A Brown and Warner [1980, 1985] event study methodology is applied to the foreign exchange area. Comparisons of the performance of four abnormal return models are examined with simulations under different experimental conditions, such as choice of foreign currency or numeraire, level of abnormal shock, sample size, length of estimation period, market return proxy, and time period examined. The results provide practical suggestions on the selection of an event study methodology and demonstrate that some of the findings of Brown and Warner are not generalizable to the foreign exchange area. © 1990, Academy of International Business.