In order to appraise the event’s impact we require a measure of
abnormal returns. The abnormal return is defined as the actual expost
return minus the normal return over the event window. The
normal return is defined as the return that would be expected if
the event did not take place. There are various choices for modeling
a normal return. We use the market adjusted return model as we
described above where the normal return is the market return.
The market adjusted return model assumes that each sector would
have a stable relation to the market and have a market beta of 1.17
In our case the pre-event estimation period has different characteristics
and risk return dynamics from the period we use for the crisis;
therefore it is not reasonable to use returns in the pre-event estimation
period as a normal return parameter. The crisis period itself,
cannot be used for estimations as it is the event period. Therefore
the most reasonable choice under the circumstances is to use the market adjusted returns model where an estimation period is not required
to obtain parameter estimates.18