Efficient Semiparametric Estimation of the Fama-French Model and Extensions

Abstract

This paper develops a new estimation procedure for characteristic-based factor models
\nof stock returns. We treat the factor model as a weighted additive nonparametric
\nregression model, with the factor returns serving as time-varying weights and a set
\nof univariate nonparametric functions relating security characteristic to the associated
\nfactor betas. We use a time-series and cross-sectional pooled weighted additive nonparametric
\nregression methodology to simultaneously estimate the factor returns and
\ncharacteristic-beta functions. By avoiding the curse of dimensionality, our methodology
\nallows for a larger number of factors than existing semiparametric methods. We
\napply the technique to the three-factor Fama–French model, Carhart’s four-factor extension
\nof it that adds a momentum factor, and a five-factor extension that adds an
\nown-volatility factor. We find that momentum and own-volatility factors are at least as
\nimportant, if not more important, than size and value in explaining equity return comovements.
\nWe test the multifactor beta pricing theory against a general alternative
\nusing a new nonparametric test