Analysing the return distributions of Australian stocks: the CAPM, factor models and quantile regressions Online publication date: Wed, 30-Oct-2013
by David E. Allen; Abhay Kumar Singh; Robert Powell
Global Business and Economics Review (GBER), Vol. 15, No. 1, 2013
Abstract: Traditionally, ordinary least square (OLS) regression methods are used to test asset pricing models. This study focuses on the use of quantile regression as an alternative approach to the analysis of risk and return distributions in quantitative finance. It empirically examines the behaviour of two widely used asset pricing factors, beta and book to market ratios, but the focus is on minimising absolute deviations around the median rather than minimising squared deviations around the mean of their distributions, as we apply quantile regressions as opposed to OLS. We show how OLS is less able to capture the extreme values or the adverse losses in the return distribution, which on the other hand are captured by quantile regressions. The study not only shows that the factors do not necessarily follow a linear relationship but also shows that the traditional use of OLS becomes less effective when it comes to analysing the extremes within a distribution, which are often a source of keen interest for investors and risk managers.
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.Complimentary Subscribers, Editors or Members of the Editorial Board of the Global Business and Economics Review (GBER):
Login with your Inderscience username and password:
Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.
If you still need assistance, please email subs@inderscience.com
Our Blog 
Follow us on Twitter 
Visit us on Facebook