Re: [R] Overlapping grid in plot
Ok, here is some sample code to my problem barplot(c(1,2,4,3,2), legend.text = Legend) grid() ..the lines are crossing my barchart :-(... - Original Message - From: Duncan Murdoch [EMAIL PROTECTED] To: r-help@stat.math.ethz.ch Sent: Sunday, January 16, 2005 12:33 AM Subject: Re: [R] Overlapping grid in plot On Sat, 15 Jan 2005 23:02:25 +, Robin Gruna [EMAIL PROTECTED] wrote : Hi, I want to create a barchart plot with a grid. The grid is overlapping my plot and legend, looking not very nice. How can I put the grid into the background of my plot? You should show some sample code to illustrate the problem. There are several ways to draw a bar chart; how to fix yours depends on which one you used. Duncan Murdoch __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Centered variables and mixed-model
Martin Julien wrote: I work in biology and I use mixed-model for my data analysis In a scientific paper, the author wrote: All continuous exploratory variables were centred on their median value prior to inclusion in the analysis (Pinheiro Bates, 2000). They refer to the book Mixed-effects model in S and S-Plus by Pinheiro et Bates in 2000. I feel a bit strange with that paper because I can't find in the book why they centred the variables on their median. So I have two question: First, is it correct to centred the variables on their median in a mixed-model? Second, why they do that? Well I don't recall Pinheiro and Bates saying that variables needed to be centered on their median. It is often the case that the conditioning of the numerical optimization for obtaining parameter estimates is improved if explanatory variables are centered in some way but I don't know of a particular reason for centering on the median. Also, as Bert Gunter pointed out, this statement is about the explanatory variables and not a response variable. With any statistical model, centering of variables results in a reparameterization of the model and one must keep this in mind when performing statistical tests. __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Overlapping grid in plot
On Sun, 16 Jan 2005 10:05:01 +0100, Robin Gruna [EMAIL PROTECTED] wrote : Ok, here is some sample code to my problem barplot(c(1,2,4,3,2), legend.text = Legend) grid() ..the lines are crossing my barchart :-(... The reason for this is the way R thinks of graphics, essentially as ways to put ink on paper. You draw the grid on top of the existing plot. Getting it to look the way you want is a little tricky: you want to draw the grid first so the bars appear on top, but R won't know how to draw the grid until it has drawn the plot. So the solution is to draw the plot twice, e.g. barplot(c(1,2,4,3,2), legend.text = Legend) grid(col='black', lty='solid') oldpar - par(bg='white') # this says to use a solid white background # instead of the default one, which is usually transparent. The # old colour is saved in oldpar par(new=T) # this says to overwrite the plot barplot(c(1,2,4,3,2), legend.text = Legend) par(oldpar) # restore the old colour Duncan Murdoch __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] graphing of Princomp object
Tobias, Great, works like a charm! I'm already seeing all kinds of patterns that were invisible before. I appreciate your help. -Erik On 15/01/2005, at 16:30, Tobias Verbeke wrote: On Sat, 15 Jan 2005 15:53:18 +0100 List account [EMAIL PROTECTED] wrote: Thanks, Tobias for the response. I tried the suggestion you gave, and apparently (at least according to the biplot manpage, only the first two members of the col vector are used, the first to plot the first set of values, i.e. the scores, and the second color is used for the loadings (I think I have that right). At any rate, if I add the clause 'col = c(rep(red, 100), rep(blue, 17), rep(green, 62))' I just get a bunch of red points! :( You're right. I'm sorry I did not read ?biplot, but only checked it had a col argument (Semel in anno licet insanire..). Anyway, with PCA it is not a good idea to plot both variables and cases on one single plot, because the temptation is too great to interpret proximities between variables and cases. You'd better plot two different graphs, one for the cases and one for the `circle of correlations'. For plotting the cases, you could make up your own plot using something similar to this: library(MASS) # for eqscplot F1 - yourpca$score[,1] F2 - yourpca$score[,2] eqscplot(F1, F2, pch = 20) text(F1, F2, labels = names(F1), col = c(rep(red, 100), rep(blue, 17), rep(green, 62)), pos = 3) Tobias Si vales, valeo... -Erik __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Multiple plots in one screen
I'm a fairly new user of R and I'm confronted with a problem to which I can't find the solution in any R manual or FAQ. I'd like to plot multiple 'graphs' in one plot screen. For example, my data frame would be: x a b c 1111518 2261219 3221714 And I'd like to plot a, b and c against x at the same time in one plot screen. How is this done? Thanks! Robert Weenink [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Multiple plots in one screen
