07-06-2016 04:11 PM
I'm trying to use frequency matching/category matching to match a set of control patients to my selected case patients. That is, rather than individual (1:n) matching, I just want my control group to have similar distributions for a selected set of covariates. I don't need a white, 50-year-old, female case patient to have another exact white, 50-yr-old, female control patient -- I just want to be sure that if 50% of my cases are white, 20% are 50-year-olds, and 55% are female, those respective distributions are similar in the control group. Is there a straightforward way to match this way in SAS? I have done 1:n matching using PROC SURVEYSELECT, but I haven't been able to find any examples of performing frequency matching.
Any help would be greatly appreciated!
07-07-2016 05:39 PM - edited 07-07-2016 05:48 PM
Control sorting in PROC SURVEYSELECT would get you a match to the population frequency, if your population has the right size.
STRATA would let you select certain numbers in each stratum, but it sounds like you're really not going for that detail (that would be 1:N).
You could use pre-sampling weights perhaps with the SIZE option in SURVEYSELECT, to weight your control population to match the demographics of your experimental group?