Re: [R] logging messages
On Mon, 15 Nov 2004, Faber Fedor wrote: Hi all, I'm trying to learn R from an non-statistician's POV. I've got a statistician who uses R, but I'm the schmuck who has to integrate his R functions into an automated process. Defining a POV (undefined, as is `schmuck') as `not something' is really non-communication. Please do read the R posting guide and its references, and try to formulate questions in standard (and polite) English. Also, check the correct list to use as described in that posting guide -- R-help is not intended for questions involving programming concepts (like `syslog', which needs explanation even there). One of the things I would really like is the ability to log messages to file, specifically using syslog on a Linux box. (I also want to write messages to STDOUT based on a command-line flag, but I figure that can't be too hard to figure out. If it is too hard to figure out, you'll be seeing another message from me shortly. :-) It's not clear what you mean by this. If you mean send warnings and messages to stdout (what is `STDOUT'?) then `why?' You deal with this the same way as any other Linux application that uses stderr for warning/error messages. To `tee' output, see ?sink, or indeed `man tee'. R is principally an interactive program used for exploration. You haven't told us what you are trying to do, and you may be better off embedding R in some other front end to give you more control. -- Brian D. Ripley, [EMAIL PROTECTED] Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ University of Oxford, Tel: +44 1865 272861 (self) 1 South Parks Road, +44 1865 272866 (PA) Oxford OX1 3TG, UKFax: +44 1865 272595 __ [EMAIL PROTECTED] 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] Pairwise Distances -- How to vectorize the loop
Hi From what you write it seems to me a work for outer(). Did you try it? Cheers Petr On 15 Nov 2004 at 22:26, Timothy W. Victor wrote: R-List, I'm trying to compute pairwise distances among pairs of observations, which each pair containing data from 2 groups. There are more than 10 unique pairs. I have programmed a distance function that has three parameters, a vector of covariates from the ith observation in Group 1, a vector of covarites from the jth observation in Group 2, and a weighting matrix. I have used expand.grid to create a matrix containing all possible pairs of Keys (unique identifiers) from Group 1 and Group 2 and a placeholder for each pairwise distance in an effort to pre-allocate memory. The data containing the covariates are currently in a matrix that looks like: x1 x2 x3 ... xn Key Group where x1,...,xn are the covariates of interest. The Key values correspond to the row number. I'm trying to figure out a way to calculate all of the distances by vectorizing a loop. I'm trying to avoid the nested-loop paradigm. I'm sure I'm missing something quite obvious. Any insights would be appreciated. Best, Tim __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html Petr Pikal [EMAIL PROTECTED] __ [EMAIL PROTECTED] 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] Adding mean and SEM in Hmisc ecdf
Dear R Gurus, Sorry if this has been asked before but I did not find it in the archives. I would like to add a horizontal display of mean and SEM on Hmisc ecdf plots done by group (ie variate~treatment). Has anyone written some code to do that ? Thanks and kind regards, Jean-Louis __ [EMAIL PROTECTED] 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] how can draw probability density plot?
I hope this is the direct operation you are looking for: curve(dnorm(x),from=-3,to=3) Best regards, Ales Ziberna - Original Message - From: LONG Yu [EMAIL PROTECTED] To: [EMAIL PROTECTED] Sent: Monday, November 15, 2004 1:26 PM Subject: [R] how can draw probability density plot? Dear support, I want to draw a probability density plot in R. For example, I provide the mean and variance of a normal distribution, then R can provide me the probability density plot. Now I always generate random numbers of normal distribution and calculate their dnorm(mu, var), finally plot them. I am eager to know some directly operation. Thank you for your attention. I am looking forward to hearing from you soon. Best regards, Long Yu __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ [EMAIL PROTECTED] 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] question about AIC
Hi everybody, we are a pool of phd students and we have a question about AIC. We are interested in calculating the AIC for a mixture model on galaxies data. So far we have found AIC works only for regression models, whereas we need AIC for a mixture of Normal with mean, sd and weights given by our EM algorithm. May you help us? thanks in advance __ Tiscali Adsl 2 Mega Free: naviga gratis tutto l'anno! Supera tutti i limiti di velocita' con Tiscali Adsl 2 Mega Free. Sei libero da costi fissi e, se ti abboni entro il 25 novembre, navighi gratis fino al 31 dicembre 2004 e non paghi il costo di adesione. http://abbonati.tiscali.it/adsl/ __ [EMAIL PROTECTED] 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] From S-Plus to R?
Dear collegues, I am using S-Plus for many years and is thinking of moving to R. In the FAQ I did not manage to find an answer to the following questions: Is it easy to move and transform functions, written under S-plus to functions under R? Furthermore, S-Plus has interesting functions to deal with regular and irregular times series (rts, its, ts.plot, ts.lines, ts.points, aggregate.rts, etc..) and the possibility to plot, on the same graphic, regular time series with different frequencies and even irregular time series. Is it still possible in R? Thanks in advance for your answers. Best wishes Isabelle Braud *** Isabelle BRAUD Chargée de recherche au LTHE-Grenoble/CEMAGREF-Lyon CEMAGREF Unité de Recherche Hydrologie-Hydraulique 3 bis, Quai Chauveau, CP 220 69336 Lyon Cedex 9 Tel: 04 72 20 87 78 (from abroad 33 4 72 20 87 78) Fax: 04 78 47 78 75 (from abroad 33 4 78 47 78 75) E-mail: [EMAIL PROTECTED] ou [EMAIL PROTECTED] __ [EMAIL PROTECTED] 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] Multivariate Sampling
Dear Ales, I have found a matlab routine which does latin hypercube sampling with random distributions. It seem to be quite straightforward to transform it to R. If you or anybody else is interested - and it works - I am happy to send the R version to him. The method is from Iman and Conover and allows inducing rank correlation among input variables, like you can do with @Risk, e.g. quite easily. Many thanks and best regards, Stefan I do not belive (although I am not an expert) that such a pacake exist in R. You might try sampling first one variable and then the other conditional on the previous one? I hope it helps; Ales Ziberna - Original Message - From: [EMAIL PROTECTED] To: [EMAIL PROTECTED] Sent: Monday, November 15, 2004 4:49 PM Subject: [R] Multivariate Sampling Dear all, I am looking for routines which allow multi-variate sampling from non-normal distributions (loglogistic) given correlations among the variables. Unfortunately, I could not find a suitable package for R. Does anybody know one? Many thanks and best regards, Stefan Albrecht [[alternative HTML version deleted]] __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html [[alternative HTML version deleted]] __ [EMAIL PROTECTED] 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] question about AIC
On Tue, 16 Nov 2004 [EMAIL PROTECTED] wrote: we are a pool of phd students and we have a question about AIC. We are interested in calculating the AIC for a mixture model on galaxies data. So far we have found AIC works only for regression models, whereas we need AIC for a mixture of Normal with mean, sd and weights given by our EM algorithm. What is the problem? The concept AIC or the function AIC()? If the concept, it was originally developed in the area of AR(p) time series models, using asymptotic theory for MLEs, and you need to check that the concepts apply to your situation (the original papers do not). Note there are some fundamental problems here: the likelihood for a mixture of normals is unbounded, the MLE corresponding to degenerate (zero-variance) components. And AIC is about maximized likelihoods, with maxima in the interior of the space. So you need to take some professional statistical advice about the concepts. -- Brian D. Ripley, [EMAIL PROTECTED] Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ University of Oxford, Tel: +44 1865 272861 (self) 1 South Parks Road, +44 1865 272866 (PA) Oxford OX1 3TG, UKFax: +44 1865 272595 __ [EMAIL PROTECTED] 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] question about AIC
did you try google? e.g., with key word: `AIC mixture models'. Moreover, look at package `flexmix' (i.e., help(package=flexmix)) whose usage is illustrated in a recent article in JSS: http://www.jstatsoft.org/v11/i08/v11i08.pdf I hope it helps. Best, Dimitris Dimitris Rizopoulos Ph.D. Student Biostatistical Centre School of Public Health Catholic University of Leuven Address: Kapucijnenvoer 35, Leuven, Belgium Tel: +32/16/396887 Fax: +32/16/337015 Web: http://www.med.kuleuven.ac.be/biostat http://www.student.kuleuven.ac.be/~m0390867/dimitris.htm - Original Message - From: [EMAIL PROTECTED] To: [EMAIL PROTECTED] Sent: Tuesday, November 16, 2004 10:12 AM Subject: [R] question about AIC Hi everybody, we are a pool of phd students and we have a question about AIC. We are interested in calculating the AIC for a mixture model on galaxies data. So far we have found AIC works only for regression models, whereas we need AIC for a mixture of Normal with mean, sd and weights given by our EM algorithm. May you help us? thanks in advance __ Tiscali Adsl 2 Mega Free: naviga gratis tutto l'anno! Supera tutti i limiti di velocita' con Tiscali Adsl 2 Mega Free. Sei libero da costi fissi e, se ti abboni entro il 25 novembre, navighi gratis fino al 31 dicembre 2004 e non paghi il costo di adesione. http://abbonati.tiscali.it/adsl/ __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ [EMAIL PROTECTED] 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] From S-Plus to R
