I have a matrix 14000 row X 69 col. I noticed that when I break them in to 5~200 clusters. Each cluster has the same size. I use the first 100 row to run, each cluster has different size. Why is that? I used this command cl<- kmeans(t,k,algorithm = "Hartigan-Wong",nstart=5*k,iter.max=5*k) Thanks a lot!!!!! -- View this message in context: http://www.nabble.com/What-is-wrong-with-my-Kmean--tp19802268p19802268.html Sent from the R help mailing list archive at Nabble.com.