An Investigation of Event Study Methodologies with Clustered Events and Event Day Uncertainty

The specification and power of mean-adjusted, market and quadratic models in event studies using OLS, Patell, Jaffe and GLS are examined. Simulation is used with security and portfolio returns to capture different cross correlations. The market model is always superior in specification and power compared to the mean-adjusted and quadratic models. The use of OLS with the market model is supported in the absence of clustered events and event day uncertainty, whereas use of Jaffe with the market model is supported in the presence of these problems.