Capital asset pricing model through quantile regression: An entropy approach

• Main Authors: Woraphon Yamaka, Kittawit Autchariyapanitkul, Paravee Meneejuk, Songsak Sriboonchitta
• Format: Journal
• Published: 2018
• Subjects: Mathematics; Agricultural and Biological Sciences
• Online Access: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85039714336&origin=inward; http://cmuir.cmu.ac.th/jspui/handle/6653943832/43757
• Institution: Chiang Mai University

© 2017 by the Mathematical Association of Thailand. All rights reserved. This paper introduces the generalized maximum entropy(GME) approach, which was proposed by Golan, Judge and Miller in 1997 to estimate the quantile regression model for capital asset pricing because this information-theoretic estimator method is robust to multicolinearity and ill-posed problems inherent in CAPM. Monte Carlo simulations for quantile regression exhibited that the primal GME estimator outperforms several classical estimators such as least squares, maximum likelihood and Bayesian when the extreme quantile is considered. We describe statistical inference techniques for this estimator and demonstrate its usefulness in risk measurement through capital asset pricing model.