Was the promotion intended to increase category writing (unbranded) or writing of a particular product (branded)?
Were individual physicians selected to participate in the promotion (e.g., dinner meetings) or were all physicians/consumers in a geographic area exposed to the promotion (e.g., DTC campaigns)?
How was the "treatment group/test area" selected?
What was the time period of the promotion? Was the promotion conducted in phases?
What was the time period immediately preceding the promotion ("pre-period")?
How can a matched comparison group be selected?
Selection of Matched Comparison Group
Once the treatment physicians have been identified (by ME number or geography), a matched comparison group must be selected so that the treatment and comparison groups are as similar in the pre-period as possible.
This increases the likelihood that differences in the post-period (promotion period) can be attributed to the promotion.
Comparison physicians are selected by performing a one-on-one match with each treatment physician using parameters such as specialty, age, gender, geographic location, average pre-period product Rx's and product market share, pre-period market decile, and pre-period detailing and sampling.
Promotion Impact Evaluation
A monthly post-period evaluation is performed to determine the difference in the measure being tested (product NRx or TRx volume market share).
A double difference impact (I) calculation is performed for each matched treatment (T)/comparison (C) physician pair for each post-period month (j) being evaluated:
Ij = (Tj - Tpre) - (Cj - Cpre) where "pre" = avarage pre-period value
A statistical test is performed to determine whether each impact difference is significantly different from zero.