Robert Weenink [EMAIL PROTECTED] writes: I'm a fairly new user of R and I'm confronted with a problem to which I can't find the solution in any R manual or FAQ. I'd like to plot multiple 'graphs' in one plot screen. For example, my data frame would be: x a b c 1111518 2261219 3221714 And I'd like to plot a, b and c against x at the same time in one plot screen. How is this done? With matplot(). There are various possibilities, e.g. dd - read.table(stdin(),header=TRUE) 0: x a b c 1: 1111518 2: 2261219 3: 3221714 4: matplot(dd$x,dd[-1],type=b) (and you don't actually need the dd$x bit because it will plot against the index if no x is given). -- O__ Peter Dalgaard Blegdamsvej 3 c/ /'_ --- Dept. of Biostatistics 2200 Cph. N (*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918 ~~ - ([EMAIL PROTECTED]) FAX: (+45) 35327907 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] probabilty calculation in SVM
Raj: The references given on the help page will tell you. Best, David - Hi All, In package e1071 for SVM based classification, one can get a probability measure for each prediction. I like to know what is method that is used for calculating this probability. Is it calculated using logistic link function? Thanks for your help. Regards, Raj __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Overlapping grid in plot
On Sun, 2005-01-16 at 05:00 -0500, Duncan Murdoch wrote: On Sun, 16 Jan 2005 10:05:01 +0100, Robin Gruna [EMAIL PROTECTED] wrote : Ok, here is some sample code to my problem barplot(c(1,2,4,3,2), legend.text = Legend) grid() ..the lines are crossing my barchart :-(... The reason for this is the way R thinks of graphics, essentially as ways to put ink on paper. You draw the grid on top of the existing plot. Getting it to look the way you want is a little tricky: you want to draw the grid first so the bars appear on top, but R won't know how to draw the grid until it has drawn the plot. So the solution is to draw the plot twice, e.g. barplot(c(1,2,4,3,2), legend.text = Legend) grid(col='black', lty='solid') oldpar - par(bg='white') # this says to use a solid white background # instead of the default one, which is usually transparent. The # old colour is saved in oldpar par(new=T) # this says to overwrite the plot barplot(c(1,2,4,3,2), legend.text = Legend) par(oldpar) # restore the old colour You can also look at the barplot2() function, which is in the 'gregmisc' bundle on CRAN and take note of the 'plot.grid' argument, which will enable a grid to be drawn behind the bars. As an example: [after installing gregmisc] library(gplots) barplot2(c(1, 2, 4, 3, 2), legend.text = Legend, plot.grid = TRUE, grid.lty = solid) This will result in horizontal lines behind the bars at the same points as the y axis default tick marks. HTH, Marc Schwartz __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] CGIwithR
See below for the reply I sent you when you asked me this earlier today. David On 16 Jan 2005, at 20:22, ebashi wrote: Dear R users; I'm trying to use CGIwithR on a linux machine, I have followed the instructions on the package manual but still it does not run, the message that I get is as follows: The requested URL was not found on this server I used the example trivial, I put trivial.html under Web directory and trivial.R in cgi-bin directory, which itself is a subdirectory of Web directory, ( I have changed the modes of R.cgi and .Rprofile according to what package says) but i still get the same message, do you have any tips for me? my question is that where should for example myscript.R that is mentioned in the manual, be placed? (under Web directory or under cgi-bin). besides the path to R and GS, should anything else in the R.cgi be changed? many tanx in advance Sean __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html Dear Sean Thanks for your email. It is hard to diagnose your problem at a distance, but here is some general stuff: -- the trivial.html file needs to be in a place that is served by your http server (is that the URL that is not found? ie can you see the form in your browser? it wasn't clear to me from your email.) -- your web server needs to be configured to allow CGI scripts, and probably to specify one or more directories where such scripts are allowed to live. This is often a directory called cgi-bin; but note that it is not enough just to create a directory with that name, you must tell your webserver through its configuration file(s) that it exists and that CGI scripts placed there can be run. How this is done depends on which HTTP server you are running, and I cannot help you with that I'm afraid. -- the trivial.R, R.cgi and .Rprofile files all need to be in one of the places where CGI scripts are allowed (by your HTTP server) to live. I hope that helps. Good luck. best wishes, David __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] RWinEdt install problem
I cannot get the R button to appear in RWinEdt. I'm running R 2.0.1 under Windows XP. I did a clean install of the latest WinEdt. Previously (for an earlier installation of WinEdt) I had RWinEdt running OK. Now, even though I have the distributed RWinEdt_1.6-2.zip extracted to the right place in the R directory, and when I execute library(RWinEdt) in the R Console, when RWinEdt opens I do not have the R button on the toolbar. How do I fix this? In case it matters, note that I'm using a WinEdt User configuration (i.e., a directory that WinEdt refers to as %b) in addition to the main WinEdt directory (the one that WinEdt refers to as %B). -- Murray Eisenberg [EMAIL PROTECTED] Mathematics Statistics Dept. Lederle Graduate Research Tower phone 413 549-1020 (H) University of Massachusetts413 545-2859 (W) 710 North Pleasant Streetfax 413 545-1801 Amherst, MA 01003-9305 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Empirical cumulative distribution with censored data
