Short-Horizon Event Study Estimation with a STAR Model and Real Contaminated Events

Abstract

We propose a test statistic for nonzero mean abnormal returns based on a Smooth Transition Auto Regressive (STAR) specification. Estimation of the STAR test statistic takes into account the probability of unrelated events that could otherwise bias the parameters of the market model and thus the specification and power of the resulting test statistics. Using both simulated and real stock returns data from mergers and acquisitions, we find that the STAR test statistic is robust to unrelated events happening in the event-study estimation window and in the presence of variance-induced events. Under the STAR test statistic the true null hypothesis is rejected at appropriate levels. Moreover, it exhibits the highest levels of power when compared with other test statistics that are widely and routinely applied in the event-study approach.

Keywords: Event studies, parametric test statistics, unrelated events, Markov switching regression model, Smooth Transition Auto Regressive (STAR) model

JEL Classification: G14, G34