表單編號：ATRX-Q03-001-FM030-01 The thesis aims to compare the performance of event study tests using daily return rates of Taiwan’s stock market. Under the number of simulated samples of 25 and 50 securities for each portfolio, respectively, parametric, non-parametric and jackknife methods are studied on testing whether the abnormal return is statistically significant on the event day. In order to investigate the power of the test methods under significant levels of 0.05 and 0.1, different levels of abnormal returns are artificially added. Assume that there is no change of the abnormal returns variance during the event period, most of the tests have certain power of detecting the abnormal return, especially, delete-one jackknife method outperforms the event study test methods in terms of size and power. Except it shows that sign test underestimates the occurrence of type I error probability (namely size) for small sample size and over rejects it for large sample size. Furthermore, two types of variance changes cases adopting Christie''s (1983) model and Beaver''s (1968) model are also studied. The simulation results also shows the delete-one jackknife method still outperforms the rest of the event study test methods and robust even under the variance changes cases in terms of the size and power.