Models for expected returns with statistical factors: Evidence from European Equities

J. M. Cueto Muñoz, I. Cascos, A. Grané

In this paper we propose several factor-models and evaluate them on European Equities. Such factors are built from statistical measurements on stock prices, in particular, coefficient of variation, skewness and kurtosis. The data come from Bloomberg, correspond to nearly 2000 EU companies and span from Jan-2010 to Feb-2018. Regarding methodology, we compare the results of classical parametric procedures (based on F-statistics) for multiple factor models with non-parametric block-bootstrap. Methods under assessment are Time-series regression, Cross-Sectional regression and the Fama-Macbeth procedure. Preliminary results indicate that the inclusion of coefficient of variation improves the CAPM-model.

Keywords: Asset pricing Bootstrap Cross-Sectional Factor models Time series

A. J. Bello Espina, M. Á. Sordo Díaz, A. Suarez Llorens, J. Mulero González

M. A. Cebrián Hernández, E. Jiménez Rodriguez, J. M. Feria Domínguez