科学研究

科学研究

论文发表
当前位置是: 首页 -> 科学研究 -> 论文发表 -> 正文

Improvement in Finite-Sample Properties of GMM-Based Wald Tests

id:2162 时间:20131014 status:published 点击数:
杂志Computational Statistics   
作者Qihui Chen, Yu Ren
正文GMM-based Wald tests tend to overreject when used for small samples, mainly due to inaccurate estimation of the weighting matrix. This article proposes applying the shrinkage method to address this problem. Using a possibly-misspecied factor model, the shrinkage method can provide a good estimator for the weighting matrix, and hence improve the nite-sample performance of the GMM-based Wald tests.
JEL-Codes:
关键词:Generalized method of moments, Wald tests, Finite-sample properties, Covariance matrix, Shrinkage method
TOP