• 论文 •

一类近似因子模型的GMM估计及其统计性质研究

• 出版日期:2016-03-15 发布日期:2016-03-21

A Study on GMM Estimation for a Class of Approximate Factor Models and Their Statistical Properties

Bai Zhonglin & Bai Qiang

• Online:2016-03-15 Published:2016-03-21

Abstract:

The paper firstly presents the Generalized Method of Moments for estimation of the common factors vector and the factor loadings matrix for a class of approximate factor models with the idiosyncratic error term being cross-sectionally correlated. This method generalizes the maximum likelihood estimation method of Doz et al.(2012). Secondly, the paper studies the asymptotic properties of generalized moments estimation of model parameters and statistical properties of finite sample respectively. It is proved that the GMM estimators of parameters are consistent estimations with asymptotic normal distribution under appropriate conditions. Finally，we use approximate factor models to detect common driving factors of growth of listed companies in China and their differences empirically.