Conditional heteroskedasticity adjusted market model and an event study

Abstract

Stock returns series generally exhibit time-varying volatility. Therefore, one can cast doubt on the way abnormal returns are calculated and consequently interpreted in traditional event studies. In this paper we apply a market model which accounts for GARCH effects leading to more efficient estimators. Using a sample of divestitures, we empirically investigate how this adjustment affects the magnitude of the abnormal returns associated with an event.