Volatility clustering at the Johannesburg Stock Exchange: Investigation and Analysis

Abstract

This paper examines the existence and the nature of the volatility clustering phenomenon in the Johannesburg Stock Exchange (JSE). Volatility clustering is one of the most common stylized facts in financial time series; this phenomenon has intrigued many researchers and oriented in a major way the development of stochastic models in finance. The study uses GARCH-type models to detect volatility clustering. GARCH-type models are widely used to test the volatility clustering phenomenon. Their popularity stems from their healing power for heteroskedasticity in regression models and their ability to model nonlinear dynamics. Various studies on volatility clustering suggest that negative shocks to stock prices will generate more volatility than positive shocks of equal magnitude. In this regard the study also examines the asymmetric effect of positive and negative shocks in the JSE. The results indicate the presence of volatility clustering in the JSE. An asymmetric effect of positive and negative shocks on conditional volatility could not be identified. DOI: 10.5901/mjss.2013.v4n14p621