空间经济计量模型检验中Bootstrap方法有效性研究

项目名称： 空间经济计量模型检验中Bootstrap方法有效性研究

项目编号： No.70871041

项目类型： 面上项目

立项/批准年度： 2009

项目学科： 金属学与金属工艺

项目作者： 龙志和

作者单位： 华南理工大学

项目金额： 24万元

中文摘要： 在有限样本和模型误差不服从正态独立同分布条件下，空间相关性检验是目前国际学术界有待解决的难题。本项目将Bootstrap方法应用于空间相关性检验的Moran's I统计量的构建，进而通过数理推导和Monte Carlo模拟实验，研究Bootstrap方法用于线性回归模型的OLS估计残差和空间滞后模型的2SLS或GMM估计残差所构建的Moran's I统计量的有效性。主要研究结论如下：1、线性回归模型Bootstrap Moran检验能够有效地检验OLS估计残差间的空间相关性；2、提出空间滞后模型中空间相关性检验的Moran's I统计量，即OLL-Moran检验，并推导出OLL-Moran检验的渐近分布和精确分布；3、空间滞后模型Bootstrap Moran检验能够有效地检验空间滞后模型2SLS估计残差间的空间相关性。该项目为解决有限样本和模型误差不服从正态独立同分布时空间经济计量模型检验问题提供理论基础，同时项目组在Gauss软件中编写的一系列Bootstrap Moran检验程序大大丰富了Gauss软件工具箱，为空间经济计量研究者提供了便利的研究手段。

中文关键词： Bootstrap；Moran's I；空间相关性；渐近改进；Monte Carlo模拟实验

英文摘要： Moran's I test for spatial dependence is a difficult question in the international academia under the conditions of finite sample or the non-normal i.i.d errors. Bootstrap methods are applied to construct Moran's I test statistic for spatial dependence, and then we research the efficiency of Bootstrap Moran's I statistic based on OLS residuals of the linear regression model and 2SLS or GMM residuals of the spatial autoregressive model, applying mathematical derivation and Monte Carlo simulation experiments. The main conclusions of this dissertation are as follows: 1.Spatial dependence for the OLS residuals can be effectively checked up by the bootstrap Moran test in the linear regression model; 2. We establish Moran's I statistic based the 2SLS or GMM residuals, obtain the OLL-Moran test, and prove its asymptotic and exact distribution in theory; 3. Spatial dependence for the 2SLS residuals can be effectively checked up by the bootstrap Moran test in the spatial autoregressive model. In the project, we have provided the theoretical basis for how to solve the puzzle of the test for spatial econometric model using bootstrap method under the conditions of finite sample or the non-normal i.i.d errors. The series of programs about the bootstrap Moran test are designed and written in the Gauss software which the toolbox of Gauss software is greatly enriched, and then the convenient method is provided for the spatial econometric researchers.

英文关键词： Bootstrap; Moran's I; Spatial dependence; Asymptotic refinement; Monte Carlo simulation experiments