Scientific Beta

The finance literature has established a Size effect: stocks with smaller market capitalisation outperform large stocks over the long term. The Size factor is included in asset-pricing models, due to its explanatory power for cross-sectional differences in equity returns. However, a common recommendation in the asset management industry is to remove Size from the factor menu, given its relatively weak post-publication performance. Instead of looking at the stand-alone performance, we account for cross-factor correlation to assess the impact of excluding the Size factor.

The finance literature has established a Size effect: stocks with smaller market capitalisation outperform large stocks over the long term. The Size factor is included in asset-pricing models, due to its explanatory power for cross-sectional differences in equity returns. However, a common recommendation in the asset management industry is to remove Size from the factor menu, given its relatively weak post-publication performance. Instead of looking at the stand-alone performance, we account for cross-factor correlation to assess the impact of excluding the Size factor. We consider three different tests. First, we measure the impact on model fit of asset pricing models. Second, we assess whether the Size premium remains intact when accounting for implicit exposures to other factors. Third, we evaluate the impact of the Size factor on the performance of optimal multi-factor portfolios. Our results suggest that the Size factor improves model fit, delivers a significant positive premium in the presence of other factors, and contributes positively to the performance of multi-factor portfolios. Omitting the Size factor has substantial cost to investors, which often exceed that of omitting other popular factors.