Dear Isabelle, for most of my work I have switched from S-Plus to R, because it is easier to make scripts with due to the better documentation and some other more reasonable implementations. And there was also a cost issue with the S-Plus Server, which is not for free at all. In R I use the its package for time series, which is quite sufficient for my needs. The only problem I encountered was with computing time. So I use R matrixes as long as possible and not the its (S4) objects, since this makes some commands very slow (like union). There are also other packages like zoo, tsseries (I guess) and certainly Rmetrics, which should have all you need Most functions transform directely and easily. Among others, I missed the numRows() and numCols() etc in R, but this can be redone quickly. One big advantage of S-Plus is the possibility to edit graphics and to make Powerpoints presentations very quickly. Also the Excel interface is already build in. In R you must always programm to whole picture, which is ok if you are doing the same task often. Best regards, Stefan --- Dr. Stefan Albrecht, CFA Allianz Private Equity Partners GmbH Giselastrasse 4 D-80802 Munich, Germany Phone +49.89.38 00 - 18 317 Fax +49.89.38 00 - 818 317 Dear collegues, I am using S-Plus for many years and is thinking of moving to R. In the FAQ I did not manage to find an answer to the following questions: Is it easy to move and transform functions, written under S-plus to functions under R? Furthermore, S-Plus has interesting functions to deal with regular and irregular times series (rts, its, ts.plot, ts.lines, ts.points, aggregate.rts, etc..) and the possibility to plot, on the same graphic, regular time series with different frequencies and even irregular time series. Is it still possible in R? Thanks in advance for your answers. Best wishes Isabelle Braud *** Isabelle BRAUD Chargée de recherche au LTHE-Grenoble/CEMAGREF-Lyon CEMAGREF Unité de Recherche Hydrologie-Hydraulique 3 bis, Quai Chauveau, CP 220 69336 Lyon Cedex 9 Tel: 04 72 20 87 78 (from abroad 33 4 72 20 87 78) Fax: 04 78 47 78 75 (from abroad 33 4 78 47 78 75) E-mail: braud at lyon.cemagref.fr ou Isabelle.Braud at hmg.inpg.fr [[alternative HTML version deleted]] __ [EMAIL PROTECTED] 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] UML programming
hello, I'd like to know if it is possible to use R in a UML way by creating classes, methods,etc... If yes, can you please give me links for documentation and example ? thanks Accédez au courrier électronique de La Poste : www.laposte.net ; 3615 LAPOSTENET (0,34/mn) ; tél : 08 92 68 13 50 (0,34/mn) [[alternative HTML version deleted]] __ [EMAIL PROTECTED] 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] question about AIC
I would also mention the mixreg package on CRAN. Regards m. ** Massimiliano Marinucci http://personales.ya.com/max_mar/ Ph.D Candidate in Economics Fundamentos del Analisis Económico II (Economía Cuantitativa) Facultad de CC.EE. Universidad Complutense Madrid Campus de Somosaguas Madrid - Spain ** - Original Message - From: Dimitris Rizopoulos [EMAIL PROTECTED] To: [EMAIL PROTECTED] Cc: [EMAIL PROTECTED] Sent: Tuesday, November 16, 2004 10:35 AM Subject: Re: [R] question about AIC did you try google? e.g., with key word: `AIC mixture models'. Moreover, look at package `flexmix' (i.e., help(package=flexmix)) whose usage is illustrated in a recent article in JSS: http://www.jstatsoft.org/v11/i08/v11i08.pdf I hope it helps. Best, Dimitris Dimitris Rizopoulos Ph.D. Student Biostatistical Centre School of Public Health Catholic University of Leuven Address: Kapucijnenvoer 35, Leuven, Belgium Tel: +32/16/396887 Fax: +32/16/337015 Web: http://www.med.kuleuven.ac.be/biostat http://www.student.kuleuven.ac.be/~m0390867/dimitris.htm - Original Message - From: [EMAIL PROTECTED] To: [EMAIL PROTECTED] Sent: Tuesday, November 16, 2004 10:12 AM Subject: [R] question about AIC Hi everybody, we are a pool of phd students and we have a question about AIC. We are interested in calculating the AIC for a mixture model on galaxies data. So far we have found AIC works only for regression models, whereas we need AIC for a mixture of Normal with mean, sd and weights given by our EM algorithm. May you help us? thanks in advance __ Tiscali Adsl 2 Mega Free: naviga gratis tutto l'anno! Supera tutti i limiti di velocita' con Tiscali Adsl 2 Mega Free. Sei libero da costi fissi e, se ti abboni entro il 25 novembre, navighi gratis fino al 31 dicembre 2004 e non paghi il costo di adesione. http://abbonati.tiscali.it/adsl/ __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ [EMAIL PROTECTED] 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] UML programming
Sure, you could do it in a UML way. But I know of no tools yet that will, and more importantly, the object-orientation style (generic functions, i.e. similar to CLOS) isn't the easiest to use in that way. On Tue, 16 Nov 2004 11:03:28 +0100, wayne [EMAIL PROTECTED] wrote: hello, I'd like to know if it is possible to use R in a UML way by creating classes, methods,etc... If yes, can you please give me links for documentation and example ? thanks Accdez au courrier lectronique de La Poste : www.laposte.net ; 3615 LAPOSTENET (0,34/mn) ; tl : 08 92 68 13 50 (0,34/mn) [[alternative HTML version deleted]] __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- best, -tony --- A.J. Rossini [EMAIL PROTECTED] __ [EMAIL PROTECTED] 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] How to remove x, y labels from a plot
try : plot(rnorm(20),rnorm(20),axes=F,xlab=,ylab=) Selon [EMAIL PROTECTED]: Hi there, I need to plot an illustrative figure without ticks, x, y labels in R. I managed to get the ticks removed, but had no luck with x, y labels. Any suggestions would be much appreciated. Jin Li [[alternative HTML version deleted]] __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ [EMAIL PROTECTED] 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] How to remove x, y labels from a plot
Hi Jin Li, does plot( 1:100, rnorm(100), ann=FALSE, xaxt=n, yaxt=n ) produce what you want? Arne On Tuesday 16 November 2004 13:06, [EMAIL PROTECTED] wrote: Hi there, I need to plot an illustrative figure without ticks, x, y labels in R. I managed to get the ticks removed, but had no luck with x, y labels. Any suggestions would be much appreciated. Jin Li [[alternative HTML version deleted]] __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- Arne Henningsen Department of Agricultural Economics University of Kiel Olshausenstr. 40 D-24098 Kiel (Germany) Tel: +49-431-880 4445 Fax: +49-431-880 1397 [EMAIL PROTECTED] http://www.uni-kiel.de/agrarpol/ahenningsen/ __ [EMAIL PROTECTED] 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] Barplot difficulties
Heather J. Branton wrote: Hello. I am an R newbie struggling to learn and use R . I have read many portions of the R Reference Manual, as well as the FAQs. Given that I learn something new each time, I know I might be missing something obvious. But I appeal to your good nature to help me through this initial problem. I have attached a pdf file to demonstrate what I desire and have listed what my data looks like in Excel (below). Following is the data and script I developed - which does not provide what I want. Dear Heather - Please read Bill Cleveland's book The Elements of Graphing Data. A MUCH better plot can be produced. And let time be one of the first variables to vary. -- Frank E Harrell Jr Professor and Chair School of Medicine Department of Biostatistics Vanderbilt University __ [EMAIL PROTECTED] 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] Adding mean and SEM in Hmisc ecdf
Jean-Louis Abitbol wrote: Dear R Gurus, Sorry if this has been asked before but I did not find it in the archives. I would like to add a horizontal display of mean and SEM on Hmisc ecdf plots done by group (ie variate~treatment). Has anyone written some code to do that ? Thanks and kind regards, Jean-Louis It is customary to show quantiles on ecdfs, and the functions make that easy. You can add other points or reference lines to an existing plot easily if using the non-lattice ecdf. To do it with the lattice version ecdf.formula you will have to change its default panel function. -- Frank E Harrell Jr Professor and Chair School of Medicine Department of Biostatistics Vanderbilt University __ [EMAIL PROTECTED] 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] violinplot options
Hi, I am using the function vioplot() to generate violin plots. Now I would like to add a label to the y axix and a title to the diagram. Just setting ylab didnt work. Is it possible to set such options for the function ? I tried also with the function simple.violinplot, but also with this I couldnt set the options. Kind Regards Tanja __ [EMAIL PROTECTED] 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] Simple plot() question
Hi First a simple question to do with plot(). How do I change the x-axis labels on a plot? For example, I am plotting each row of a matrix, and I want each row to be a line on my graph. Simple really. Eg: plot(sg[1,], type=l) When I do this, the x-axis is labelled 1:38, as I have 38 columns in my matrix. When I do: plot(sg[1,order(sg[1,])], type=l) Ideally I would like the x-axis labels to reflect the new order of the columns, but they're still numbered 1:38... I've read the plot() docs and the par() docs and can't figure it out - I know I'm missing something obvious, but what? Cheers Mick Michael Watson Head of Informatics Institute for Animal Health, Compton Laboratory, Compton, Newbury, Berkshire RG20 7NN UK Phone : +44 (0)1635 578411 ext. 2535 Mobile: +44 (0)7990 827831 E-mail: [EMAIL PROTECTED] __ [EMAIL PROTECTED] 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] Difference between two correlation matrices
Hi Now a more theoretical question. I have two correlation matrices - one of a set of variables under a particular condition, the other of the same set of variables under a different condition. Is there a statistical test I can use to see if these correlation matrices are different? Thanks Mick __ [EMAIL PROTECTED] 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] Simple plot() question
michael watson (IAH-C) wrote: Hi First a simple question to do with plot(). How do I change the x-axis labels on a plot? For example, I am plotting each row of a matrix, and I want each row to be a line on my graph. Simple really. Eg: plot(sg[1,], type=l) When I do this, the x-axis is labelled 1:38, as I have 38 columns in my matrix. When I do: plot(sg[1,order(sg[1,])], type=l) Ideally I would like the x-axis labels to reflect the new order of the columns, but they're still numbered 1:38... I've read the plot() docs and the par() docs and can't figure it out - I know I'm missing something obvious, but what? You want to add xaxt=n so the x-axis labels are not printed. Then add your new labels using axis(1, at=1:38, labels=some vector of label names) HTH, Jim Cheers Mick Michael Watson Head of Informatics Institute for Animal Health, Compton Laboratory, Compton, Newbury, Berkshire RG20 7NN UK Phone : +44 (0)1635 578411 ext. 2535 Mobile: +44 (0)7990 827831 E-mail: [EMAIL PROTECTED] __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- James W. MacDonald Affymetrix and cDNA Microarray Core University of Michigan Cancer Center 1500 E. Medical Center Drive 7410 CCGC Ann Arbor MI 48109 __ [EMAIL PROTECTED] 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] Simple plot() question
