[R] pvclust: highly varying results for the exactly same analysis, unknown warning message

Hello, I have got problems using pvclust() and it would be really nice if somebody could help me. I have got a dataframe called "owner2006" looking like this: company year share0 share1 share2 share5 share6 share7 share11 share12 1 aareal bank 200

Re: [R] pvclust crashing R on Ubuntu 10.10

I confirm this bug exists and is 100% replicable on R version 2.12.2 (2011-02-25) Platform: i686-pc-linux-gnu (32-bit) locale: [1] LC_CTYPE=en_US.utf8 LC_NUMERIC=C [3] LC_TIME=en_US.utf8LC_COLLATE=en_US.utf8 [5] LC_MONETARY=C LC_MESSAGES=en_US.utf8 [7] LC_PAPER=en_US

[R] pvclust crashing R on Ubuntu 10.10

Hi all I am writing to you with a question regarding the pvclust package. And yes, before the usual people produce their usual contact-the-package-maintainers line, ye, I tried that but the emails one can find on the web either bounce or are not responded to. Also, yes, this error has already been

[R] pvclust package

I have been using the pvclust package to perform hierarchical clustering with bootstrapped p-values. I am using it to compare the numbers of clusters identified between different datasets. However, the numbers are not comparable because pvclust calculates p-values for the optimal number of clusters

Re: [R] pvclust() with distance method from vegdist(), package = vegan

thank you for the information. would be great to have the possibility to check significance of clusters coming from other distance-measures, too - but i'll be satisified with what pvclust() can do. yours, kay -- View this message in context: http://n4.nabble.com/hvcluster-with-distance-method-f

[R] pvclust with squared euclidean distance

hi, I'm trying to use pvclust function (pvclust package) to perform a cluster analysis and finding p-values for groups, however, i need to use the "squared euclidean distance" method instead of "euclidean distance" as distance matrix but it seems that the package only allows the last... any ideas

[R] pvclust

Hello there, Here's a question regarding p-values on clusters produced by hierarchical cluster analysis. A web search led me to the program pvclust to tackle this problem. But when I run the problem I get strange results. The 'AU' (approximately unbiased) p-values are very different from the '

[R] pvclust distance matrix

Hello, I am attempting to assign significance levels to a UPGMA cluster analysis as part my doctoral research. The pvclust function works well but doesn't include the similarity index I need (morisita's) as an option for computing a distance matrix. Morisita's is available in vegdist in the

Re: [R] pvclust warning message

Phil taylor wrote: > Hi all > > I am trying to perform the follwing: > > fit<-pvclust(wq, method.hclust="ward", method.dist="euclidean") What is wq? Which version of R? WHich version of the pvclust package (I guess we are talking about that one?)? We also need a reproducible example, as the

[R] pvclust warning message

Hi all I am trying to perform the follwing: fit<-pvclust(wq, method.hclust="ward", method.dist="euclidean") but get a strange error message that I just cant figure out. Has anyone come across this? Any help would be most appricieated Error in hclust(distance, method = method.hclust) : NA/NaN/