Ulrich Koehler wrote:
>However, if I use wards-linkage I get different results for the two distance matrizes: [snip]<
You may have run into a local optima problem. Clustering methods and other multivariate data reduction procedures are plagued by this. The clustering program should give you the option of starting from different configurations, possibly many random starts or from a given starting value. I don't know enough about Ward's linkage to know if is is more susceptible to this problem than the others.
Jay
<<winmail.dat>>