try something like plot(..., axes=FALSE) axis(2); axis(1, labels=c(your labels)) Best, Dimitris Dimitris Rizopoulos Ph.D. Student Biostatistical Centre School of Public Health Catholic University of Leuven Address: Kapucijnenvoer 35, Leuven, Belgium Tel: +32/16/396887 Fax: +32/16/337015 Web: http://www.med.kuleuven.ac.be/biostat http://www.student.kuleuven.ac.be/~m0390867/dimitris.htm - Original Message - From: michael watson (IAH-C) [EMAIL PROTECTED] To: [EMAIL PROTECTED] Sent: Tuesday, November 16, 2004 3:45 PM Subject: [R] Simple plot() question Hi First a simple question to do with plot(). How do I change the x-axis labels on a plot? For example, I am plotting each row of a matrix, and I want each row to be a line on my graph. Simple really. Eg: plot(sg[1,], type=l) When I do this, the x-axis is labelled 1:38, as I have 38 columns in my matrix. When I do: plot(sg[1,order(sg[1,])], type=l) Ideally I would like the x-axis labels to reflect the new order of the columns, but they're still numbered 1:38... I've read the plot() docs and the par() docs and can't figure it out - I know I'm missing something obvious, but what? Cheers Mick Michael Watson Head of Informatics Institute for Animal Health, Compton Laboratory, Compton, Newbury, Berkshire RG20 7NN UK Phone : +44 (0)1635 578411 ext. 2535 Mobile: +44 (0)7990 827831 E-mail: [EMAIL PROTECTED] __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ [EMAIL PROTECTED] 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] Simple plot() question
Hi Mick: I'm a little unsure if this is what you are after but does this do it? foo.mat - matrix(rnorm(100), nrow = 10, ncol = 10) plot(foo.mat[1,], type=l, xlab = Crud, ylab = More Crud) plot(foo.mat[1,order(foo.mat[1,])], type=l, xaxt = n, xlab = Crud, ylab = More Crud) axis(1, at=1:length(foo.mat[1,]), labels= order(foo.mat[1,])) Seems like a barplot might be a nice way to go too: barplot(foo.mat[1,order(foo.mat[1,])], names.arg = order(foo.mat[1,])) A reproducible example would help the list see what you are after as I might be totally off on this. HTH, Andy -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] Behalf Of michael watson (IAH-C) Sent: Tuesday, November 16, 2004 9:45 AM To: [EMAIL PROTECTED] Subject: [R] Simple plot() question Hi First a simple question to do with plot(). How do I change the x-axis labels on a plot? For example, I am plotting each row of a matrix, and I want each row to be a line on my graph. Simple really. Eg: plot(sg[1,], type=l) When I do this, the x-axis is labelled 1:38, as I have 38 columns in my matrix. When I do: plot(sg[1,order(sg[1,])], type=l) Ideally I would like the x-axis labels to reflect the new order of the columns, but they're still numbered 1:38... I've read the plot() docs and the par() docs and can't figure it out - I know I'm missing something obvious, but what? Cheers Mick Michael Watson Head of Informatics Institute for Animal Health, Compton Laboratory, Compton, Newbury, Berkshire RG20 7NN UK Phone : +44 (0)1635 578411 ext. 2535 Mobile: +44 (0)7990 827831 E-mail: [EMAIL PROTECTED] __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ [EMAIL PROTECTED] 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] Difference between two correlation matrices
Hello, I don't know if it is applicable in your case, but have you tried Mantel test? You can use it to determine significant correlation between two matrices, using Pearsion, Spearman or Kendal correlation indices. Hope it helps, All the best, Marta - Original Message - From: michael watson (IAH-C) [EMAIL PROTECTED] To: [EMAIL PROTECTED] Sent: Tuesday, November 16, 2004 2:49 PM Subject: [R] Difference between two correlation matrices Hi Now a more theoretical question. I have two correlation matrices - one of a set of variables under a particular condition, the other of the same set of variables under a different condition. Is there a statistical test I can use to see if these correlation matrices are different? Thanks Mick __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ [EMAIL PROTECTED] 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] deleting a file
Dear all, I have a very simple question. Simple, that is, if you know the answer. I wish to delete a file in a given directory after having first checked its existence. I issue the following commands path-'c:example/R/' Thus creating the directory. indicator-length(grep(filename,path)) If indicator is greater than zero then the file exists. Now I wish to remove this file. However, I would like to make the code compatible for Linux/Windows and Macs. In Linux I would issue the command system('rm paste(path,'filename',sep='')') and this works just fine. It does not however work for windows, and I have no idea whether it would work on a mac. Is there a single command thay escapes me? Best Wishes Roger Gill __ [EMAIL PROTECTED] 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] deleting a file
In Linux I would issue the command system('rm paste(path,'filename',sep='')') and this works just fine. It does not however work for windows, and I have no idea whether it would work on a mac. Is there a single command thay escapes me? Yes. help(file.remove) __ [EMAIL PROTECTED] 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] memory allocation
Dear sirs, I'm using the Splancs package to compute standard errors of the estimates of a spatio-temporal k function. When I use as spatial and temporal distances too long vectors (respectively 60 and 80 entries) for a dataset of 1000 observations, R gives me the message Error: cannot allocate vector of size 18 Kb Reached total allocation of 512 Mb. I ran the function memory.size() and obtained 39200 more or less. Can anyone help me? Thanks in advance. Massimiliano Copetti -- Massimiliano Copetti, PhD Student Institute of Quantitative Methods L.Bocconi University Viale Isonzo 25 20135 Milano (Italy) http://www.unibocconi.it http://spazioinwind.libero.it/maxcop78 __ [EMAIL PROTECTED] 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] User package - Simple Ports
R experts, I created a package X for R 1.8 that I want to re-install for 2.0.1. In addition to downloading/installing Perl and Rtools as directed in the README.packages file and ensuring that they appear in my path, I have modified X's DESCRIPTION file to include all required fields. Additionally I have deleted the built line since the make process will add that. The source contains no Fortran/C/C++ and resides in . R/rw2000/src/library From .R/rw2000/src/gnuwin32 make X -X seems to run the make utility, but the package is never installed. In R 1.8 manually added the build line and copied the package directory into the library tree and library(X) worked without a formal install (As you would guess this was a work-around for my earlier and evidently persistent lack of success in my package installation endeavors.). The same work-around approach seems not to work with 2.0. Your suggestions are appreciated. Thank you! Keith Sabol [[alternative HTML version deleted]] __ [EMAIL PROTECTED] 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] deleting a file
You may be interested in one of dir.create(), file.exists(), or unlink(). -roger Roger Gill wrote: Dear all, I have a very simple question. Simple, that is, if you know the answer. I wish to delete a file in a given directory after having first checked its existence. I issue the following commands path-'c:example/R/' Thus creating the directory. indicator-length(grep(filename,path)) If indicator is greater than zero then the file exists. Now I wish to remove this file. However, I would like to make the code compatible for Linux/Windows and Macs. In Linux I would issue the command system('rm paste(path,'filename',sep='')') and this works just fine. It does not however work for windows, and I have no idea whether it would work on a mac. Is there a single command thay escapes me? Best Wishes Roger Gill __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- Roger D. Peng http://www.biostat.jhsph.edu/~rpeng/ __ [EMAIL PROTECTED] 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] Difference between two correlation matrices
One solution is to use procruste analysis. Perform a principal coordinate analysis on your data (cmdscale) to obtain two individuals by variables tables. Then, you can perform procruste rotation and test to know if the two matrice tell the same thing. It is more powerful than mantel test. As you have correlations, I suppose than you can consider your original variables rather than correlation and cmdscale Functions are available in the ade4 package: procuste(ade4) Simple Procruste Rotation between two sets of points procuste.randtest(ade4) Monte-Carlo Test on the sum of the singular values of a procustean rotation (in C). procuste.rtest(ade4)Monte-Carlo Test on the sum of the singular values of a procustean rotation (in R). A reference on the analysis: http://www.steph280.freesurf.fr/files/articles/Ecosci2003.pdfS. Dray, D. Chessel, J. Thioulouse : Procrustean co-inertia analysis for the linking of ecological tables. Ecosciencehttp://www.steph280.freesurf.fr/files/articles/Ecosci2003.pdf, 2003, vol. 10, 110-119. available at : http://www.steph280.freesurf.fr/files/articles/Ecosci2003.pdf Hope this helps ! At 10:31 16/11/2004, Marta Rufino wrote: Hello, I don't know if it is applicable in your case, but have you tried Mantel test? You can use it to determine significant correlation between two matrices, using Pearsion, Spearman or Kendal correlation indices. Hope it helps, All the best, Marta - Original Message - From: michael watson (IAH-C) [EMAIL PROTECTED] To: [EMAIL PROTECTED] Sent: Tuesday, November 16, 2004 2:49 PM Subject: [R] Difference between two correlation matrices Hi Now a more theoretical question. I have two correlation matrices - one of a set of variables under a particular condition, the other of the same set of variables under a different condition. Is there a statistical test I can use to see if these correlation matrices are different? Thanks Mick __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html Stéphane DRAY -- Département des Sciences Biologiques Université de Montréal, C.P. 6128, succursale centre-ville Montréal, Québec H3C 3J7, Canada Tel : (514) 343-6111 poste 1233 Fax : (514) 343-2293 E-mail : [EMAIL PROTECTED] -- Web http://www.steph280.freesurf.fr/ __ [EMAIL PROTECTED] 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] Rggobi-color maps and colors
Hello, I was wondering if the function get(set)ColorMap.ggobi() is working for anyone.. The function is not defined when I tried to work on it. Also, I would really like to know, if I can increase the number of colors in any of the color scheme, if possible. We only got 12 colors (maximum?) to look at the clusters, but what if I got as many as 25 clusters.. How do people look at many clusters? Any help is appreciated. Thank you Sincerely Aruna __ [EMAIL PROTECTED] 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] Fourier analysis
