> Well, that is in all good texts on R, together with the > solution: drop=FALSE. See ?"[" for the on-line details.OK. Thank you a lot. Now patched cclust and clustIndex work fine for 1D case. BTW, why not to apply the "drop=F" to these functions? I guess other users need 1D case as well. kind regards, Valery A.Khamenya --------------------------------------------------------------------------- Bioinformatics Department BioVisioN AG, Hannover
On Thu, 15 May 2003, Khamenia, Valery wrote:> > Well, that is in all good texts on R, together with the > > solution: drop=FALSE. See ?"[" for the on-line details. > > OK. Thank you a lot. Now patched cclust and clustIndex > work fine for 1D case. BTW, why not to apply the "drop=F" > to these functions? I guess other users need 1D case as > well.Nothing to do with me: you should report problems with packages to the maintainers, rather than R-help or a member of R-core. -- Brian D. Ripley, ripley at stats.ox.ac.uk Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ University of Oxford, Tel: +44 1865 272861 (self) 1 South Parks Road, +44 1865 272866 (PA) Oxford OX1 3TG, UK Fax: +44 1865 272595
I am trying to use hclust function from mva package but I can't understand what the variable height stands for when I use the ward criterion. Here is a small example : library(mva) x <- c(1,2,3,4) cluster <- hclust(dist(x), method="ward") cluster$height cluster$height = 1 1 3 but it is supposed to be 0.5 0.5 4 the distance between clusters is Ni*Nj/(Ni+Nj)*||Gi-Gj||^2 and cluster$height does not match with this distance. Does someone has any idea ? Thanks in advance. Philippe Hup? -- -------------------------------------------------- Philippe Hup? Institut Curie - Equipe Bioinformatique 26, rue d'Ulm - 75005 PARIS France +33 (0)1 42 34 65 29 Philippe.Hupe at curie.fr <mailto:Philippe.Hupe at curie.fr>