The asymmetric reverting property of stock returns on the JSE: an ANAR-GJR GARCH approach
No Thumbnail Available
Date
2015-02-03
Authors
Unterhalter, Amber
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
This research report examines the asymmetric reverting behaviour of the conditional mean and conditional variance of daily, weekly and monthly nominal stock return observations on the Johannesburg Stock Exchange (“JSE”), across eight value-weighted indices for the sixteen-year period from July 1995 to October 2011.
Utilizing the Asymmetric Nonlinear Autoregressive (“ANAR”) model of Nam, Kim and Arize (2006) to model asymmetry in the conditional mean, and the GJR Generalized Autoregressive Conditional Heteroskedasticity (“GJR GARCH”) model of Glosten, Jagannathan and Runkle (1993) to model asymmetry in the conditional variance, this research report presents an empirical investigation into the asymmetric reverting behaviour of stock returns upon the JSE.
Asymmetry in the conditional mean and conditional variance manifests in stochastic time-series data by way of a negative return reverting more quickly and with a greater magnitude to a positive return than a positive return reverting to a negative return (Nam, Kim, & Arize, 2006). The results of the empirical investigation of stock returns on the JSE indicate that the uneven reverting qualities are present across seven indices and are more pronounced in the daily and weekly observed time intervals.
Description
Thesis (M.Com. (Finance)--University of the Witwatersrand, Faculty of Commerce, Law and Management, School of Economic and Business Sciences, 2014.