Combine cluster analysis with proc GENMOD

[stat_sas]

Thanks for the detail. I think you are on the right track,  you have 4 clusters just need to check heterogeneity in freq_adj variable across 4 clusters using proc anova. If they are statistically different then you can proceed with proc genmod.

[jonathanch]

I win with homogeneity but I also lose because I multiply the number of estimations..

Thanks for your time.

See you.