[R] weighted hierarchical cluster analysis

Moritz Lennert mlennert at club.worldonline.be
Wed Jan 21 18:23:32 CET 2004


After an exchange of mail with Martin Maechler, I turn to the list on hist
demand, trying to reformulate my question to make it clearer.

We are trying to submit data to a hierarchical cluster analysis which
weights each observation by a value given for each observation.

The weighting should occur at two moments in the process:

1) in the calculation of the distance by multiplying (for each pair) the
sum of squares by the product of the respective weights divided by the sum
of the weights (if two pairs of observations are of equal euclidian
distance, the pair with a higher weight should be considered of greater

2) in the calculation of the ward criterion, by not using just the number
of observations in each cluster, but a weighted sum of observations.

Has anyone implemented such a type of weighted hierarchical clustering
analysis ? If not, does this mean we would have to create new fortran or C
code to implement this ?

Thank you,

Moritz Lennert

More information about the R-help mailing list