中文摘要：

虚假回归是非平稳时间序列分析中的重要问题，但目前对面板虚假回归特别是对纵剖面序列相关下的虚假回归研究较少。而运用贝弗里奇．纳尔逊分解考察虚假回归的LSDV估计量性质的文献还没有。本文在假定时间序列一般相关的前提下利用面板贝弗里奇-纳尔逊分解考察面板LSDV估计量的虚假回归性质，研究表明面板虚假回归的LSDV估计量对其真值是一致的，并且是渐近正态分布的，但其t值是发散的。在给出统计量的渐近分布之后我们利用Mento Carlo模拟给出了不同样本条件和不同相关系数下LSDV估计量的小样本性质。

英文摘要：

Spurious Begression is an important question in analysis of nonstationary time series. But not much attention has been paid to the Spurious Begression in Panel Data. However, there are have not literatures based on Beveridge - Nelson decomposition. This paper study the asymptotic properties of the LSDV estimator on the assumption that the time series is general correlation. We show that the LSDV estimator is consistent for its true value, but the t statistic diverges. We also study the finite sample properties of the estimator using monte carlo experiments.