[R] transferring a graph from R into word

2013-10-01 Thread Charles Thuo
I have been copying graphs as bitmap image from R by right clicking on them and pasting on word. However this does not seem to be working any more. Is there another way. Charles [[alternative HTML version deleted]] __ R-help@r-project.org mail

[R] package:nlme unexpected varIdent behaviour

2013-10-01 Thread Sonya Odsen
I'm running R version 3.0.2 (2013-09-25) on a Windows computer. Here is a simplified version of my data: a <- expand.grid(SITE=c("A","B"),TREAT=c("low","med","high"), REP=c(1:5)) VAR <- round(rep(c(10,12,14,15,17,18),5)+rnorm(30)*2,1) dat <- cbind(a,VAR) I'm running a GAM on my data (package: mgc

Re: [R] [sm.density.compare] scale up y-axis and additional line type

2013-10-01 Thread Jim Lemon
On 10/02/2013 04:43 AM, Xianwen Chen wrote: Thanks Jim, The picture width is adjusted. That was great help! I really appreciate it. Does lwd mean 'line width'? I'm not exactly sure how that will help. Can you please explain the intuition behind it? Yes, "lwd" refers to line width. The combinat

[R] re-coding variables

2013-10-01 Thread Robert Lynch
I am running a large mixed model, 65k entries on 11 fixed effects and one random. One of the fixed effects is "Course" a factor that takes on 14 different values >levels(Master.complete$Course) [1] "B101" "B2A" "B2B" "B2C" "C118A" "C118B" "C118C" "C2A" "C2B" [10] "C2C" "N101" "P7A" "

Re: [R] barplot - easy for experienced, difficult for me

2013-10-01 Thread Jim Lemon
On 10/01/2013 07:32 PM, happyR wrote: hey lobachevsky - thanks! but: Error in barplot.default (matrix, col = c("yellow","purple"), beside = TRUE) : 'height' must be a vector or a matrix what to do? :) First, one must always avoid confusing the general case with a specific instance. If you

[R] Java requested System.exit(130)

2013-10-01 Thread Ed Siefker
I'm used to using ctrl-c to end operations without killing R. But I've used xlsx in this session, which loads Java, which apparently intercepts the ctrl-C. Accordingly, I hit ctrl-C, R died, and I lost a lot of work. I did some looking, and found a thread(http://comments.gmane.org/gmane.comp.lan

Re: [R] 'XML' package cannot be un-zipped or un-tar'd"

2013-10-01 Thread Rolf Turner
On 10/02/13 00:22, Steven Dwayne Randolph wrote: > R-help, > > There are several packages that have package 'XML' as a dependency. I > cannot get this package (XML) to extract or install. I have tried manually > downloaded to local machines (client PC and Linux), unsuccessful extraction. >

Re: [R] can no longer install packages on OSX

2013-10-01 Thread Duncan Murdoch
On 01/10/2013 2:05 PM, carlisle thacker wrote: R running on my MacPro under OS X 10.6.8 no longer installs packages. I would greatly appreciate help in sorting this out. Typically I get the messages like: > install.packages("party") Warning: unable to access index for repository http://software

Re: [R] can no longer install packages on OSX

2013-10-01 Thread Ista Zahn
On Tue, Oct 1, 2013 at 2:05 PM, carlisle thacker wrote: > R running on my MacPro under OS X 10.6.8 no longer installs packages. I > would greatly appreciate help in sorting this out. > > Typically I get the messages like: >> install.packages("party") > Warning: unable to access index for reposito

Re: [R] [sm.density.compare] scale up y-axis and additional line type

2013-10-01 Thread Xianwen Chen
Thanks Jim, The picture width is adjusted. That was great help! I really appreciate it. Does lwd mean 'line width'? I'm not exactly sure how that will help. Can you please explain the intuition behind it? Can I also ask another question? My graph is made from 7 plots from sm.density.compare(

[R] can no longer install packages on OSX

2013-10-01 Thread carlisle thacker
R running on my MacPro under OS X 10.6.8 no longer installs packages. I would greatly appreciate help in sorting this out. Typically I get the messages like: > install.packages("party") Warning: unable to access index for repository http://software.rc.fas.harvard.edu/mirrors/R/bin/macosx/leopard/

Re: [R] leveneTest - output

2013-10-01 Thread Rui Barradas
Hello, Just to add that the value 0.9829 [Pr(>F)] can be checked with pf(0.0173, df1 = 2, df2 = 7, lower.tail = FALSE) Rui Barradas Em 01-10-2013 19:02, John Fox escreveu: Dear Hermann, -Original Message- From: r-help-boun...@r-project.org [mailto:r-help-bounces@r- project.org] On B

