Asset selection using a factor model and data envelopment analysis– A quantile regression approach

David E. Allen, Abhay Kumar Singh, Robert J. Powell

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Given the growing number of stocks and other financial instruments available in the investment market, there is always a need for quick and efficient methods of asset selection for investment purposes. The Fama–French three-factor model has the allure of simplifying asset selection by narrowing the number of parameters required to assess risk, but the usual technique of ordinary least squares regression (OLS) used for the estimation of the coefficients or sensitivity to the three factors suffers from the problem of modeling the conditional mean of the distribution inherent to OLS. In this chapter, we use the technique of data envelopment analysis applied to the Fama–French three-factor model to choose stocks from the Dow Jones Industrial Index. We also apply the more robust technique of quantile regression to estimate the coefficients for the factor model and show that the assets selected using this regression method lead to the construction of superior portfolios with higher returns in equally weighted portfolios when contrasted with the outcomes from OLS.
Original languageEnglish
Title of host publicationRethinking valuation and pricing models
Subtitle of host publicationlessons learned from the crisis and future challenges
EditorsCarsten Wehn, Christian Hoppe , Greg N. Gregoriou
Place of PublicationOxford
PublisherElsevier
Chapter27
Pages443–455
Number of pages13
ISBN (Electronic)9780124158757
DOIs
Publication statusPublished - 2013
Externally publishedYes

    Fingerprint

Cite this

Allen, D. E., Singh, A. K., & Powell, R. J. (2013). Asset selection using a factor model and data envelopment analysis– A quantile regression approach. In C. Wehn, C. Hoppe , & G. N. Gregoriou (Eds.), Rethinking valuation and pricing models: lessons learned from the crisis and future challenges (pp. 443–455). Oxford: Elsevier. https://doi.org/10.1016/B978-0-12-415875-7.00027-0