Dear colegues, Is there any function in R for calculating the four coefficients of each harmonic in fourier analysis, from a set of x,y coordinates is given? Is it possible to do Fourier analysis? Has anyone done contour analysis using R? Any help wil be apretiated, Thank you very much, All the best, Marta __ [EMAIL PROTECTED] 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] memory allocation
There is more to that message you have not reproduced. I am pretty sure you are on Windows, and you need to read the rw-FAQ (as the posting guide asks you too). See Q2.7. On Tue, 16 Nov 2004, Massimiliano Copetti wrote: I'm using the Splancs package to compute standard errors of the estimates of a spatio-temporal k function. When I use as spatial and temporal distances too long vectors (respectively 60 and 80 entries) for a dataset of 1000 observations, R gives me the message Error: cannot allocate vector of size 18 Kb Reached total allocation of 512 Mb. I ran the function memory.size() and obtained 39200 more or less. Yes, but see its help page for the relevant usage. -- Brian D. Ripley, [EMAIL PROTECTED] Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ University of Oxford, Tel: +44 1865 272861 (self) 1 South Parks Road, +44 1865 272866 (PA) Oxford OX1 3TG, UKFax: +44 1865 272595 __ [EMAIL PROTECTED] 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] deleting a file
On Tue, 16 Nov 2004 15:43:12 - Roger Gill wrote: Dear all, I have a very simple question. Simple, that is, if you know the answer. Yes, look at ?file.remove Z I wish to delete a file in a given directory after having first checked its existence. I issue the following commands path-'c:example/R/' Thus creating the directory. indicator-length(grep(filename,path)) If indicator is greater than zero then the file exists. Now I wish to remove this file. However, I would like to make the code compatible for Linux/Windows and Macs. In Linux I would issue the command system('rm paste(path,'filename',sep='')') and this works just fine. It does not however work for windows, and I have no idea whether it would work on a mac. Is there a single command thay escapes me? Best Wishes Roger Gill __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ [EMAIL PROTECTED] 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] Changing zeros to NAs in a data frame
Dear R People: I have a data frame with some columns that are numeric and some which are factors. There are zeros in the numeric columns and I would like to change them to NAs. However, there are zeros in some of the factor columns, and I would like them to be left alone. Is there a global way to do this, please? I was thinking about use the results from str but am not sure. R Version 2.0.0 Windows. Thanks in advance. Sincerely, Laura Holt mailto: [EMAIL PROTECTED] Security. http://clinic.mcafee.com/clinic/ibuy/campaign.asp?cid=3963 __ [EMAIL PROTECTED] 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] R 2.0.0 Installation Problem
I and my students have been having an odd problem with this release, which is that packages are disappearing. After installation the package is found with the library command, but later in the same session or in a later session, the library command returns a not found error. Then later it is back. Happening on both Windows and OS X, mostly but not entirely with Bioconductor packages. David --- | David M. Rocke, Professor Phone: (530) 752-0510 | | Division of Biostatistics (Medicine) and(530) 752-7368 | | Department of Applied Science (Engineering) | | Co-Director of IDAV FAX:(530) 752-8894 | | University of California, Davis E-mail: [EMAIL PROTECTED] | | Davis, CA 95616-8553 www.cipic.ucdavis.edu/~dmrocke | __ [EMAIL PROTECTED] 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] changing character to a vector name
Dear R People: I would like to generate a vector/variable name from within a loop to be passed to a table function. This is what I have so far: assign(p1,paste(raw3.df$,rw2$V1[3],sep=)) p1 [1] raw3.df$CITIZEN Essentially, I want to use the raw3.df$CITIZEN along with another value to generate a table. However, I'm stuck here. I know this is incredibly stupid. Thanks in advance. Sincerely Laura Holt mailto: [EMAIL PROTECTED] __ [EMAIL PROTECTED] 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] R: Changing zeros to NAs in a data frame
Hi, see this example. I hope I helped you a little bit. Bye Vito dati X YZ 1 10 0 0 2 0 20 60 3 30 40 50 4 11 12 3 dati[dati==0]-NA dati X YZ 1 10 NA 0 2 NA 20 60 3 30 40 50 4 11 12 3 = Diventare costruttori di soluzioni Became solutions' constructors The business of the statistician is to catalyze the scientific learning process. George E. P. Box Visitate il portale http://www.modugno.it/ e in particolare la sezione su Palese http://www.modugno.it/archivio/cat_palese.shtml __ [EMAIL PROTECTED] 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 on EM Algorithm for bivariate normal
Hi, I woul like to know if it is possible to have a R code to generate EM Algorithm for a normal bivariate mixture. Best regard, S.F. __ [EMAIL PROTECTED] 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] Please help using SQL with R SQL Server
I cannot get a database connection in R to my MS SQL Server database. In S-Plus 6.2 I have used the following successfully: rawdata - importData(type=DIRECT-SQL, user=xfl2, password=xfl2, server=rinnycs0059, database=xf, table=, sqlQuery=select * from testTbl) In R I have tried both DBI and RSQLite, but have not had any luck. It always says cannot find driver. All the examples use My SQL or some other program. I only have SQL Server by Microsoft. I know R might not have a native driver, but I have tried ODBC, too, without luck. If anyone can give me an example and hints on finding the driver that would be great! Thanks. Roger ** * This message is for the named person's use only. It may contain confidential, proprietary or legally privileged information. No right to confidential or privileged treatment of this message is waived or lost by any error in transmission. If you have received this message in error, please immediately notify the sender by e-mail, delete the message and all copies from your system and destroy any hard copies. You must not, directly or indirectly, use, disclose, distribute, print or copy any part of this message if you are not the intended recipient. __ [EMAIL PROTECTED] 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] Changing zeros to NAs in a data frame
Laura Holt wrote: Dear R People: I have a data frame with some columns that are numeric and some which are factors. There are zeros in the numeric columns and I would like to change them to NAs. However, there are zeros in some of the factor columns, and I would like them to be left alone. Is there a global way to do this, please? I was thinking about use the results from str but am not sure. R Version 2.0.0 Windows. Let x be your data.frame. Then use: is.num - sapply(x, is.numeric) x[is.num] - lapply(x[is.num], function(y) ifelse(y == 0, NA, y)) HTH, --sundar __ [EMAIL PROTECTED] 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] memory allocation
On Tue, 16 Nov 2004, Massimiliano Copetti wrote: Dear sirs, I'm using the Splancs package to compute standard errors of the estimates of a spatio-temporal k function. When I use as spatial and temporal distances too long vectors (respectively 60 and 80 entries) for a dataset of 1000 observations, R gives me the message The memory demands arise in stvmat() called inside stsecal(), in which an (s*tm)*(s*tm) numeric matrix is allocated, described in the code as a full spacetime variance/covariance matrix, and which is necessarily large. In your case 2304 elements are used of 8 bytes each, so to do this in the way you describe you need more RAM - the matrix may be copied as well. The authors of the package and the underlying method did not anticipate needing this high degree of spatial and temporal resolution. Roger Bivand Error: cannot allocate vector of size 18 Kb Reached total allocation of 512 Mb. I ran the function memory.size() and obtained 39200 more or less. Can anyone help me? Thanks in advance. Massimiliano Copetti -- Roger Bivand Economic Geography Section, Department of Economics, Norwegian School of Economics and Business Administration, Breiviksveien 40, N-5045 Bergen, Norway. voice: +47 55 95 93 55; fax +47 55 95 93 93 e-mail: [EMAIL PROTECTED] __ [EMAIL PROTECTED] 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] Changing zeros to NAs in a data frame
This isn't pretty but it's a way to do it: foo - data.frame(x = c(1,0,1,1,0,2,4), y = as.factor(c(0,2,1,1,0,3,1))) Zero2NA - function(x){ if(is.numeric(x)) { x[x == 0] - NA; } return(x) } foo2 - as.data.frame(lapply(foo, Zero2NA)) foo foo2 HTH, Andy -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] Behalf Of Laura Holt Sent: Tuesday, November 16, 2004 11:31 AM To: [EMAIL PROTECTED] Subject: [R] Changing zeros to NAs in a data frame Dear R People: I have a data frame with some columns that are numeric and some which are factors. There are zeros in the numeric columns and I would like to change them to NAs. However, there are zeros in some of the factor columns, and I would like them to be left alone. Is there a global way to do this, please? I was thinking about use the results from str but am not sure. R Version 2.0.0 Windows. Thanks in advance. Sincerely, Laura Holt mailto: [EMAIL PROTECTED] Security. http://clinic.mcafee.com/clinic/ibuy/campaign.asp?cid=3963 __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ [EMAIL PROTECTED] 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] R help
Hi, I was wondering as to how I could convert SPSS data imported to R into tabular form. In the sense, direct usage of read.table( ) doesnt help. Thanks - Meet the all-new My Yahoo! Try it today! [[alternative HTML version deleted]] __ [EMAIL PROTECTED] 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] Changing zeros to NAs in a data frame
On Tue, 16 Nov 2004, Laura Holt wrote: Dear R People: I have a data frame with some columns that are numeric and some which are factors. There are zeros in the numeric columns and I would like to change them to NAs. However, there are zeros in some of the factor columns, and I would like them to be left alone. Is there a global way to do this, please? I was thinking about use the results from str but am not sure. myDF - data.frame(a=0:4, b=letters[1:5], c=-2:2) myDF[] - lapply(myDF, function(x) if(is.numeric(x)) {x[x==0] - NA; x} else x) myDF a b c 1 NA a -2 2 1 b -1 3 2 c NA 4 3 d 1 5 4 e 2 -- Brian D. Ripley, [EMAIL PROTECTED] Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ University of Oxford, Tel: +44 1865 272861 (self) 1 South Parks Road, +44 1865 272866 (PA) Oxford OX1 3TG, UKFax: +44 1865 272595 __ [EMAIL PROTECTED] 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] help on EM Algorithm for bivariate normal
