Linear Factor Models and the Estimation of Expected Returns
52 Pages Posted: 20 Apr 2016 Last revised: 1 Nov 2017
Date Written: March 3, 2016
Standard factor models imply a linear relationship between expected returns on assets and their factor exposures. We provide the asymptotic properties of factor-model-based expected return estimators for individual assets and show that exploiting this linear relationship leads to precision gains of up to 31% in the estimates of expected returns compared to using historical averages. Moreover, in the presence of omitted factors, adding an alpha to the model captures mispricing only in case of traded factors, otherwise, the bias caused by misspecification cannot be corrected. Finally, inference about expected returns, unlike inference on factor prices, does not suffer from a small-beta bias. The more precise factor-model-based estimates of expected returns translate into signicant improvements in out-of-sample performance of optimal portfolios.
Keywords: Factor Pricing, Risk Premium, Small Betas, Omitted Factors
JEL Classification: C13, C38, G11
Suggested Citation: Suggested Citation