Analysis of Financial Time Series, Third Edition

9.3 Fundamental Factor Models

Fundamental factor models use observable asset specific fundamentals such as industrial classification, market capitalization, book value, and style classification (growth or value) to construct common factors that explain the excess returns. There are two approaches to fundamental factor models available in the literature. The first approach is proposed by Bar Rosenberg, founder of BARRA Inc., and is referred to as the BARRA approach; see Grinold and Kahn (2000). In contrast to the macroeconomic factor models, this approach treats the observed asset specific fundamentals as the factor betas, , and estimates the factors at each time index t via regression methods. The betas are time invariant, but the realizations evolve over time. The second approach is the Fama–French approach proposed by Fama and French (1992). In this approach, the factor realization fjt for a given specific fundamental is obtained by constructing some hedge portfolio based on the observed fundamental. We briefly discuss the two approaches in the next two sections.

9.3.1 BARRA Factor Model

Assume that the excess returns and, hence, the factor realizations are mean corrected. At each ...