Re: [R] hierarchical model with heteroscedastic variances

2014-12-01 Thread John McKown
Please repost your message in plain text. On my gmail account, it was totally unreadable due to the fact that the forum software strips out all the HTML "stuff". On Mon, Dec 1, 2014 at 7:51 PM, Rafael Moral wrote: > Dear useRs,I have been wondering whether it would be possible to fit a > linear

[R] hierarchical model with heteroscedastic variances

2014-12-01 Thread Rafael Moral
Dear useRs,I have been wondering whether it would be possible to fit a linear mixed model including heteroscedastic variances for a 2-level hierarchical study with subsampling.Suppose that I had three levels for the first hierarchical level and 4 for the second, with 2 subsamples, e.g. set.seed(

Re: [R] Remove the border/frame in a dotplot()

2014-12-01 Thread Duncan Mackay
Hi See also https://stat.ethz.ch/pipermail/r-help/2007-September/140098.html This may do library(grid) dotplot(~ 1:10, scales = list(col = "black", tck = c(1, 0)), par.settings = list(axis.line = list(col = "transparent")), axis = function(side, ...) { if (side == "le

Re: [R] Creating submatrices from a dataframe, depending on factors in sample names

2014-12-01 Thread David L Carlson
I may have misunderstood, but does this do what you want? > df.mat <- as.matrix(df) > same <- lapply(1:3, function(x) df.mat[grep(paste0("_", x), + rownames(df.mat)), grep(paste0("_", x), colnames(df.mat))]) > same [[1]] HQ673618_1 HQ674317_1 EU686630_1 HQ673618_1 NA 90.8

[R] New book using R

2014-12-01 Thread bpro
Dear Colleagues, I have prepared a book to be published in Czech, ‘Biostatistika pro lékaře, principy základních metod a jejich interpretace s využitím statistického systému R’  (in English ‘Biostatistics for physicians – principles of basic methods and interpretation of results using the R sta

Re: [R] Cycling and different xerror values in cp of rpart, which result should I trust?...

2014-12-01 Thread Prof Brian Ripley
Do see the posting guide, and do not re-post (https://stat.ethz.ch/pipermail/r-help/2014-November/423727.html). I suspect I am not alone in not knowing what you are talking about (even though I am the rpart maintainer). Please do try to explain clearly what you mean with the reproducible exam

Re: [R] Creating submatrices from a dataframe, depending on factors in sample names

2014-12-01 Thread Bert Gunter
I do not have the patience to study your request carefully, but does the following help? > a <- 1:3 > x <- outer(a,a,paste,sep=".") > x [,1] [,2] [,3] [1,] "1.1" "1.2" "1.3" [2,] "2.1" "2.2" "2.3" [3,] "3.1" "3.2" "3.3" > x[upper.tri(x)] [1] "1.2" "1.3" "2.3" > x[upper.tri(x,diag=TRUE)] [1

Re: [R] R source scripts

2014-12-01 Thread peter dalgaard
> On 01 Dec 2014, at 17:37 , Deniz Ağırdan wrote: > > Dear R Team, > > I have problem about finding R source scripts. I need script of > kmeans(stats) function. I would be grateful, if you helped me. > > I am looking forward to hearing from you. > @article{Rnews:Ligges:2006 , author = {Uwe

Re: [R] R source scripts

2014-12-01 Thread Sarah Goslee
Hi, On Mon, Dec 1, 2014 at 11:37 AM, Deniz Ağırdan wrote: > Dear R Team, > > I have problem about finding R source scripts. I need script of > kmeans(stats) function. I would be grateful, if you helped me. I assume you mean the source code rather than a script using that function. Google is your

[R] Creating submatrices from a dataframe, depending on factors in sample names

2014-12-01 Thread Tim Richter-Heitmann
Hello there, this is a cross-post of a stack-overflow question, which wasnt answered, but is very important for my work. Apologies for breaking any rules, but i do hope for some help from the list instead: I have a huge matrix of pairwise similarity percentages between different samples. The

[R] R source scripts

2014-12-01 Thread Deniz Ağırdan
Dear R Team, I have problem about finding R source scripts. I need script of kmeans(stats) function. I would be grateful, if you helped me. I am looking forward to hearing from you. Yours sincerely, Deniz Agirdan [[alternative HTML version deleted]] ___

Re: [R] please please unsubscribe!!!!!!!!!!!!!!!!