take a look at: flexmix mixreg mclust packages on CRAN You may also define your own M-step in some of these packages... EM is used to find the parameters of the mixture. Ciao M. ** Massimiliano Marinucci http://personales.ya.com/max_mar/ Ph.D Candidate in Economics Fundamentos del Analisis Económico II (Economía Cuantitativa) Facultad de CC.EE. Universidad Complutense Madrid Campus de Somosaguas Madrid - Spain ** - Original Message - From: [EMAIL PROTECTED] To: [EMAIL PROTECTED] Sent: Tuesday, November 16, 2004 6:22 PM Subject: [R] help on EM Algorithm for bivariate normal Hi, I woul like to know if it is possible to have a R code to generate EM Algorithm for a normal bivariate mixture. Best regard, S.F. __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ [EMAIL PROTECTED] 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] User package - Simple Ports
If I'm not mistaken, I believe you need to do make pkg-X or R CMD INSTALL X Andy From: Keith J Sabol R experts, I created a package X for R 1.8 that I want to re-install for 2.0.1. In addition to downloading/installing Perl and Rtools as directed in the README.packages file and ensuring that they appear in my path, I have modified X's DESCRIPTION file to include all required fields. Additionally I have deleted the built line since the make process will add that. The source contains no Fortran/C/C++ and resides in . R/rw2000/src/library From .R/rw2000/src/gnuwin32 make X -X seems to run the make utility, but the package is never installed. In R 1.8 manually added the build line and copied the package directory into the library tree and library(X) worked without a formal install (As you would guess this was a work-around for my earlier and evidently persistent lack of success in my package installation endeavors.). The same work-around approach seems not to work with 2.0. Your suggestions are appreciated. Thank you! Keith Sabol [[alternative HTML version deleted]] __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ [EMAIL PROTECTED] 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] R help
I don't understand your question. PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html;. In particular, have you read the R Data Import / Export documentation that some with R [available, from www.r-project.org - Manuals or R - help.start()]? Have you tried read.spss in library(foreign)? [help(package=foreign) provides additional documentation.] If you've tried all these without satisfaction, please explain what you've tried, the error message, the version of R, operating system, etc., as requested in the posting guide. hope this helps. spencer graves gauri wrote: Hi, I was wondering as to how I could convert SPSS data imported to R into tabular form. In the sense, direct usage of read.table( ) doesnt help. Thanks - Meet the all-new My Yahoo! Try it today! [[alternative HTML version deleted]] __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- Spencer Graves, PhD, Senior Development Engineer O: (408)938-4420; mobile: (408)655-4567 __ [EMAIL PROTECTED] 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] problems with compiling a package
Hello, I am trying to compile packages for R2.0.0 patch in a win XP machine. Most of the packages compile without problems, with C or FTG or only R. Now some packeges give the following error which I do not understand how to correct ... preparing package xxx for lazy loading Error in names - .default('*tmp*',value=c(R,Platform,Date, : names attribute[4] must be the same length as the vector [3] Execution halted make: *** [lazyload] Error 1 Can somebody tell me how I can correct this error? One other question, this npreparing package for lazy loading does not occur for all packages, although their DESCRIPTION and folders are similar, When does a package goes to lazy loading and when it does not? Thanks Heberto Ghezzo McGill U Montreal - Canada __ [EMAIL PROTECTED] 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] help on EM Algorithm for bivariate normal
The three packages that someone else mentioned in response to your post flexmix mixreg mclust may be usefule in real applications. On the other hand, if your interest is in teaching EM or developing your own EM by using a simple example, the most recent issue of The American Statistician has an article with a sample R code for the purpose. Right now I'm away from my journal. But if you would want further info, let me know and I can find it for you. Tim Liao Original message Date: Tue, 16 Nov 2004 18:22:07 +0100 From: [EMAIL PROTECTED] Subject: [R] help on EM Algorithm for bivariate normal To: [EMAIL PROTECTED] Hi, I woul like to know if it is possible to have a R code to generate EM Algorithm for a normal bivariate mixture. Best regard, S.F. __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R- project.org/posting-guide.html __ [EMAIL PROTECTED] 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] problems with compiling a package
On Tue, 16 Nov 2004 [EMAIL PROTECTED] wrote: Hello, I am trying to compile packages for R2.0.0 patch in a win XP machine. What exactly is `R2.0.0 patch'? If you mean 2.0.0 patched, it has a date, and the date is crucial. Most of the packages compile without problems, with C or FTG or only R. Now some packeges give the following error which I do not understand how to correct ... preparing package xxx for lazy loading Error in names - .default('*tmp*',value=c(R,Platform,Date, : names attribute[4] must be the same length as the vector [3] Execution halted make: *** [lazyload] Error 1 Can somebody tell me how I can correct this error? My guess is that this comes from tools:::.split_description which has if(!is.na(Built - db[Built])) { Built - as.list(strsplit(Built, ; )[[1]]) names(Built) - c(R, Platform, Date, OStype) Built[[R]] - package_version(sub(^R ([0-9.]+), \\1, Built[[R]])) } else Built - NULL so probably your DESCRIPTION file is faulty. Did you have a Built: line in it that you put there yourself? I can reproduce this by doing so. If so, `Writing R Extensions' does say There should be no @samp{Built} or @samp{Packaged} fields, as these are added by the package management tools. and R CMD check on such package throws an immediate error. One other question, this npreparing package for lazy loading does not occur for all packages, although their DESCRIPTION and folders are similar, When does a package goes to lazy loading and when it does not? Please do read the NEWS (or ONEWS) file! It says in the first 20 lines Packages are by default installed using lazy loading if they have more than 25Kb of R code and did not use a saved image. -- Brian D. Ripley, [EMAIL PROTECTED] Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ University of Oxford, Tel: +44 1865 272861 (self) 1 South Parks Road, +44 1865 272866 (PA) Oxford OX1 3TG, UKFax: +44 1865 272595 __ [EMAIL PROTECTED] 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] changing character to a vector name
Laura Holt lauraholt_983 at hotmail.com writes: . I would like to generate a vector/variable name from within a loop to be . passed to a table . function. . . This is what I have so far: . assign(p1,paste(raw3.df$,rw2$V1[3],sep=)) . p1 . [1] raw3.df$CITIZEN . . Essentially, I want to use the raw3.df$CITIZEN along with another value to . generate a table. You can use eval and parse to parse and execute arbitrary R commands that you construct from strings. The exec function below is a one statement convenience function that pastes its arguments together and executes them this way in its parent's environment. (Sometimes when one gets complex requirements like this if one backs up a bit one discovers that the requirements can be simplified and you might consider whether that is the case here in which case you might be able to disregard all this.) R ### create some test data ### R data(iris) R irish - head(iris) R irish Sepal.Length Sepal.Width Petal.Length Petal.Width Species 1 5.1 3.5 1.4 0.2 setosa 2 4.9 3.0 1.4 0.2 setosa 3 4.7 3.2 1.3 0.2 setosa 4 4.6 3.1 1.5 0.2 setosa 5 5.0 3.6 1.4 0.2 setosa 6 5.4 3.9 1.7 0.4 setosa R ### this is the actual processing ### R exec - function(...) eval.parent(parse(text = paste(..., collapse = ))) R exec(irish$Sepal.Length, -, irish$Sepal.Length, +1) R irish Sepal.Length Sepal.Width Petal.Length Petal.Width Species 1 6.1 3.5 1.4 0.2 setosa 2 5.9 3.0 1.4 0.2 setosa 3 5.7 3.2 1.3 0.2 setosa 4 5.6 3.1 1.5 0.2 setosa 5 6.0 3.6 1.4 0.2 setosa 6 6.4 3.9 1.7 0.4 setosa __ [EMAIL PROTECTED] 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] problems with compiling a package
r.ghezzo at staff.mcgill.ca writes: : One other question, this npreparing package for lazy loading does not occur for : all packages, although their DESCRIPTION and folders are similar, When does a : package goes to lazy loading and when it does not? You can use LazyLoad: no in the DESCRIPTION file to prevent lazy loading. Alternately you can use the --no-lazy switch on R CMD install __ [EMAIL PROTECTED] 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] Difference between two correlation matrices
If you have the data that created the correlation matrices, then you can do a permutation test. The first question to ask is, What does 'different' mean? Some choices include: max(abs(cor1 - cor2)) max(abs(eigen(cor1 - cor2)$values)) Once you have decided what metric makes most sense, you can perform the test. First pool all of the data (if you think that there are different means in the two conditions, then remove the means within each group before pooling). Then perform a number of random allocations of the pooled data into two groups with the number in each group equal to the original numbers. The test compares your statistic using the original correlation matrices to the distribution of statistics of the correlations from the random allocations. Patrick Burns Burns Statistics [EMAIL PROTECTED] +44 (0)20 8525 0696 http://www.burns-stat.com (home of S Poetry and A Guide for the Unwilling S User) michael watson (IAH-C) wrote: Hi Now a more theoretical question. I have two correlation matrices - one of a set of variables under a particular condition, the other of the same set of variables under a different condition. Is there a statistical test I can use to see if these correlation matrices are different? Thanks Mick __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ [EMAIL PROTECTED] 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] gcrma package
Hi ! I would like to understand where do affinity.spline.coefs used in function compute.affinities come from ? library(gcrma) data(affinity.spline.coefs) affinity.spline.coefs X1 X2 X3 X4 X5 X1 -0.55004171 -0.58579091 -0.08870557 -0.47774242 0.23205570 0.58002746 X2 X3 X4 X5 X1 X2 0.61274425 0.10294309 0.57388808 -0.28334367 0.01350914 -0.02030805 X3 X4 X5 -0.14747469 0.05436463 -0.10124882 Thank you in advance! Julie AUBERT [[alternative HTML version deleted]] __ [EMAIL PROTECTED] 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] CDs for R?
