Title: Functional-coefficient panel data models with cross-sectional dependence with an application to asset pricing
Authors: Cai Zongwu - The University of Kansas (United States)
Ying Fang - Xiamen University (China)
Qiuhua Xu - Southwestern University of Finance and Economics (China) [presenting]
Abstract: A functional-coefficient panel data model with cross-sectional dependence is proposed motivated by re-examining the empirical performance of conditional capital asset pricing model. In order to characterize the time-varying property of assets betas and alpha, the proposed model allows the betas to be unknown functions of some macroeconomic and financial instruments. Moreover, a common factor structure is introduced to characterize cross-sectional dependence which is an attractive feature under a panel data regression setting as different assets or portfolios may be affected by same unobserved shocks. Compared to the extant studies, such as the classic Fama-MacBeth two-step procedure, our model can achieve substantial efficiency gains for inference by adopting a one-step procedure using the entire sample rather than a single cross-sectional regression at each time point. We propose a local linear common correlated effects estimator for estimating time-varying betas by pooling the data. The consistency and asymptotic normality of the proposed estimators are established. More importantly, an L2-norm statistic is constructed for testing the constancy of conditional betas and the significance of pricing errors. We show that the new test statistic has a limiting standard normal distribution under the null hypothesis.