I have 400 clusters (20,000 observations). I want to get proportion of smokers in each cluster (Smoking vs non-smoking) as a separate variable in the same data set for each cluster. I would really appreciate the help from helping hands.
Thanks
How is a smoker identified in these clusters? How are the clusters identified? Can you show us the first 10 records of your data set?
cluster Smoker . Proportion of smoker in each cluster (Expected outcome) . Observations
1 . 1 (Yes) .5 1
1 . 2 (No) .5 2
1 . 1 .5
1 2 .5
2 . 1 .667
2 . 2 .667
2 . 1 .667
3 . 2
3 . 1
3 . 2
Learn how use the CAT functions in SAS to join values from multiple variables into a single value.
Find more tutorials on the SAS Users YouTube channel.
Ready to level-up your skills? Choose your own adventure.