Comparing Cross-Section and Time-Series Factor Models

Abstract

We use the cross-section regression approach of Fama and MacBeth (FM 1973) to construct cross-section factors corresponding to the time-series factors of Fama and French (FF 2015). Time-series models that use only cross-section factors provide better descriptions of average returns than time-series models that use time-series factors. This is true when we impose constant factor loadings and when we use time-varying loadings that are natural for time-series factors and time-varying loadings that are natural for cross-section factors.

JEL Classification: G!, G!!, G12