[R] multiple groups anova

2014-06-11 Thread Dragana Stanley
Hi All I have a matrix on which I want to do ANOVA between different Groups. My matrix looks something like this Sample GroupMes1 Mes2 Mes3 sample1Group1 10 0 5 sample2Group1 2 0 1 sample3Group1 2 0 1 sam

Re: [R] Average value in a particular range of a matrix

2014-06-11 Thread Rolf Turner
On 12/06/14 00:17, Pat-74100 wrote: Hi I have a matrix with values of size 1*500 i have to find the avg value of first 1 to 100 ,avg value of 100 - 200 and so on up to 400-500. is there any function to find the average of 1 -100 and 100 - 200, 200 - 300,300 - 400,400 - 500 ?? This looks v

[R] Average value in a particular range of a matrix

2014-06-11 Thread Pat-74100
Hi I have a matrix with values of size 1*500 i have to find the avg value of first 1 to 100 ,avg value of 100 - 200 and so on up to 400-500. is there any function to find the average of 1 -100 and 100 - 200, 200 - 300,300 - 400,400 - 500 ?? Thanks

[R] install.packages problem with R 3.1.0 on a multiuser linux system

2014-06-11 Thread eugene
Hello R users. I have a problem with R installation on one of my systems: install.packages returns different errors. Here is an example: * ~# /share/apps/r/3.1.0/bin/R R version 3.1.0 (2014-04-10) -- "Spring Dance" Copyrigh

Re: [R] Error clmm(){ordinal}

2014-06-11 Thread adesgroux
Dear Rune, Thanks for your script using drop1()! It worked well! Now I know I have significant effects for my predictors. Best regards Aurore -- View this message in context: http://r.789695.n4.nabble.com/Error-clmm-ordinal-tp4691592p4691969.html Sent from the R help mailing list archive at N

[R] Help using Rwinsteps

2014-06-11 Thread El Samuels, Ph.D.
Does anyone have experience using Rwinsteps? I think my issue could be resolved simply by someone with experience using it guiding me on it. Falling back to understand it through simple examples, I used the example code on page 12 of the manual (http://cran.r-project.org/web/packages/Rwinsteps/Rw

Re: [R] Standard Deviation in R

2014-06-11 Thread Greg Snow
The help page ?sd (I only checked version 3.1.0) has as the 1st sentence in the details section: "Like ‘var’ this uses denominator n - 1." and on the help page ?var in the details section (though down in the 3rd paragraph from the end) there is this sentence: "The denominator n - 1 is used which gi

Re: [R] Recurrent analysis survival analysis data format question

2014-06-11 Thread bgreen
Hello Chris, Thanks. This is not as straight forward as it seems. Given an index release date, I have dates of prior and subsequent imprisonment, offending that results in re-incarceration and hospital admission dates, pre and post. There are some additional complexities, such as people released

Re: [R] plot in package psych with function error.bars.by

2014-06-11 Thread William Revelle
Tham and Jim, The Mac version of psych_1.4.6.11 is now on the personalty.project.org/r server repository. The PC version is at personality-project/r/src/contrib/ as a zip file: psych_1.4.6.11.zip For a Mac, just set your other repository to personalty.project.org/r and install the sourc

Re: [R] rbind multiple data sets (.csv)

2014-06-11 Thread arun
Hi, If your working directory is "data 3" which has only two folders C1 and C2. May be this helps: lsF1 <- list.files(recursive=TRUE) lst1 <- lapply(split(lsF1,gsub(".*\\_(\\d+)\\..*","\\1",lsF1)),function(x) do.call(rbind,lapply(x,function(y) read.csv(y, header=TRUE A.K. Hello, I am tryi

Re: [R] Pulling data based on the quater

2014-06-11 Thread arun
Hi, Please Check ?as.yearqtr() fromlibrary(zoo) dat <- read.table(text="ID  Phase RESEARCH Area   Date Result 100   IV S_Care A&P 7/23/2013 Positive 1001   IV P_Care EU 12/20/2012 Positive 2001   IV Car    AS 9/13/2012 Positive 20003   III Spec IN 10/6/2011

Re: [R] Recurrent analysis survival analysis data format question

2014-06-11 Thread Andrews, Chris
Hi John, That must be in Canada, where everyone is a thug, unlike here in the US. :-) But seriously, you make a good point. I guess it depends on what the event variable is: commission of a new crime, start of a new sentence, reincarceration after a period of freedom, etc. (and what data Bob h

Re: [R] Recurrent analysis survival analysis data format question

2014-06-11 Thread John Kane
Hi Chris, Why would you not consider the person at risk for re incarceration if he is currently imprisoned? Symantically I'd agree, he or she is already behind bars. But from the point of view of extra sentences it is quite possible to commit an offence while in prision and recieve another se

Re: [R] Rgl: set trackball behavior

2014-06-11 Thread Duncan Murdoch
On 11/06/2014, 5:02 AM, Céline b wrote: > I would like to set zoom mouse control in rgl in order to redraw the map > with more or less details depending of the zoom coefficient (such as google > maps or openstreetmap do). > > I already tried the rgl.setMouseCallbacks(button, begin = NULL, updat

[R] R function for Step-wise Panel Regression

2014-06-11 Thread Nitin Jain
Hi, Can anyone please suggest if it's possible to do a step-wise panel regression in R ? Thanks, Nitin [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do

Re: [R] Standard Deviation in R

2014-06-11 Thread arun
Hi Bob, You may check: library(multicon) ?popsd() sd(1:3) #[1] 1  popsd(1:3) #[1] 0.8164966  sd(1:3)*sqrt(2/3) #[1] 0.8164966 A.K. The formula I generally use to compute the standard deviation is the square root of the variance where the variance is E(X^2) - (E(x))^2. That is, the divisor is

[R] Rgl: set trackball behavior

2014-06-11 Thread Céline b
I would like to set zoom mouse control in rgl in order to redraw the map with more or less details depending of the zoom coefficient (such as google maps or openstreetmap do). I already tried the rgl.setMouseCallbacks(button, begin = NULL, update = NULL, end = NULL) function but this function

Re: [R] r internet connection is very slow

2014-06-11 Thread Aidan Corcoran
Appreciate your thoughts on this Uwe. If I make any progress with it I will post back. On Wed, Jun 11, 2014 at 1:43 AM, Uwe Ligges wrote: > > > On 10.06.2014 16:32, Aidan Corcoran wrote: > >> thanks Uwe. I have tried a few mirrors, it makes no difference. >> I don't have lots of packages, as it

Re: [R] aov + pairwise.t.test: only selected pairs

2014-06-11 Thread ONKELINX, Thierry
Have a look at the multcomp package. The examples in glht() demonstrate how to specify the required contrasts. Best regards, ir. Thierry Onkelinx Instituut voor natuur- en bosonderzoek / Research Institute for Nature and Forest team Biometrie & Kwaliteitszorg / team Biometrics & Quality Assuran

[R] aov + pairwise.t.test: only selected pairs

2014-06-11 Thread Andreas Maunz
Hi, I have a 1-way anova result and want to do a post test. I want to do pairwise t-tests where the global variance is taken into account (i.e. a real post test on the anova result, not multiple simple t tests on the samples). I understand I should use pairwise.t.test() for that. However, it doe