A1251
Title: Multivariate factors: Accounting for the joint dependence among characteristics
Authors: Rasmus Lonn - Erasmus University Rotterdam - Econometric Institute (Netherlands)
Gustavo Freire - Erasmus University of Rotterdam (Netherlands)
Anastasija Tetereva - Erasmus University Rotterdam (Netherlands) [presenting]
Abstract: The aim is to propose a new approach for constructing characteristics-based factor portfolios. Instead of forming independent quantiles or univariate rank sorts, weights are allocated proportional to the conditional distribution of each characteristic given all other characteristics. This is modelled as a conditional distribution in a simple and data-driven way using copulas. The method is applied to the five Fama-French factor portfolios. Relative to the original construction, the multivariate factors increase the maximum attainable Sharpe ratio from 1.04 to 1.80 and decrease by half the number of anomalies with significant alphas in the cross-section of stock returns.
