This article develops a new methodology for estimating and testing conditional factor models in finance. We propose a two-stage procedure that naturally unifies the two existing approaches in the finance literature-the parametric approach and the nonparametric approach. Our combined approach possesses important advantages over both methods. Using our two-stage combined estimator, we derive new test statistics for investigating key hypotheses in the context of conditional factor models. Our tests can be performed on a single asset or jointly across multiple assets. We further propose a novel test to directly check whether the parametric model used in our first stage is correctly specified. Simulations indicate that our estimates and tests perform well in finite samples. In our empirical analysis, we use our new method to examine the performance of the conditional capital asset pricing model (CAPM), which has generated controversial results in the recent asset-pricing literature.
Specification tests, Conditional CAPM, Semiparametric method, Nonparametric method, Conditional factor models
Journal of Business and Economic Statistics
Taylor & Francis: SSH Journals
LI, Yan; SU, Liangjun; and XU, Yuewa.
A combined approach to the inference of conditional factor models. (2015). Journal of Business and Economic Statistics. 33, (2), 203-220. Research Collection School Of Economics.
Available at: http://ink.library.smu.edu.sg/soe_research/1863
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.