Hi Folks, I'm sure I'm speaking for more than a few (though possibly a minority) here. There's something of a hidden assumption that R users can readily download whatever they need from CRAN. Some of us are on narrow bandwidth dialup connections, so downloading large quantities of stuff is out of the question (e.g. at approx. 5min/MB, it would take over 2 days to download a single CD). The meat of CRAN (including contributed packages and documentation) is enough to fill 5 CDs, though one individual probably wouldn't be interested in all of that. (And, before anyone asks, no I won't be seeing broadband in the foreseeable future!) I've worked round this in various ways in the past. Some Linux distributions (e.g. RedHat, SuSE) come with the basics of R on their CDs, so when I've upgraded Linux I've got a new R (though not the latest). Linux Emporium once obligingly did me a custom CD very cheaply with the contributed packages. A friend with high-bandwidth access did me the 5 CDs in return for a pub lunch. And so on. One can get round it by bothering someone. What I'd like to suggest, for consideration, is that along with the stirling work done at many centres to set up and maintain mirrors of CRAN, some might consider offering also the service of burning CDs on request, for a reasonable charge. The difficulty, of course, is that it's going to take someone's time om something which may well not be their proper business. (I'm prompted to think about this again by the emergence of R-2 - 2.0.1 - one day soon? - 2.1. This is clearly a major advance in R and changes several things, so I'm looking at a major download operation, if not by me then by somebody that I can get CDs from, if I'm to be sure of being up to date on everything I'd like to have. And I'm sure I'm not the only one.) I'd be interested in people's comments on this proposal. Best wishes to all, Ted. E-Mail: (Ted Harding) [EMAIL PROTECTED] Fax-to-email: +44 (0)870 094 0861 [NB: New number!] Date: 16-Nov-04 Time: 21:39:14 -- XFMail -- __ [EMAIL PROTECTED] 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] deleting a file
Achim Zeileis wrote: On Tue, 16 Nov 2004 15:43:12 - Roger Gill wrote: Dear all, I have a very simple question. Simple, that is, if you know the answer. Yes, look at ?file.remove Z ... and file.path() in order to specify the location in an OS independent way. Uwe Ligges I wish to delete a file in a given directory after having first checked its existence. I issue the following commands path-'c:example/R/' Thus creating the directory. indicator-length(grep(filename,path)) If indicator is greater than zero then the file exists. Now I wish to remove this file. However, I would like to make the code compatible for Linux/Windows and Macs. In Linux I would issue the command system('rm paste(path,'filename',sep='')') and this works just fine. It does not however work for windows, and I have no idea whether it would work on a mac. Is there a single command thay escapes me? Best Wishes Roger Gill __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ [EMAIL PROTECTED] 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] gcrma package
This question is more for the BioConductor mailing list. If you type in library(gcrma) help(affinity.spline.coefs) at the command prompt, it suggests you to see compute.affinities. Doing a help(compute.affinities), you will see under References section : Hekstra, D., Taussig, A. R., Magnasco, M., and Naef, F. (2003) Absolute mRNA concentrations from sequence-specific calibration of oligonucleotide array. Nucleic Acids Research, 31. 1962-1968. On Tue, 2004-11-16 at 16:55, [EMAIL PROTECTED] wrote: Hi ! I would like to understand where do affinity.spline.coefs used in function compute.affinities come from ? library(gcrma) data(affinity.spline.coefs) affinity.spline.coefs X1 X2 X3 X4 X5 X1 -0.55004171 -0.58579091 -0.08870557 -0.47774242 0.23205570 0.58002746 X2 X3 X4 X5 X1 X2 0.61274425 0.10294309 0.57388808 -0.28334367 0.01350914 -0.02030805 X3 X4 X5 -0.14747469 0.05436463 -0.10124882 Thank you in advance! Julie AUBERT [[alternative HTML version deleted]] __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- Adaikalavan Ramasamy[EMAIL PROTECTED] Centre for Statistics in Medicine http://www.ihs.ox.ac.uk/csm/ Cancer Research UK Tel : 01865 226 677 Old Road Campus, Headington, Oxford Fax : 01865 226 962 __ [EMAIL PROTECTED] 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] How to remove x, y labels from a plot
Hi Arne, It works. It produced what I wanted. y-rnorm(1000, 2, 0) plot(density(y), ylab=Abundance of species, xlab=Environmental gradient, main= , lty=2, col=4, xaxt=n, yaxt=n) Thanks, Arne. And also thanks to other responses. Regards, Jin -Original Message- From: Arne Henningsen [mailto:[EMAIL PROTECTED] Sent: Tuesday, 16 November 2004 10:33 P To: [EMAIL PROTECTED] Cc: Li, Jin (CSE, Atherton) Subject: Re: [R] How to remove x, y labels from a plot Hi Jin Li, does plot( 1:100, rnorm(100), ann=FALSE, xaxt=n, yaxt=n ) produce what you want? Arne On Tuesday 16 November 2004 13:06, [EMAIL PROTECTED] wrote: Hi there, I need to plot an illustrative figure without ticks, x, y labels in R. I managed to get the ticks removed, but had no luck with x, y labels. Any suggestions would be much appreciated. Jin Li [[alternative HTML version deleted]] __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- Arne Henningsen Department of Agricultural Economics University of Kiel Olshausenstr. 40 D-24098 Kiel (Germany) Tel: +49-431-880 4445 Fax: +49-431-880 1397 [EMAIL PROTECTED] http://www.uni-kiel.de/agrarpol/ahenningsen/ __ [EMAIL PROTECTED] 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] CDs for R?
(Ted Harding) [EMAIL PROTECTED] writes: [...] There's something of a hidden assumption that R users can readily download whatever they need from CRAN. [...] What I'd like to suggest, for consideration, is that along with the stirling work done at many centres to set up and maintain mirrors of CRAN, some might consider offering also the service of burning CDs on request, for a reasonable charge. The difficulty, of course, is that it's going to take someone's time om something which may well not be their proper business. I have been in a similar situation a fair bit in the past and understand your position. Now I'm back in the UK and have a reasonably fast broadband connection at home I'd be willing to help out now and then. I guess that to make this work more generally we would need to work out how to make sure that only the CDs get burned and not the prospective customer or supplier. As for charges, I think I'd only be interested in covering costs of the CDs and postage. I don't have industrial strength hardware so I could not get into mass production. Perhaps we could establish informal groups of R buddies where, for example, I help you and a small number of other people out each time there is an update and we establish some kind of trust between ourselves, rather than new people coming to me each time. People could sign up to be suppliers and be allocated or choose a group of people they provide the service to. I would feel comfortable with something like this working for people who have been on the R-help list for a while and have some recgonised identity, and something to lose in terms of reputation if they take advantage. But, it is possible that new users might need it the most and, by definition, we might not feel comfortable dealing with new people. Dave -- David Whiting University of Newcastle upon Tyne, UK __ [EMAIL PROTECTED] 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] CDs for R?
There was a similar thread earlier this year http://tolstoy.newcastle.edu.au/R/help/04/03/1785.html I think I previously made the suggestion that you could download this from an internet cafe. I am not sure if these cafes allow you to plug in your own laptop or burn it for you. If you have a DVD readable CDROM and a DVD writer, you could opt for that. Failing that, you could see if someone in your local R-group or university department has the latest R on disc. But the real question is that if there are enough people on slow connection that are interested in obtaining R. Regards, Adai On Tue, 2004-11-16 at 21:39, [EMAIL PROTECTED] wrote: Hi Folks, I'm sure I'm speaking for more than a few (though possibly a minority) here. There's something of a hidden assumption that R users can readily download whatever they need from CRAN. Some of us are on narrow bandwidth dialup connections, so downloading large quantities of stuff is out of the question (e.g. at approx. 5min/MB, it would take over 2 days to download a single CD). The meat of CRAN (including contributed packages and documentation) is enough to fill 5 CDs, though one individual probably wouldn't be interested in all of that. (And, before anyone asks, no I won't be seeing broadband in the foreseeable future!) I've worked round this in various ways in the past. Some Linux distributions (e.g. RedHat, SuSE) come with the basics of R on their CDs, so when I've upgraded Linux I've got a new R (though not the latest). Linux Emporium once obligingly did me a custom CD very cheaply with the contributed packages. A friend with high-bandwidth access did me the 5 CDs in return for a pub lunch. And so on. One can get round it by bothering someone. What I'd like to suggest, for consideration, is that along with the stirling work done at many centres to set up and maintain mirrors of CRAN, some might consider offering also the service of burning CDs on request, for a reasonable charge. The difficulty, of course, is that it's going to take someone's time om something which may well not be their proper business. (I'm prompted to think about this again by the emergence of R-2 - 2.0.1 - one day soon? - 2.1. This is clearly a major advance in R and changes several things, so I'm looking at a major download operation, if not by me then by somebody that I can get CDs from, if I'm to be sure of being up to date on everything I'd like to have. And I'm sure I'm not the only one.) I'd be interested in people's comments on this proposal. Best wishes to all, Ted. E-Mail: (Ted Harding) [EMAIL PROTECTED] Fax-to-email: +44 (0)870 094 0861 [NB: New number!] Date: 16-Nov-04 Time: 21:39:14 -- XFMail -- __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- Adaikalavan Ramasamy[EMAIL PROTECTED] Centre for Statistics in Medicine http://www.ihs.ox.ac.uk/csm/ Cancer Research UK Tel : 01865 226 677 Old Road Campus, Headington, Oxford Fax : 01865 226 962 __ [EMAIL PROTECTED] 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] CDs for R?
On Tue, 16 Nov 2004 21:39:14 - (GMT), (Ted Harding) [EMAIL PROTECTED] wrote: Hi Folks, I'm sure I'm speaking for more than a few (though possibly a minority) here. There's something of a hidden assumption that R users can readily download whatever they need from CRAN. Some of us are on narrow bandwidth dialup connections, so downloading large quantities of stuff is out of the question (e.g. at approx. 5min/MB, it would take over 2 days to download a single CD). The meat of CRAN (including contributed packages and documentation) is enough to fill 5 CDs, though one individual probably wouldn't be interested in all of that. (And, before anyone asks, no I won't be seeing broadband in the foreseeable future!) The tarballs for the base source installation are only around 10 MB. That's only 50 minutes for you to do the main download. Then you can pick and choose what other packages to install. (It's 23 MB to download the Windows binary; I don't know the size of the Linux binaries.) Is it really worth setting up a duplication service? How much would you think is reasonable to pay for a CD to be mailed to you? Duncan Murdoch __ [EMAIL PROTECTED] 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] beginner's problem in displaying large data
I got a sample data (let's call it sample.data), which is about 2200 by 15. I tried to take a look of all data sample.data It shows only a part of data that I thought was a corner. It does not really affect my job, but I thought it is nice to have a look of all data. I can see individual records and they are fine. Is this normal because of buffer size or some reasons? Can I use other commands or change some settings to display all data? Thanks, Terry __ [EMAIL PROTECTED] 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] plot question
Say y and z are two time series (functions of date). What is the R command to plot y and z together on a graph with date on the x-axis? DISCLAIMER: This e-mail message and any attachments are inte...{{dropped}} __ [EMAIL PROTECTED] 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] beginner's problem in displaying large data
1. Did you try dim(sample.data)? Is it actually 2200 by 15? Or are you reading in just some subset of the data? If it is 2200 by 15, could you also please do class(sample.data)? 2. I just got a full listing from the following: (tst - data.frame(array(rnorm(2200), dim=c(2200, 15 You might try this. With R 2.0.0patched under Windows 2000, I got rows 1:2200 flying by 3 times, each with 5 columns. 3. Have you considered doing plots (including qqnorm) of numeric variables and tables of character variables? These can often reveal problems I might never see in a simple scan of numbers. 4. PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html;. At minimum, please tell us which version of R under which operating system, and specifically what you did to get it into R and how you know it's 2200 by 15. hope this helps. spencer graves Terry Mu wrote: I got a sample data (let's call it sample.data), which is about 2200 by 15. I tried to take a look of all data sample.data It shows only a part of data that I thought was a corner. It does not really affect my job, but I thought it is nice to have a look of all data. I can see individual records and they are fine. Is this normal because of buffer size or some reasons? Can I use other commands or change some settings to display all data? Thanks, Terry __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- Spencer Graves, PhD, Senior Development Engineer O: (408)938-4420; mobile: (408)655-4567 __ [EMAIL PROTECTED] 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] Cross-correlated variables in kernel density estimation
