Dynamic Factors and Asset Pricing
46 Pages Posted: 11 Sep 2007 Last revised: 4 Oct 2008
Date Written: September 29, 2008
This study develops an econometric model that incorporates features of price dynamics across assets as well as through time. With the dynamic factors extracted via the Kalman filter, we formulate an asset-pricing model, termed as the dynamic factor pricing model (DFPM). We then conduct asset-pricing tests in the in-sample and out-of-sample contexts. Our analyses show that the ex ante factors are a key component in asset pricing and forecasting. By using the ex ante factors, the DFPM improves upon the explanatory and predictive power of other competing models, including unconditional and conditional versions of the Fama and French (1993) three-factor model. In particular, the DFPM can explain and better forecast the momentum portfolio returns, which are mostly missed by other alternative models.
Keywords: Kalman filter, asset pricing, dynamic factors
JEL Classification: G12
Suggested Citation: Suggested Citation