How can I use a control-firm approach, where each sample firm is pre-matched to a similar firm?
Solution: The control-firm approach as it commonly appears in the literature can be implemented using the SHORT and GROUP options on the REQUEST statement. Include the PERMNOs (or whatever security identifier is being used) for both the sample and control firms in the same request file. Include a grouping variable which has a unique value for each sample firm; each control firm should receive the same grouping variable value as its matched sample firm. See the documentation for the REQUEST statement option GROUP for details. Also include a short-long indicator, ‘S’ for control firms and ‘L’ for sample firms. See the documentation of the REQUEST statement option SHORT for details. The simple paired difference test frequently used with the control-firm approach can be invoked with the EvtStudy statement option CSECTERR. To suppress benchmark models, include the EvtStudy statement options RAW NOMM NOMAR. An estimation period still must be defined, but may be forced to overlap the event pe
