Long-term effects of the asymmetry and persistence of the prediction of volatility: Evidence for the equity markets of Latin America

Abstract

This article proposes an extension to the CGARCH model in order to capture the characteristics ofshort-run and long-run asymmetry and persistence, and examine their effects in modeling and forecastingthe conditional volatility of the stock markets from the region of Latin America during the period from 2January 1992 to 31 December 2014. In the sample analysis, the estimation results of the CGARCH-classmodel family reveal the presence of short-run and long-run significant asymmetric effects and long-runpersistency in the structure of stock price return volatility. The empirical results also show that the use ofsymmetric and asymmetric loss functions and the statistical test of Hansen (2005) are sound alternativesfor evaluating the predictive ability of the asymmetric CGARCH models. In addition, the inclusion of long-run asymmetry and long-run persistency in the variance equation improves significantly the out of samplevolatility forecasts for emerging stock markets of Argentina and Mexico.