Panel Data Models with Grouped Factor Structure Under Unknown Group Membership
研究了群组归属和数量未知的面板数据模型，通过带惩罚的最小二乘法估计，可处理大量解释变量，并用于美国共同基金和中国A股收益分析。
Summary This paper studies panel data models with unobserved group factor structures. The group membership of each unit and the number of groups are left unspecified. We estimate the model by minimizing the sum of least squared errors with a shrinkage penalty. The number of explanatory variables can be large. The regressions coefficients can be homogeneous or group specific. The consistency and asymptotic normality of the estimator are established. We also introduce new C p ‐type criteria for selecting the number of groups, the numbers of group‐specific common factors and relevant regressors. Monte Carlo results show that the proposed method works well. We apply the method to the study of US mutual fund returns and to the study of individual stock returns of the China mainland stock markets. Copyright © 2015 John Wiley & Sons, Ltd.