Abstract

We compare major factor models and find that the Stambaugh and Yuan (2016) 4-factor model is the overall winner in the time-series domain. The Hou, Xue, and Zhang (2015) q-factor model takes second place and the Fama and French (2015) 5-factor model and the Barillas and Shanken (2018) 6-factor model jointly take third place. The pairwise cross-sectional R2 and the multiple model comparison tests show that the Hou et al. (2015) q-factor model, the Fama and French (2015) 5-factor and 4-factor models, and the Barillas and Shanken (2018) 6-factor model take equal first place in the horse race.

Highlights

  • Starting with the classic capital asset pricing model of Sharpe (1964) and Lintner (1965), the finance literature has been in search for a model that explains the cross-section of expected returns on assets

  • Turning to the 30 IND portfolios, the results for which are shown in Panel I of Table 1, we find that the Gibbons, Ross, and Shanken (1989) test rejects almost all of the factor models at conventional significance levels

  • In Panel B, which reports equality of R2s test results based on the generalized least squares (GLS) cross-sectional regressions, we find that the FF3, FFC, FFPS, FFAF, FF4, and BS6 models outperform the capital asset pricing model (CAPM)

Read more

Summary

Introduction

Starting with the classic capital asset pricing model of Sharpe (1964) and Lintner (1965), the finance literature has been in search for a model that explains the cross-section of expected returns on assets. Different from most studies in the time-series domain (see, for example, Fama and French, 1996, 2016; Hou, Xue, and Zhang, 2015, 2017a), we find that the capital asset pricing model of Sharpe (1964) and Lintner (1965) performs reasonably well All of these findings remain robust irrespective of cross-sectional regression methodologies and normal and sequential tests for nonnested models. Our paper differs from several recent papers that compare model performance, as we employ misspecification robust statistical tests on a much larger array of factor pricing models in the cross-sectional domain Some of these papers include Fama and French (2016), Hou, Xue, and Zhang (2017a), and Stambaugh and Yuan (2016). A separate Internet Appendix contains further details on test assets, robustness tests, and additional results

Competing models
Anomaly portfolios
Model performance measures
Pairwise tests of equality of cross-sectional R2s
Multiple model comparison
Time-series results
Cross-sectional results12
Findings
Conclusion
Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call