You seem to be missing a step here. To make up for the fact that don't know the zipcode of the deaths you want to match them to controls that are in zipcodes with similar DECILE values. But for the controls you do not say for what range of dates they were in that zipcode. Are we to assume the controls never moved during the time range of interest?
Hi @Tom, I do know the zipcode of both the deaths and controls. The dataset had zipcode assigned to each beneficiary annually. About 5% changed zipcode from one calendar year to the next, but the rest had the same zipcode during the entire 2-year period.
Good news: We've extended SAS Hackathon registration until Sept. 12, so you still have time to be part of our biggest event yet – our five-year anniversary!