A new approach to the computation of the Jardine-Sibson Bk clusters
F. James Rohlf · The Computer Journal · 1975
A new approach to the computation of Jardine and Sibson's (1968a) (fine) k-cluster method Bk is described. The algorithm makes use of the fact that the set of dissimilarities which are invariant under the Bk clustering transformation can be represented as an abstract graph. The proposed algorithms for computing this graph obtains both the (weak) k-ultrametric dissimilarity matrix and the k-clusters simultaneously.