Hi, I am wondering if the kde2d 2-D kernel density estimation function in the MASS package can take into account the effect of correlations between the variables. I couldn't find any achieved information on this issue. Unfortunately, I don't have the 2002 edition of Modern Applied Statistics with S by Venables and Ripley in case it was described there. Thanks in advance. Adam Adam Kenea Gobena Research Assistant, Water Resources Engineering Department of Civil Environmental Engineering 220 Civil/Electrical Eng Bldg University of Alberta Edmonton, AB CANADA T6G 2G7 __ [EMAIL PROTECTED] 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] Cross-correlated variables in kernel density estimation
From: Adam Gobena Hi, I am wondering if the kde2d 2-D kernel density estimation function in the MASS package can take into account the effect of correlations between the variables. I couldn't find any achieved information on this issue. Unfortunately, I don't have the 2002 edition of Modern Applied Statistics with S by Venables and Ripley in case it was described there. The subject of your message doesn't seem to have much to do with your question... Also, it's not clear to me what you mean by taking into account the effect of correlations between variables. Do you mean a kernel function that is something like a bivariate Gaussian density with non-diagonal covariance matrix? If so, ?kde2d in MASS says: Two-dimensional kernel density estimation with an axis-aligned bivariate normal kernel, evaluated on a square grid. so the answer is no. No other R packages that does 2D kernel density estimation (that I know of, anyway) can do it, either, and probably for a good reason. Why would you need it? If there are correlation structures in the (X, Y) data, small enough bandwidths in both direction should give satisfactory estimate of the density. Andy Thanks in advance. Adam -- -- Adam Kenea Gobena Research Assistant, Water Resources Engineering Department of Civil Environmental Engineering 220 Civil/Electrical Eng Bldg University of Alberta Edmonton, AB CANADA T6G 2G7 __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ [EMAIL PROTECTED] 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] about 2 color variance stabilization
Hello sir: A paper of you namedExact and Approximate Variance-Stabilizing Transformations for Two-Color Microarrays is very helpful for my work. A question which needs your help.Thanks a lot. For instance,cy3~control cy5~treatment And after calculating the htransformation for each channel,we can get h(cy3) and h(cy5).But obviously,each h value isn't calculated individually ,but through the information of the all 2 channels.I wanna know how the all 2 channels's information is included in h transformation. By using the vsnpackage under R environment,if I enter only 1 channel(i.e. just 1 column data for gene expression),the system gives warning which notice me that I must enter at least 2 channels(i.e. 2 column data for gene expression).If I enter to channel,I can get the h value for each of the 2 channels.So I wanna know how to use the all 2 channels's imformation for the h transformation. Thanks again. My best regards! __ [EMAIL PROTECTED] 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] plot question
Apoian, Zack Zack.Apoian at sac.com writes: Say y and z are two time series (functions of date). What is the R command to plot y and z together on a graph with date on the x-axis? There are several time series classes (ts, zoo in zoo, irts in tseries, its in its, timeDate in fBasics) and its also possible to plot a numeric vector against a vector of dates. Here is an example using zoo which also illustrates the case where the times are not the same: library(zoo) # -- test data -- # y is over today and next 4 days. # z over today and next 9 days. y - zoo(11:15, Sys.Date() + 0:4) z - zoo(21:30, Sys.Date() + 0:9) plot(merge(y,z), plot.type = single, ylim = range(c(y,z)), col = c(green, red)) __ [EMAIL PROTECTED] 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] Non-Linear Regression on a Matrix
Hi, I'm terribly sorry for submitting my primitive question, I'm a beginner in R and was hoping to get some help re: non-linear fit. I have a 2D data with the following structure: A BC 1 1 111 1 2 121 1 3 131 2 1 141 2 2 151 2 3 161 3 1 171 3 2 181 3 3 191 I'm trying to fit C = non-linear function (A,B). I was wondering if there's a package that would save my time of doing direct least square estimation. Thank you, Diana __ [EMAIL PROTECTED] 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] Cross-correlated variables in kernel density estimation
Hi Andy, Sorry about the vague subject line. I think I overlooked a lot of things including the description of the function itself. Anyway, you have got the essence of my question. Thanks for the reply. I am using kernel density estimation to estimate the pdf some data. The pdf estimation is an intermediate step in a modeling work. So, I can work with one variable at a time and combine the final results from my model in some way but I thought it would be good to look at the joint PDF. The problem is, my (X,Y) data have a correlation structure. Thanks, Adam Adam K. Gobena Research Assistant, Water Resources Engineering Department of Civil Environmental Engineering 220 Civil/Electrical Eng Bldg University of Alberta Edmonton, AB CANADA T6G 2G7 -Original Message- From: Liaw, Andy [mailto:[EMAIL PROTECTED] Sent: Tuesday, November 16, 2004 6:06 PM To: 'Adam Gobena'; [EMAIL PROTECTED] Subject: RE: [R] Cross-correlated variables in kernel density estimation From: Adam Gobena Hi, I am wondering if the kde2d 2-D kernel density estimation function in the MASS package can take into account the effect of correlations between the variables. I couldn't find any achieved information on this issue. Unfortunately, I don't have the 2002 edition of Modern Applied Statistics with S by Venables and Ripley in case it was described there. The subject of your message doesn't seem to have much to do with your question... Also, it's not clear to me what you mean by taking into account the effect of correlations between variables. Do you mean a kernel function that is something like a bivariate Gaussian density with non-diagonal covariance matrix? If so, ?kde2d in MASS says: Two-dimensional kernel density estimation with an axis-aligned bivariate normal kernel, evaluated on a square grid. so the answer is no. No other R packages that does 2D kernel density estimation (that I know of, anyway) can do it, either, and probably for a good reason. Why would you need it? If there are correlation structures in the (X, Y) data, small enough bandwidths in both direction should give satisfactory estimate of the density. Andy Thanks in advance. Adam -- -- Adam Kenea Gobena Research Assistant, Water Resources Engineering Department of Civil Environmental Engineering 220 Civil/Electrical Eng Bldg University of Alberta Edmonton, AB CANADA T6G 2G7 __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- Notice: This e-mail message, together with any attachments,...{{dropped}} __ [EMAIL PROTECTED] 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] Non-Linear Regression on a Matrix
If your non-linear function (A, B) is parametric nls should do it for you. If you have R version 2 (perhaps even 1.9) do ?nls to see the help page. Older versions of R require library(nls) first. Hope this helps, Andy __ Andy Jaworski 518-1-01 Process Laboratory 3M Corporate Research Laboratory - E-mail: [EMAIL PROTECTED] Tel: (651) 733-6092 Fax: (651) 736-3122 Diana Abdueva [EMAIL PROTECTED] ail.com To Sent by: [EMAIL PROTECTED] [EMAIL PROTECTED] cc at.math.ethz.ch Subject [R] Non-Linear Regression on a 11/16/2004 08:33 Matrix PM Please respond to Diana Abdueva [EMAIL PROTECTED] ail.com Hi, I'm terribly sorry for submitting my primitive question, I'm a beginner in R and was hoping to get some help re: non-linear fit. I have a 2D data with the following structure: A BC 1 1 111 1 2 121 1 3 131 2 1 141 2 2 151 2 3 161 3 1 171 3 2 181 3 3 191 I'm trying to fit C = non-linear function (A,B). I was wondering if there's a package that would save my time of doing direct least square estimation. Thank you, Diana __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ [EMAIL PROTECTED] 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] how to estimate conditional density
Hi, there. Suppose I have a bivariate data set y1 and y2. Can anybody tell me how to estimate the conditional density of f(y1|y2) and vice versa? Thanks. Yulei $$$ Yulei He 1586 Murfin Ave. Apt 37 Ann Arbor, MI 48105-3135 [EMAIL PROTECTED] 734-647-0305(H) 734-763-0421(O) 734-763-0427(O) 734-764-8263(fax) $$ __ [EMAIL PROTECTED] 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] CDs for R?
Ted, On Tue, Nov 16, 2004 at 09:39:14PM -, Ted Harding wrote: Hi Folks, I'm sure I'm speaking for more than a few (though possibly a minority) here. There's something of a hidden assumption that R users can readily download whatever they need from CRAN. Some of us are on narrow bandwidth dialup connections, so downloading large quantities of stuff is out of the question (e.g. at approx. 5min/MB, it would take over 2 days to download a single CD). The meat of CRAN (including contributed packages and documentation) is enough to fill 5 CDs, though one individual probably wouldn't be interested in all of that. I'll cc this reply to Mark Walker. His shop, budgetlinuxcds.com / blcds.com, is one of the resellers of my Quantian 'scientific / cluster-computing workstation on a bootable dvd' Linux distribution / environment (see http://dirk.eddelbuettel.com/quantian for more on this). Mark has been consistently responsive while offering a low-cost cd/dvd service (of which I receive no cut, in case you're wondering about disclaimers). I think he'd be happy to add regular snapshots of certain portions of http://cran.r-project.org/src/, maybe for the sources and/or windows binaries, for his failry reasonable fees. (And, before anyone asks, no I won't be seeing broadband in the foreseeable future!) I've worked round this in various ways in the past. Some Linux distributions (e.g. RedHat, SuSE) come with the basics of R on their CDs, so when I've upgraded Linux I cannot resist mentioning that Debian will almost surely have the best R coverage with R, several dozen CRAN packages, ESS and many other goodies. Debian may well not be for everyone, but maybe Ubuntu will make the initial experience more pleasant. Hope this helps, Dirk I've got a new R (though not the latest). Linux Emporium once obligingly did me a custom CD very cheaply with the contributed packages. A friend with high-bandwidth access did me the 5 CDs in return for a pub lunch. And so on. One can get round it by bothering someone. What I'd like to suggest, for consideration, is that along with the stirling work done at many centres to set up and maintain mirrors of CRAN, some might consider offering also the service of burning CDs on request, for a reasonable charge. The difficulty, of course, is that it's going to take someone's time om something which may well not be their proper business. (I'm prompted to think about this again by the emergence of R-2 - 2.0.1 - one day soon? - 2.1. This is clearly a major advance in R and changes several things, so I'm looking at a major download operation, if not by me then by somebody that I can get CDs from, if I'm to be sure of being up to date on everything I'd like to have. And I'm sure I'm not the only one.) I'd be interested in people's comments on this proposal. Best wishes to all, Ted. E-Mail: (Ted Harding) [EMAIL PROTECTED] Fax-to-email: +44 (0)870 094 0861 [NB: New number!] Date: 16-Nov-04 Time: 21:39:14 -- XFMail -- __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- If your hair is standing up, then you are in extreme danger. -- http://www.usafa.af.mil/dfp/cockpit-phys/fp1ex3.htm __ [EMAIL PROTECTED] 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] Search engine for LINUX MOZILLA
Hi, I am looking for help on searc engine at R htmlhelp page. Here is the system settings: R 2.0.0 (2004-10-04). Installed at Linux RH 9.0 (kernal 2.4.20-8) and FC2 (kernal 2.5.8). The web broswer is Mozilla 1.7 Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.7) Gecko/20040616 From help.start(), web broswer started ok. However, the search engine does not respond. The status bar only shows done. In Windows settings, it shows Applet started or something similar. I tried a few plugins, did not work. Any suggest? Yuandan __ [EMAIL PROTECTED] 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] persp grid
I've got a 4x4 matrix of points from a 2-way ANOVA I'd like to plot. The x,y correspond to the treatment groups and look like this ((1,1),(1,2),(1,3),(1,4),(2,1),...). The z is the 4x4 matrix. How can I get persp to grid the x,y axis with only the numbers 1-4 on both? Regards, Joel Bremson UC Davis Statistics Dept. __ [EMAIL PROTECTED] 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] CDs for R?