Dear list, I would like to plot the empirical cumulative distribution of the time needed by a treatment to attain a certain goal. A number of experiments is run with a strict time limit. In some experiments the goal is attained before the time limit, in other experiments time expires before the goal is attained. The situation is very similar to survivial analysis with censored data. I tryed the function: plot(survfit(Surv(time),data=mydata,conf.int=F)) from the package survival. Nevertheless, what i would like to see is an increase of probability as time increases, and not a decrease of survival probabilty. I tried to play with ecdf(), but dealing with the censored data is quite hard-working in this case. Is there anything for censored data in ecdf like-functions or a way to adapt plot.survfit to my case? Thank you for consideration, Ragards, --- Marco Chiarandini, Fachgebiet Intellektik, Fachbereich Informatik, Technische Universität Darmstadt __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Empirical cumulative distribution with censored data
Marco Chiarandini [EMAIL PROTECTED] writes: Dear list, I would like to plot the empirical cumulative distribution of the time needed by a treatment to attain a certain goal. A number of experiments is run with a strict time limit. In some experiments the goal is attained before the time limit, in other experiments time expires before the goal is attained. The situation is very similar to survivial analysis with censored data. I tryed the function: plot(survfit(Surv(time),data=mydata,conf.int=F)) from the package survival. Nevertheless, what i would like to see is an increase of probability as time increases, and not a decrease of survival probabilty. I tried to play with ecdf(), but dealing with the censored data is quite hard-working in this case. Is there anything for censored data in ecdf like-functions or a way to adapt plot.survfit to my case? Did you try the fun=event argument? -- O__ Peter Dalgaard Blegdamsvej 3 c/ /'_ --- Dept. of Biostatistics 2200 Cph. N (*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918 ~~ - ([EMAIL PROTECTED]) FAX: (+45) 35327907 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Empirical cumulative distribution with censored data
Peter Dalgaard wrote: Marco Chiarandini [EMAIL PROTECTED] writes: Dear list, I would like to plot the empirical cumulative distribution of the time needed by a treatment to attain a certain goal. A number of experiments is run with a strict time limit. In some experiments the goal is attained before the time limit, in other experiments time expires before the goal is attained. The situation is very similar to survivial analysis with censored data. I tryed the function: plot(survfit(Surv(time),data=mydata,conf.int=F)) from the package survival. Nevertheless, what i would like to see is an increase of probability as time increases, and not a decrease of survival probabilty. I tried to play with ecdf(), but dealing with the censored data is quite hard-working in this case. Is there anything for censored data in ecdf like-functions or a way to adapt plot.survfit to my case? Did you try the fun=event argument? Now yes. It does what I want indeed. Thank you a lot! Marco __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] RWinEdt install problem
Murray Eisenberg wrote: I cannot get the R button to appear in RWinEdt. I'm running R 2.0.1 under Windows XP. I did a clean install of the latest WinEdt. Previously (for an earlier installation of WinEdt) I had RWinEdt running OK. Now, even though I have the distributed RWinEdt_1.6-2.zip extracted to the right place in the R directory, and when I execute library(RWinEdt) in the R Console, when RWinEdt opens I do not have the R button on the toolbar. How do I fix this? In case it matters, note that I'm using a WinEdt User configuration (i.e., a directory that WinEdt refers to as %b) in addition to the main WinEdt directory (the one that WinEdt refers to as %B). If you don't have write access to the WinEdt directory, you have to copy the R.ini file to, e.g., your local directory (%b), use the *manual* installation procedure as described in the ReadMe, but replace the command line args -e=R.ini by the full path specification, e.g.: -E=/path/to/%b/R.ini In a second (apparently private mail), you told that WinEdt ... 5.4 builds ... including the most recent one of 14 January 2005... do not work with the recent version of R-WinEdt, because 1. The first time, immediately I get a message that WinEdt.ini is corrupted and that a default copy (from the RWinEdt distribution I presume) is being used. Is this version also configured to use a User configuration? I don't have a WinEdt 5.4 version installed (still working with 5.2), but I will certainly take a look during the next one or two weeks. Uwe Ligges __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html