Re: [R] Basic help on DF creation row by row

2013-10-01 Thread Rui Barradas
Hello, The main problem is in the way you form newRow. You can't mix data classes in a vector created with c(), so all its elements become characters, the least common denominator: newRow <- c("primitiveSpace", 1.1 , "mm2") newRow [1] "primitiveSpace" "1.1""mm2" Then when you rb

Re: [R] Basic help on DF creation row by row

2013-10-01 Thread arun
Hi, Not sure if this helps. deviceSummary <- data.frame(item = character(0) ,  value = numeric(0) , unit = character(0) ,stringsAsFactors=FALSE) newlst<-  list("primitiveSpace",1.1,"mm2") deviceSummary[nrow(deviceSummary)+1,]<- newlst newlst2<-  list("primitiveSpace",2.2,"mm2")  deviceSummary[n

[R] over dispersion plot

2013-10-01 Thread Sagan Friant
I want to show over dispersion in my data by plotting the variance against the mean for 8 groups. I used the following code to plot by type (parasite). scatterplot(variance~mean | parasite, reg.line=lm, smooth=FALSE, spread=FALSE, boxplots=FALSE, span=0.5, by.groups=TRUE, data=Disp2) I now want

Re: [R] Tex-mining in R

2013-10-01 Thread Ista Zahn
Do you know about task views? Try http://cran.r-project.org/web/views/NaturalLanguageProcessing.html Best, Ista On Tue, Oct 1, 2013 at 6:06 AM, umesh khatri wrote: > Can anyone please guide me on any useful links or resource regarding text > mining in R? > > -- > Regards > Umesh Khatri > >

Re: [R] leveneTest - output

2013-10-01 Thread John Fox
Dear Hermann, > -Original Message- > From: r-help-boun...@r-project.org [mailto:r-help-bounces@r- > project.org] On Behalf Of Hermann Norpois > Sent: Tuesday, October 01, 2013 8:07 AM > To: r-help > Subject: [R] leveneTest - output > > Hello, > > I have a question concerning the output o

[R] Question ANACOR-HELP

2013-10-01 Thread Matilde de Araújo e Sá Valente Rosa
Dear all, Sorry for bothering you but I am having a doubt for a long time and I cannot find a solution for it. I don't know if you can help me but I am doing a research study on Correspondence Analysis and I have been using the package ANACOR. After performing the Correspondence Analysis, I

[R] Save intermediate result in a same file

2013-10-01 Thread Matthew
Hello everybody, i have to save a 100 iteration computation in a file every 5 iterations until the end. I first give a vector A of 100 elements for the 100 iterations and i want to update A every 5 iterations. I use "save" but it doesn't work. Someone has an idea, i need a help Cheers. -

[R] 'XML' package cannot be un-zipped or un-tar'd"

2013-10-01 Thread Steven Dwayne Randolph
R-help, There are several packages that have package 'XML' as a dependency. I cannot get this package (XML) to extract or install. I have tried manually downloaded to local machines (client PC and Linux), unsuccessful extraction. How can this be compiled manually? How can a new version b

[R] Basic help on DF creation row by row

2013-10-01 Thread rolf . kemper
Dear Experts I'm very new to R and after some days or reading and testing I tried to make my first small application (and failed ...) In general I would like to work with sqldf , ggplot2 to create some graphical output. At present I got stuck with this: PROG ###

[R] Tex-mining in R

2013-10-01 Thread umesh khatri
Can anyone please guide me on any useful links or resource regarding text mining in R? -- Regards Umesh Khatri [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do rea

[R] leveneTest - output

2013-10-01 Thread Hermann Norpois
Hello, I have a question concerning the output of leveneTest. I don't understand the "7" in my output Levene's Test for Homogeneity of Variance (center = median) Df F value Pr(>F) group 2 0.0173 0.9829 7# Where does this number come from? Thanks. Hermann > res group.I

Re: [R] barplot - easy for experienced, difficult for me

2013-10-01 Thread happyR
hey lobachevsky - thanks! but: Error in barplot.default (matrix, col = c("yellow", "purple"), beside = TRUE) : 'height' must be a vector or a matrix what to do? :) Gesendet: Dienstag, 01. Oktober 2013 um 10:42 Uhr Von: "Jim Lemon [via R]"

Re: [R] glm's for a logistic regression - no warnings?

2013-10-01 Thread Xochitl CORMON
Le 01/10/2013 17:41, Dimitri Liakhovitski a écrit : Ah, thank you very much - I did not understand first brglm was the name of a package! Dimitri My bad! If there is separation you should see it in the way the coefficient diverges from one (it's pretty exponential). You can increase the numb

Re: [R] glm's for a logistic regression - no warnings?