On 16 Nov 2004, at 23:39, (Ted Harding) wrote: Some of us are on narrow bandwidth dialup connections, so downloading large quantities of stuff is out of the question (e.g. at approx. 5min/MB, it would take over 2 days to download a single CD). The meat of CRAN (including contributed packages and documentation) is enough to fill 5 CDs, though one individual probably wouldn't be interested in all of that. 5 CDs sounds 4 too many. I once burnt CDs for my students, and they fitted nicely in one CD (Windows binaries, all packages as Windows binaries and sources, contributed documents). I guess you can fit Windows, Mac and some Linux binaries all in one CD. Now comes my suggestion to CRAN maintainer: this all would be easier, if you would produce a CD image file ('iso') that would contain a snapshot of the latest version: main binaries, all contributed packages, and docs. Getting somebody to help downloading this iso would be much easier than trying to collect all first and then make up your own cd image. Actually, only Windows and Mac users need binary versions of packages. The former because they don't have tools to install from source, the latter because they don't know that they have the tools (being command line challenged). To Dirk Eddelbuettel: Yes indeed, Ubuntu gives human face to Debian and is a much more pleasant experience. However, changing OS for R may be asking too much. Further, Ubuntu/Debian comes with a tiny and biased selection of packages, and if that's not your kind of bias, you have got to go to the Internet again. Further, Ubuntu (and other Linuxes) lag behind R. The current Ubuntu release comes with R 1.9.1, and it won't be upgraded but in the next release scheduled for April 2005 (and just in the same time as the next R, so that Ubuntu will be one R version off again). I guess the lag is even worse in packages. cheers, jari oksanen -- Jari Oksanen, Oulu, Finland __ [EMAIL PROTECTED] 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] How to plot this
Hi there, I produced a plot using the following codes: y-rnorm(1000, 2, 0) x0-c(0, 0) y0-c(0, 0) y1-c(0, 1) x1-c(0, 4) plot(density(y), ylab=Abundance of species, xlab=Environmental gradient, main= , xlim=c(0, 4), ylim=c(0, 1), lty=2, col=4, xaxt=n, yaxt=n, frame.plot=F) lines(x0, y1) # add an axis lines(x1, y0) # add an axis arrows(3.95, 0, 4, 0, angle = 15, length = 0.1) arrows(0, 0.98, 0, 1, angle = 15, length = 0.1) Please help me to remove the grey horizontal line and put the axis labels closer to the axes. And also appreciate any suggestions on how to make those arrows look nicer, e.g. a filled small arrow for each axis, like what from points(0, 1, pch=17), but a slightly narrowed one. Thanks. Regards, Jin Li Jin Li, PhD Climate Impacts Modeller CSIRO Sustainable Ecosystems Atherton, QLD 4883, Australia [[alternative HTML version deleted]] __ [EMAIL PROTECTED] 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] Re: variations on the theme of survSplit
Danardono [EMAIL PROTECTED] wrote: While waiting for 2.1, for those who need function[s] for this survival-splitting business, as I do, this 'survcut' function below might be helpful. It is not an elegant nor efficient function but it works, at least for some examples below. Ditto the following, for the case where there are multiple time-varying (irreversible) binary covariates, here slicing as coarsely as possible. # # Create dataset for survival analysis with time-dependent covariate # Gill-Anderson model # x - data.frame(onset=c(46, 32, 53, 76, 64, 43), case=c(1,1,1,0,0,0), ooph=c(NA, 30, 38, 50, NA, NA), ocp=c(1,1,0,0,1,0), parity=c(2,0,1,3,3,2), age.preg=c(28,NA,27,20,22,23)) make.dep - function(onset, case, time.dep, covs=NULL) { if (is.null(n.time.dep - ncol(time.dep))) { if (!is.null(time.dep)) { n.time.dep - 1 time.dep - as.matrix(time.dep) }else{ n.time.dep - 0 warning(No time dependent covariates) } } if (is.null(n.covs - ncol(covs))) { if (!is.null(covs)) { n.covs - 1 covs - as.matrix(covs) }else{ n.covs - 0 } } ordered.t - t(apply(cbind(onset,time.dep),1,sort,na.last=TRUE)) tot.time.dep - apply(ordered.t,1,function(x) sum(!is.na(x))) ordered.t - cbind(rep(0, nrow(ordered.t)), ordered.t) npars - 4+n.time.dep+n.covs nrecs - sum(tot.time.dep) new.x - as.data.frame(matrix(nr=nrecs, nc=npars)) names(new.x) - c(start, stop, event, names(time.dep),names(covs),episode) this.rec-0 for(i in 1:length(onset)) { for(j in 1:tot.time.dep[i]) { this.rec - this.rec+1 new.x[this.rec,1] - ordered.t[i, j] new.x[this.rec,2] - ordered.t[i, j+1] new.x[this.rec,3] - 0 new.x[this.rec,4:(3+n.time.dep)] - (ordered.t[i,j]=time.dep[i,]) missing - is.na(new.x[this.rec,]) new.x[this.rec,missing] - 0 if (n.covs0) { new.x[this.rec, (4+n.time.dep):(4+n.time.dep+n.covs)] - covs[i,] } new.x[this.rec, npars]-paste(i,j,sep=.) } new.x[this.rec,3]-case[i] } new.x } David Duffy. __ [EMAIL PROTECTED] 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] Search engine for LINUX MOZILLA
This is covered in the R-admin manual, linked to from that HTML page. Please follow carefully the advice there. In particular ensure that you have a version of Java that is said to work (preferably the latest, 1.5.0). On Wed, 17 Nov 2004, Yuandan Zhang wrote: Hi, I am looking for help on searc engine at R htmlhelp page. Here is the system settings: R 2.0.0 (2004-10-04). Installed at Linux RH 9.0 (kernal 2.4.20-8) and FC2 (kernal 2.5.8). The web broswer is Mozilla 1.7 Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.7) Gecko/20040616 From help.start(), web broswer started ok. However, the search engine does not respond. The status bar only shows done. In Windows settings, it shows Applet started or something similar. I tried a few plugins, did not work. Any suggest? Yuandan __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- Brian D. Ripley, [EMAIL PROTECTED] Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ University of Oxford, Tel: +44 1865 272861 (self) 1 South Parks Road, +44 1865 272866 (PA) Oxford OX1 3TG, UKFax: +44 1865 272595 __ [EMAIL PROTECTED] 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] Cross-correlated variables in kernel density estimation
Yes it can and it is in the reference. On Tue, 16 Nov 2004, Adam Gobena wrote: Hi, I am wondering if the kde2d 2-D kernel density estimation function in the MASS package can take into account the effect of correlations between the variables. I couldn't find any achieved information on this issue. Unfortunately, I don't have the 2002 edition of Modern Applied Statistics with S by Venables and Ripley in case it was described there. -- Brian D. Ripley, [EMAIL PROTECTED] Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ University of Oxford, Tel: +44 1865 272861 (self) 1 South Parks Road, +44 1865 272866 (PA) Oxford OX1 3TG, UKFax: +44 1865 272595 __ [EMAIL PROTECTED] 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] How to plot this
If this is a quick and dirty process you want rather than learning all the capabilities that are in R then I would copy the density curve (or the bits you like) into your favourite image editor, and use it's capabilities to pretty it up. However there are a number of options. Firstly you have chosen to plot density(y). When I looked at the help for density it gives the values returned by density. If you want a custom plot maybe you should try dcurve - density(y) you could then directly access the $x and $y components as you would in any plot For instance plot(density(y)) gives you the grey line. However plot(dcurve$x,dcurve$y,type = l) gives you a different type of plot. As for arrowheads one could create an appropriate polygon to stick at each end. Which for a one off might be a bit of overkill. Sometime in all of this you'll also probably encounter clipping, in which case par(xpd = TRUE) will often help. Just remember to turn if off or you may find unwanted graphics appearing later on. For putting the labels where you want you could use mtext. This gives you control over where you want to place the text. A word of caution. If you are going to start prettying up you plots to very specific standards make sure that you are working on the final device from which you wish to take the final copy. Each of the devices have their own capabilities which are often not related to R but rather to their own environment. That is you can't get a plot looking perfect in a window and assume that the same code sent to a postscript device will produce identical results. R can give you very good graphics, often straight out of the box, but like any publishing process it can be a bit fiddly. Tom Mulholland Senior Demographer Department for Planning and Infrastructure Perth, WA, Australia. -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] Sent: Wednesday, 17 November 2004 2:39 PM To: [EMAIL PROTECTED] Subject: [R] How to plot this Hi there, I produced a plot using the following codes: y-rnorm(1000, 2, 0) x0-c(0, 0) y0-c(0, 0) y1-c(0, 1) x1-c(0, 4) plot(density(y), ylab=Abundance of species, xlab=Environmental gradient, main= , xlim=c(0, 4), ylim=c(0, 1), lty=2, col=4, xaxt=n, yaxt=n, frame.plot=F) lines(x0, y1) # add an axis lines(x1, y0) # add an axis arrows(3.95, 0, 4, 0, angle = 15, length = 0.1) arrows(0, 0.98, 0, 1, angle = 15, length = 0.1) Please help me to remove the grey horizontal line and put the axis labels closer to the axes. And also appreciate any suggestions on how to make those arrows look nicer, e.g. a filled small arrow for each axis, like what from points(0, 1, pch=17), but a slightly narrowed one. Thanks. Regards, Jin Li Jin Li, PhD Climate Impacts Modeller CSIRO Sustainable Ecosystems Atherton, QLD 4883, Australia [[alternative HTML version deleted]] __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html