I'm new here, and I'm not sure whether this is the right sub forum.
I've done a lot of searching online for tutorials, but I'm unable to find the answer to my question.
I have 1 dataset, which I can divide into 3 subgroups according to a variable.
Each group has a number of people with a certain age in it, I divided the ages into decade's by a variable. (for example 18-30years, decade=2, 30-40, decade =3, etc.)
The 3 subgroups are not equally divided in those decades. I am looking for a way to make all 3 subgroups have the same proportion of each decade for further analysis. For example, decade 2 = 5% in all groups, decade 3 = 10% in all groups. I want to delete random cases from 2 subgroups, equalizing them to the subgroup with the smallest number of cases.
Does anybody know how I can manage this? Every help is welcome, thanks in advance!
EDIT: I think case control matching might be the way to go, however I only have access to SPSS 21...