Pure Factor Portfolios and Multivariate Regression Analysis

Posted: 8 Feb 2017 Last revised: 13 Nov 2019

See all articles by Roger G Clarke

Roger G Clarke

Harindra de Silva

Analytic Investors, Inc.

Steven Thorley

BYU Marriott School of Business

Date Written: February 28, 2017


Linking factor portfolio construction to cross-sectional regressions of security returns on standardized factor exposures leads to a transparent and investable perspective on factor performance. Under capitalization-weighting, multivariate regression coefficients translate to portfolio returns that are benchmark relative and cleared of secondary factor exposures. The methodological contributions in this paper are illustrated using a 50-year data set of one-thousand large U.S. stocks and five factor exposures: Value, Momentum, Small Size, Low Beta, and Profitability. Each of the five pure factor portfolios have exposures to the other four factors that match the benchmark portfolio. As two case studies in factor portfolio analysis, we focus on cheapness as measured by Earnings Yield, and interest rate risk as measured by sensitivity to the 10-year Treasury Bond return.

Keywords: Factor Investing, Smart Beta, Portfolio Construction

JEL Classification: G11, C58

Suggested Citation

Clarke, Roger G and de Silva, Harindra and Thorley, Steven, Pure Factor Portfolios and Multivariate Regression Analysis (February 28, 2017). Journal of Portfolio Management, 2017, Available at SSRN: https://ssrn.com/abstract=2912673 or http://dx.doi.org/10.2139/ssrn.2912673

Harindra De Silva

Analytic Investors, Inc. ( email )

555 West 5th Street
50th Floor
Los Angeles, CA 90013
United States
213-688-3015 (Phone)
213-688-8856 (Fax)

Steven Thorley (Contact Author)

BYU Marriott School of Business ( email )

616 TNRB
Brigham Young University
Provo, UT 84602
United States
801-378-6065 (Phone)
801-378-5984 (Fax)

No contact information is available for Roger G Clarke

Do you have negative results from your research you’d like to share?

Paper statistics

Abstract Views
PlumX Metrics