性面板数据协整回归模型的估计

 面板数据的非平稳分析是近年来迅速发展的方向，其中考虑截面相关情形下面板数据的协整分析的发展备受关注。Bai &; Kao（2006）得出了截面相关条件下面板协整估计的因子模型，但该模型只考虑了被解释变量截面相关情形，未考虑解释变量的截面相关，且假定各截面间长期协方差矩阵相同。本文在Bai（2006）考虑截面相关条件下面板数据协整回归模型估计的基础上将其结论推广至被解释变量和解释变量均截面相关及截面长期协方差矩阵不相同即异质性时的情形，并试图通过Monte Carlo 模拟讨论其小样本性质。并且由于截面间长期协方差矩阵异质性的存在，本文还针对两变量的协整系统提出了系数检验的组间均值t统计量。

On the Estimation of Heterogeneous Panel Cointegration Model with Cross-sectional Dependence

The Nonstationary analysis in Panel data is developing very rapid recently , Especially the estimation of a panel cointegration model with cross-sectional dependence .Bai and Kao(2006) propose a continuous updated fully modified (CUP-FM) estimator. In this paper ,we consider the estimation of panel cointegration model based on Bai ,etal (2006)and developed it to the condition of cross sectional heterogeneity and correlated cross –sectional in independent variables. We also try to use Monte Carlo simulation to investigate the finite sample proprieties . And because of the cross sectional heterogeneity we also give the Panel Fmols Group Mean t- statistic in the case of two variables.