A Better Asymmetric Model of Changing Volatility in Stock Returns: Trend-GARCH
Universität Bayreuth Diskussionspapier No. 03-05
24 Pages Posted: 25 Jul 2007
Date Written: 2005
In this paper we consider the theoretical and empirical relevance of a new family of conditionally heteroskedastic models with a trend dependent conditional variance equation: the Trend-GARCH model. The interest in these models lies in the fact that modern microeconomic theory often suggests the connection between the past behavior of time series and the subsequent reaction of market individuals and thereon changes in the future characteristics of the time series. Our results reveal important properties of these models, which are consistent with stylized facts in financial data sets. They can also be employed for model identification, estimation, and testing. The empirical analysis of a broad variety of asset prices significantly supports the existence of trend effects. The Trend-GARCH model proves to be superior to alternative models such as EGARCH, AGARCH, or TGARCH in replicating the leverage effect in the conditional variance and in fitting the news impact curve.
Keywords: GARCH, trend, volatility, news impact curve
JEL Classification: C22, C52, G12
Suggested Citation: Suggested Citation