Risk models vs characteristic models from an investor’s perspective

Abstract

Purpose The purpose of this paper is to analyze the implications of the risk versus characteristic debate from the perspective of a mean-variance investor. Design/methodology/approach Expected returns and the variance-covariance matrix are estimated based on various characteristic and risk models and evaluated for the purpose of mean-variance portfolios. Findings Return estimates from characteristic models are most informative to investors. Risk-factor models provide the most informative estimates of the risk. A mean-variance investor should rely on combinations of the two model types. Originality/value Although the risk vs characteristic debate is a binary academic debate, our findings from an investor's perspective suggest to make use of the best of both worlds.