2014-12-01 Thread Martin Maechler
> Ranjan Maitra > on Mon, 1 Dec 2014 08:47:02 -0600 writes: > Well, we can start with the footer and then see how many "unsubscribe" messages continue to come R-help's way. Then, if it is not making an appreciable difference, we can look into putting it in the top. > Btw, I

Re: [R] Fwd: PLEASE HELP ON R-LANGUAGE

2014-12-01 Thread PIKAL Petr
Hm. What do you meen by "to run a non stationary time series data" http://cran.r-project.org/web/views/TimeSeries.html lead you to some packages for testing stationarity. Did you check them? Cheers Petr > -Original Message- > From: R-help [mailto:r-help-boun...@r-project.org] On Beha

Re: [R] Fwd: PLEASE HELP ON R-LANGUAGE

2014-12-01 Thread Boris Steipe
Daniel - a simple Google search for "r programme to run a non stationary time series data" turns up a large number of relevant hits, including a task view. What have you tried that did not work for you? B. On Dec 1, 2014, at 8:34 AM, Daniel James wrote: > Subject: PLEASE HELP ON R-LANGUAGE

[R] mixtools

2014-12-01 Thread ROBERTA BONÌ
Dear all, I am fitting data by the use of the normalizedEM algoritm in the mixtools package, but I don't know if it is possible to obtain as output the component (first or second) for each object. Regards Roberta Bonì [[alternative HTML version deleted]]

[R] Fwd: PLEASE HELP ON R-LANGUAGE

2014-12-01 Thread Daniel James
Subject: PLEASE HELP ON R-LANGUAGE I am writing my project on "The effect of Bootstrapping on Time Series Data". My problem is how I will write r programme to run a non stationary time series data. I am familia to r language already. Please help me. [[alternative HTML version deleted]]

Re: [R] please please unsubscribe!!!!!!!!!!!!!!!!

2014-12-01 Thread John Sorkin
Can the Gods of the mailing list please end this long email thread? All that needs to be done is to add an unsubscribe link to messages sent by the server. If this is technically feasible, please do it. If it is not let us know so we can get on to other issues! John John David Sorkin M.D., Ph.

Re: [R] please please unsubscribe!!!!!!!!!!!!!!!!

2014-12-01 Thread Ranjan Maitra
Well, we can start with the footer and then see how many "unsubscribe" messages continue to come R-help's way. Then, if it is not making an appreciable difference, we can look into putting it in the top. Btw, I have seen mailing list e-mails elsewhere with an unsubscribe line at the top. I don'

Re: [R] please please unsubscribe!!!!!!!!!!!!!!!!

2014-12-01 Thread Duncan Murdoch
On 01/12/2014 9:15 AM, Martin Maechler wrote: Thank you for all the thoughts about alleviating these problems, both to us and the "newbies" (or otherwise e-mail clueless subscribers). > Ranjan Maitra > on Sun, 30 Nov 2014 20:37:22 -0600 writes: > Following on Rich and Peter, i

Re: [R] rgl WebGL export

2014-12-01 Thread Duncan Murdoch
On 01/12/2014 4:26 AM, rh...@numberland.de wrote: Dear List members, I would be glad to get some tips on the following topic. I use rgl package to generate a 3D-cube with labeled dots at certain coordinates. After that I try to export the scene as a WebGL application. For this I use the syntax

Re: [R] please please unsubscribe!!!!!!!!!!!!!!!!

2014-12-01 Thread Jeff Newmiller
I disagree that this message belongs at the top... That is rare in bulk mail I receive, and seems unnecessarily intrusive. Addition of the word "Unsubscribe" to clarify the function of the link seems in line with current use. ---

Re: [R] please please unsubscribe!!!!!!!!!!!!!!!!

2014-12-01 Thread Martin Maechler
Thank you for all the thoughts about alleviating these problems, both to us and the "newbies" (or otherwise e-mail clueless subscribers). > Ranjan Maitra > on Sun, 30 Nov 2014 20:37:22 -0600 writes: > Following on Rich and Peter, is it practical for the list to put it at the top

[R] using win task to run Rscript somepackages can't work in script mode

2014-12-01 Thread PO SU
Dear expeRts,      These days i want to run a .R file contained a package called gmailr to do something about processing gmail , it works well in  interactive  GUI  ,that is ,Rstudio. But i want to run it by a windows task, so i need to run the .R file in Rscript mode, sadly, there seems differe

[R] rgl WebGL export

2014-12-01 Thread rhelp
Dear List members, I would be glad to get some tips on the following topic. I use rgl package to generate a 3D-cube with labeled dots at certain coordinates. After that I try to export the scene as a WebGL application. For this I use the syntax from rgl documentation "writeWebGL" mentioned in

Re: [R] please please unsubscribe!!!!!!!!!!!!!!!!

2014-12-01 Thread Rainer M Krug
Top post as new thought: I just searched the archives, and there are less then 1000 emails about unsubscribing since 2003. There are more then 70% (guess) which have nothing to do with unsubscription, and about 19 (plus this one) mails in this thread... Counting the poccurrance of "unsubscribe" i

[R] Cycling and different xerror values in cp of rpart, which result should I trust?...

2014-12-01 Thread Levent TERLEMEZ
Dear Users, Is it possible to get cycling and different xerror scores in cp of rpart while getting the same tree on every run (or am I missing something or understood wrong)? I build it with an old version of R in a Windows VM installed on a Intel based macbook and reuse the same codes with a ne

Re: [R] HELP

2014-12-01 Thread PIKAL Petr
Hi Your code is not reproducible. I found this http://rstudio-pubs-static.s3.amazonaws.com/1963_60f8740918d5416e8d54f07f48ce04fd.html which does ggplot with 2 axes. I did not went further as I do not see the point for two y axes in ggplot. Working directly with grid graphics objects is beyond