Measuring event impacts using thinly traded stocks: The case of Chile

Following the Brown-Warner simulation approach and using Chilean daily security return data we examine the specification and power of six test statistics---four parametric and two nonparametric---commonly used in event studies. Our findings show that although some symptoms of nonnormality in security returns and security abnormal returns persists even at the portfolio level, methods based on the use of parametric and non parametric tests for samples of 10 or more securities are well specified, at least for a significance level of 5%. In terms of power, our simulation results show the nonparametric rank test is consistently more likely to detect the presence of an abnormal return that its five competitors. We recommend its use, especially when the researcher conducts an event study using thinly traded stocks.