<![CDATA[This paper discusses biases that occurred on level, return and event studymodels. In a prices lead earnings condition, the coefficient in the level model isunbiased, while that in the return model is biased. In a prices do not lead earningscondition, both level and earnings models yield unbiased coefficients economically.In general, the level model suffers more serious bias econometrically than does thereturn model. In an event study, daily returns with equally-weighted index are able to detectabnormal returns better than are monthly returns with value-weighted index. Whenannouncements are clustered in calender events, the market model or the marketadjustementmodel is less biased than the mean-adjusted model. But, when eventdates are not clustered, a simple model such as the mean-adjusted model is not worsethan other models.]]>
Copyrights © 1999
