Cluster analysis forcing equal size clusters (or penalising unequal size)

[Rob Shaw]

I'm am trying to do a cluster analysis on a set of points (so my variables are x and y) but with the constraint that the resulting clusters contain the same (or similar) number of points. An alternative would be an algorithm that penalises unequal cluster sizes.

Does anyone know if this is possible within Stata?

Thanks
Rob

[Rob Shaw]

For anyone coming across this in the future, I found a solution to this. There is a package for R called anticluster that can do equal sized clusters.