Nonparametric tests for event studies under cross-sectional dependence

We propose three nonparametric tests for the null of no eventinduced shifts in the distribution of stock returns. One test is the natural extension of the popular Corrado rank test to the case of crosssectionally dependent returns, while the other two are based on new ideas. Unfortunately only for one of these tests a solid theory for approximating the distribution of the statistic can be derived, but some simulation experiments confirm that normality is a good approximation also for the other two. The new tests are compared to a widely used parametric test (Patell) through simulation experiments and are shown to compare favourably in terms of power. Simulation results are based on bootstrapping daily stock returns from the S&P100 and NASDAQ indexes.