2013-10-01 Thread Dimitri Liakhovitski
Ah, thank you very much - I did not understand first brglm was the name of a package! Dimitri On Tue, Oct 1, 2013 at 11:34 AM, Xochitl CORMON wrote: > > > > <>< <>< <>< <>< > > Xochitl CORMON > > Le 01/10/2013 17:29, Dimitri Liakhovitski a écrit : > >> Thank you very much, Bert - it's very helpf

Re: [R] glm's for a logistic regression - no warnings?

2013-10-01 Thread Xochitl CORMON
<>< <>< <>< <>< Xochitl CORMON Le 01/10/2013 17:29, Dimitri Liakhovitski a écrit : Thank you very much, Bert - it's very helpful. This post says that R issues a warning: Warning message: *glm.fit: fitted probabilities numerically 0 or 1 occurred * Actually the warning message should be so

Re: [R] glm's for a logistic regression - no warnings?

2013-10-01 Thread Dimitri Liakhovitski
Thank you very much, Bert - it's very helpful. This post says that R issues a warning: Warning message:*glm.fit: fitted probabilities numerically 0 or 1 occurred * However, in my case there is no warning. How could I detect complete separation in my data? I need to be able to flag it in my functi

Re: [R] Understanding classes in R

2013-10-01 Thread john doe
Thanks so much for your help everyone. This really helped me a lot. On Sun, Sep 29, 2013 at 11:42 PM, Barry Rowlingson < b.rowling...@lancaster.ac.uk> wrote: > On Sun, Sep 29, 2013 at 10:48 PM, john doe wrote: > > I am having trouble understanding how classes in R work. Here is a small > > re

Re: [R] glm's for a logistic regression - no warnings?

2013-10-01 Thread Xochitl CORMON
Hi, I did have warning messages about convergence issues using binomial GLM with logit link with my data in the past Do you detect separation using the function separation.detection{brglm}? Regards, Xochitl C. <>< <>< <>< <>< Xochitl CORMON +33 (0)3 21 99 56 84 Doctorante en sciences

Re: [R] glm's for a logistic regression - no warnings?

2013-10-01 Thread Bert Gunter
google "complete separation logistic" -- Bert On Tue, Oct 1, 2013 at 7:41 AM, Dimitri Liakhovitski wrote: > I have this weird data set with 2 predictors and one dependent variable - > attached. > > predictor1 has all zeros except for one 1. > I am runnning a simple logistic regression: > > temp<

[R] glm's for a logistic regression - no warnings?

2013-10-01 Thread Dimitri Liakhovitski
I have this weird data set with 2 predictors and one dependent variable - attached. predictor1 has all zeros except for one 1. I am runnning a simple logistic regression: temp<-read.csv("x data for reg224.csv") myreg <- glm(dv~predictor1+predictor2,data=temp, family=binomial("logit")

Re: [R] barplot - easy for experienced, difficult for me

2013-10-01 Thread John Kane
There is a slight problem with that second link. It is the same as the first. It is easier to sent the data (or a decent sample of it) in the email by using dput. Type ?dput for more information. Essentially you just do dput(myfile) copy it and paste it into the email. This allow the reader t

[R] A new book "Learning Regression Analysis by Simulation (Springer)"

2013-10-01 Thread Kunio Takezawa
Dear R-Users, A new book "Learning Regression Analysis by Simulation (Springer)" is out. http://www.springer.com/statistics/statistical+theory+and+methods/book/978-4-431-54320-6 http://www.amazon.de/Learning-Regression-Analysis-Simulation-Takezawa/dp/4431543201/ref=sr_1_1?ie=UTF8&qid=1380587

Re: [R] barplot - easy for experienced, difficult for me

2013-10-01 Thread Jim Lemon
On 10/01/2013 05:53 PM, happyR wrote: ... Do you think it might have sth to do with how my dataset is built up? Yes, happyR, it is definitely your dataset. I think this one is far superior: spineless<-matrix(c(6,3,9,5,4,6,7,1,3,8,7,6,10,4,3,7,6,11), nrow=2) slnames<-c("Bug","Slug","Wasp","Ti

Re: [R] barplot - easy for experienced, difficult for me

2013-10-01 Thread happyR
Hi Jean,   I tried to follow the introductions on statmethods... Didn't really work.   Do you think it might have sth to do with how my dataset is built up?   Thanks for your help!   Tobias       Gesendet: Montag, 30. September 2013 um 23:27 Uhr Von: "Adams, Jean [via R]" <