14 S.P. Kothari and J.B. Warner
3.6. A quick summary of our knowledge
3.6.1. Qualitative properties
Table 2highlights, in qualitative terms, what is known about the properties of event
study tests. The table shows the characteristics of event study methods along three di-
mensions: specification, power against specific types of alternative hypotheses, and the
sensitivity of specification to assumptions about the return generating process. The table
also shows how these properties can differ sharply for short and long horizon studies.
Much of the remainder of the chapter deals with the full details of this table.
FromTable 2, horizon length has a big impact on event study test properties. First,
short-horizon event study methods are generally well-specified, but long-horizon meth-
ods are sometimes very poorly specified. While much is understood about how to reduce
misspecification in long horizon studies (see Section4), no procedure in whose spec-
ification researchers can have complete confidence has yet been developed. Second,
short-horizon methods are quite powerful if (but only if) the abnormal performance
is concentrated in the event window. For example, a precise event date is known for
earnings announcements, but insider trading events might be known to have occurred
Ta b l e 2
General characterization of properties of event study test methodsCriterion Length of event window
Short (<12 months) Long (12 months or more)
Specification Good Poor/Moderate
Power when abnormal performance is:
Concentrated in event window High Low
Not concentrated in event window Low Low
Sensitivity of test statistic specification to assumptions about the return generating process:
Expected returns,
unconditional on event
Low HighCross-sectional and time-series
dependence of sample
abnormal returns
Low/Moderate Moderate/HighVariance of abnormal returns,
conditional on event
High HighSensitivity of power to:
Sample size High High
Firm characteristics
(e.g., size, industry)
High High