Abstract

More than three decades ago, Jacobs and Levy introduced the idea of disentangling stock returns across numerous factors. They identified the relationships between individual stock returns and firm characteristics using a cross-sectional analysis and examined the benefits of using the resulting time series of returns to the disentangled factors for return forecasting. Some years later, an alternative factor model proposed by Fama and French made use of time-series factors based on portfolio sorts (examples of these time-series factors include the return differences between small- and big-capitalization stocks and between high- and low-book-to-price stocks). Recently, Fama and French found that the cross-sectional approach using firm characteristics is better able to explain stock returns than the time-series approach based on portfolio sorts. This article compares models that use cross-sectional factors across firm characteristics with models that use time-series factors based on portfolio sorts and discusses the benefits and challenges of the cross-sectional approach for investment management.

Scientific Portfolio AI- Generated Summary

In “Factor Modeling: The Benefits of Disentangling Cross-Sectionally for Explaining Stock Returns,” Bruce Jacobs and Kenneth Levy argue that traditional time-series models often overlook the complexities of interactions between stock characteristics, which can limit their effectiveness in explaining returns. Instead, the authors advocate for a cross-sectional approach to factor modeling that isolates (“disentangles”) each characteristic’s unique contribution to stock returns. This method, they claim, provides “pure” returns by removing overlap from correlated factors like size, value, and profitability.

Jacobs and Levy base their argument on earlier research, including their own work from 1988, where they applied cross-sectional regressions to individual stock characteristics to reveal clear, uncontaminated factor effects. They argue that this disentanglement allows for a better understanding of how each factor independently drives returns and offers a more nuanced view of market anomalies (such as the size or value effects) by separating interdependent factors like book-to-market (BE/ME) and firm size, which are often correlated with profitability and investment intensity.

By comparison, time-series models—such as those by Fama and French—aggregate data over time, which can mask the distinct influences of each characteristic due to multicollinearity between factors. The cross-sectional model Jacobs and Levy propose works at the individual stock level, which reveals variations across firms and exposes individual factor returns, or “pure returns,” unaffected by the influence of other related factors. They suggest that their cross-sectional methodology more effectively captures nuanced stock characteristics, offering clearer insights into the underlying drivers of equity returns, particularly useful in multi-factor portfolios.

The authors further support their model by noting that recent empirical evidence (including studies from Fama and French in 2020) shows improved accuracy in predicting average returns for different portfolio types when using a cross-sectional framework. By avoiding “naïve” factor estimates, which don’t adjust for overlapping characteristics, Jacobs and Levy’s approach shows promise for more precisely targeting expected returns, aiding portfolio managers in building factor-based portfolios that capitalize on specific characteristics like size, value, or momentum without the noise of intertwined effects.