Balancing two subsamples

[Mahdie Raj]

Hi everyone,
I have a dataset that includes age (continuous variable) and smoking status (smokers=500 vs. non-smokers1500). Given that smokers are older than non-smokers, I would like to match two subsamples based on the age variable. In other words, I would like to have a dataset with 500 smokers and non-smokers (n=?) that have a pretty similar age.
Thanks,
NM

[Phil Bromiley]

There are a great many different ways to do this kind of thing. The treatment model estimators are built for this kind of problem. Alternatively, with only 500 smokers and only wanting to match on age, you could merge the two, sort by age, and then assign groups manually.