search for: rechtman

Hi, I am using levelplot, and would like remove from each panel (condition) its unused x levels. e.g. Remove from panel vs=1 the cyl level=8. data(mtcars) levelplot(mpg~factor(cyl)*factor(gear)|factor(vs)) Thanks for your help, Ronny -- View this message in context: http://r.789695.n4.nabble.com/Lattice-levelplot-remove-unused-levels-per-panel-tp4656087.html Sent from the R help mailing

I would like to get an hierarchical clustering tree with bootstrap values indicated on the nodes, as in pvclust. The problem is that I have only distance matrix instead of the raw data, required for pvclust. Is there a way to get it? fit1 <- hclust(dist) # an object of class '"dist" plot(fit1) # dendogram without p values library(pvclust) fit2 <- pvclust(raw.data,

I am using R dixon.test in order to perform Q test for detection of outliers. The p-values for high Q values are consistent with the table in Rorabacher, D.B. (1991) http://www.flworkshop.com/sscs/dixon_test.pdf, but it seems that small Q-values get problematic p-values. For example: dixon.test(c(0.324,0.5,1,1.324),two.sided=T) Q = 0.324, p-value = 1