Are Higher-Order Factors Useful in Pricing the Cross-Section of Hedge Fund Returns?

57 Pages Posted: 31 Jul 2018 Last revised: 12 May 2019

See all articles by Elaine Fang

Elaine Fang

Princeton University

Caio Almeida

Getulio Vargas Foundation ; Princeton University

Date Written: May 10, 2019


This paper investigates hedge funds' exposures to various risk factors across different investment strategies through models with both linear and second-order factors. We extend the analysis from an augmented linear model based on Fama and French (1993) and Fung and Hsieh (2001) to second-order models that include all quadratic and interaction terms by adopting a novel multistep strategy that combines the variable selection capabilities of the Lasso regression with the Fama-MacBeth (1973) two-step method. We find that, for some strategies, several quadratic and interaction terms are statistically significant. Nonetheless, there is no evidence that the second-order models have more overall explanatory or predictive power than the linear model. Moreover, while both linear and second-order models perform well for directional funds (like emerging markets, event driven and managed futures), missing factors may still remain for semi-directional funds, such as fund of funds, long/short equity hedge and multi-strategy.

Keywords: Hedge Fund Performance, LASSO, Risk Factors, Cross-Section of Returns

JEL Classification: C14, C58, G11, G17

Suggested Citation

Fang, Elaine and Almeida, Caio, Are Higher-Order Factors Useful in Pricing the Cross-Section of Hedge Fund Returns? (May 10, 2019). Available at SSRN: or

Elaine Fang

Princeton University ( email )

22 Chambers Street
Princeton, NJ 08544-0708
United States

Caio Almeida (Contact Author)

Getulio Vargas Foundation ( email )

Praia de Botafogo 190, 11o andar
Rio de Janeiro, Rio de Janeiro 22250-900
5521-37995827 (Phone)
5521-2553-8821 (Fax)


Princeton University ( email )

26 Prospect Avenue
Princeton, NJ 08540
United States

Register to save articles to
your library


Paper statistics

Abstract Views
PlumX Metrics