Factorial asset pricing models using statistical anomalies
González-Sánchez, Mariano . (2022) Factorial asset pricing models using statistical anomalies. Research in International Business and Finance, Volume 60, April 2022, 101595
Ficheros
(Some files may be inaccessible until you login with your e-spacio credentials)
Although up to seven factors market, size, earnings, profitability, investment, momentum, and quality are used to explain asset returns mainly due to anomalies, there is no consensus in the financial literature on the suitability of the factors to include in asset pricing models. Empirical research has found that investors’ responses to market movements up and down are not symmetric. We show a new type of anomaly, statistical anomalies, resulting from decomposing asset returns into three independent time series: positive outliers (the good), negative outliers (the bad), and the remainder or Gaussian returns (the usual). Using a sample consisting of 49 equalweighted US industrial portfolios with daily and monthly frequencies from 1969 to 2020, we find evidence that the good-usual-bad factor model exhibits fewer anomalies, better explanatory power, and greater robustness than the “magnificent seven” factors model. Our results are relevant to investors trading at less than monthly frequencies.
The registered version of this article, first published in Research in International Business and Finance, is available online at the publisher's website: Elsevier, https://doi.org/10.1016/j.ribaf.2021.101595
Notas adicionales
La versión registrada de este artículo, publicado por primera vez en Research in International Business and Finance, está disponible en línea en el sitio web del editor: Elsevier, https://doi.org/10.1016/j.ribaf.2021.101595