Copulas based seemingly unrelated quantile regression

Abstract

We propose a multivariate copulas based seemingly unrelated quantile regression. We add the multivariate copula density function into the likelihood to relax the strong assumption of multivariate normal distribution of the conventional model. The simulation study is conducted to evaluate the performance of our proposed model. Moreover, we apply our proposed model to the Fama-French equation in order to investigate the systematic risk in the three major stocks in NASDAQ market. The results of this study suggest that our proposed model provides a particularly good description of these stock prices at every quantile level.