[R] R_HOME not found
Hi, I have a problem with R 1.9.1. I installed it on my mac (os 10.2.8), and then tried to start it from the terminal. I got the following error message: R_HOME ('/Applications/StartR.app/RAqua.app/Contents') not found It also won't let me start the GUI version. Any comments or suggestions would be greatly appreciated. Thanks, Rene __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Population simulation.
[EMAIL PROTECTED] wrote: Hello, can anyone tell me if R has any special function for simulating the structure of human populations? Something like the genetic algorithm? I need to simulate a sample of a population with a specific structure. Is there something on R that can help me? As others have pointed out, you need to give us some more details. There is an artile about simulation of ecological dynamics in last December's R News, which may be of some help: http://cran.r-project.org/doc/Rnews/Rnews_2003-3.pdf If you're simulating something like a coalescence process, then it might be easier to use some specialist software. In that case, googling with a few relevant terms might be the way to go. Bob -- Bob O'Hara Dept. of Mathematics and Statistics P.O. Box 68 (Gustaf Hällströmin katu 2b) FIN-00014 University of Helsinki Finland Telephone: +358-9-191 51479 Mobile: +358 50 599 0540 Fax: +358-9-191 51400 WWW: http://www.RNI.Helsinki.FI/~boh/ Journal of Negative Results - EEB: http://www.jnr-eeb.org __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Read SPSS data (*.sav) in R 1.8.0 (ok) and R1.9.1(error)
Hallo! I read SPSS data in the following way: library(Hmisc) library(foreign) dat-spss.get(surv_abb.sav) In R1.9.1 I got the message: Error in all(arg == choices) : Object typeDate not found In R1.8.0 the same script works fine. Does anybody know a possibilty to read a SPSS file under R1.9.1? Thanks! Karl __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] computing sum of indicator variables
My problem is as follows: i is a list of integers of variable length. Now I want to compute a new vector/array that contains 1's at the positions indicated in i. For example: c(2, 4) - c(0, 1, 0, 1) Using something like i = i - c(0, i[2:length(i) - 1]); sapply(i, function(x) c(rep(0, x - 1), 1))); faces me with the problem of concatenating the result, which I could somehow not find a solution for. Thank you very much in advance. Stefan __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] computing sum of indicator variables
Stefan Böhringer wrote: My problem is as follows: i is a list Do you mean a vector? of integers of variable length. Now I want to compute a new vector/array A vector or an array (which dimensions?)? that contains 1's at the positions indicated in i. For example: c(2, 4) - c(0, 1, 0, 1) How long should the result be? max(i)??? If you mean simple vectors in both cases, i's suggest: i - c(2, 4) x - numeric(max(i)) x[i] - 1 Uwe Ligges Using something like i = i - c(0, i[2:length(i) - 1]); sapply(i, function(x) c(rep(0, x - 1), 1))); faces me with the problem of concatenating the result, which I could somehow not find a solution for. Thank you very much in advance. Stefan __ [EMAIL PROTECTED] mailing list https://www.stat.math.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://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] computing sum of indicator variables
Hi Stefan, you could try something like, x - c(2,4,7) as.numeric(!is.na(match(seq(1, max(x)), x))) I hope this helps. Best, Dimitris Dimitris Rizopoulos Doctoral 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: Stefan Bhringer [EMAIL PROTECTED] To: R Help [EMAIL PROTECTED] Sent: Monday, July 26, 2004 10:45 AM Subject: [R] computing sum of indicator variables My problem is as follows: i is a list of integers of variable length. Now I want to compute a new vector/array that contains 1's at the positions indicated in i. For example: c(2, 4) - c(0, 1, 0, 1) Using something like i = i - c(0, i[2:length(i) - 1]); sapply(i, function(x) c(rep(0, x - 1), 1))); faces me with the problem of concatenating the result, which I could somehow not find a solution for. Thank you very much in advance. Stefan __ [EMAIL PROTECTED] mailing list https://www.stat.math.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://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
RE: [R] computing sum of indicator variables
What about x - c(2,4,7) out-rep(0,max(x)) out[x]-1 Regards Wayne -Original Message- From: Stefan Böhringer [mailto:[EMAIL PROTECTED] Sent: 26 July 2004 09:46 To: R Help Subject: [R] computing sum of indicator variables My problem is as follows: i is a list of integers of variable length. Now I want to compute a new vector/array that contains 1's at the positions indicated in i. For example: c(2, 4) - c(0, 1, 0, 1) Using something like i = i - c(0, i[2:length(i) - 1]); sapply(i, function(x) c(rep(0, x - 1), 1))); faces me with the problem of concatenating the result, which I could somehow not find a solution for. Thank you very much in advance. Stefan __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html KSS Ltd Seventh Floor St James's Buildings 79 Oxford Street Manchester M1 6SS England Company Registration Number 2800886 Tel: +44 (0) 161 228 0040 Fax: +44 (0) 161 236 6305 mailto:[EMAIL PROTECTED]http://www.kssg.com The information in this Internet email is confidential and m...{{dropped}} __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] fisher.test FEXACT error 7
Thanks Sundar, That changes the behaviour of R, but only in so far as it waits longer before giving the same error: fisher.test(testDataTwoColumns, workspace = 2e8) Error in fisher.test(testDataTwoColumns, workspace = 2e+08) : FEXACT error 7. LDSTP is too small for this problem. Try increasing the size of the workspace. ...There also seems to be an upper limit of how big the workspace can be... fisher.test(testDataTwoColumns, workspace = 2e9) Error in fisher.test(testDataTwoColumns, workspace = 2e+09) : negative length vectors are not allowed fisher.test(testDataTwoColumns, workspace = 2e10) Error in fisher.test(testDataTwoColumns, workspace = 2e+10) : NAs in foreign function call (arg 10) In addition: Warning message: NAs introduced by coercion A further question - do you (or anyone else) think that this is a problem with the physical capabilities of the box that I'm running on, or is it likely to be an upper limit with the amount of data that the algorithm can handle? Many thanks, Ken Sundar Dorai-Raj wrote: Ken Edwards wrote: Hello, I have an error message that doesn't seem to make sense in that having read the R documentation I was under the impression that R was able to grab as much memory as it needed, and has been able to do so for some time, so the advice given below about increasing the size of the workspace is redundant. If I'm right, does anyone have a solution to the problem of the size of LDSTP? Or is this really a message about the limit of data size that the function can handle? I have tried the function using test data containing a similar number of (randomly generated) data points, and it worked then. There are 258 data points in two columns (i.e. 2 * 134), if that helps. Any advice would be very much appreciated, Many thanks, Ken Edwards. R script below: fisher.test(testData) Error in fisher.test(testData) : FEXACT error 7. LDSTP is too small for this problem. Try increasing the size of the workspace. Maybe you should try increasing the workspace: fisher.test(testData, workspace = 2e6) --sundar __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Read SPSS data (*.sav) in R 1.8.0 (ok) and R1.9.1(error)
On 07/26/04 10:36, Karl Knoblick wrote: Hallo! I read SPSS data in the following way: library(Hmisc) library(foreign) dat-spss.get(surv_abb.sav) In R1.9.1 I got the message: Error in all(arg == choices) : Object typeDate not found In R1.8.0 the same script works fine. Does anybody know a possibilty to read a SPSS file under R1.9.1? I cannot find spss.get in the man pages for the current version of foreign. It works for me with read.spss. But I'm surprised it ever worked. So, possibly, there is something wrong with the spss file you are trying to import. Jon -- Jonathan Baron, Professor of Psychology, University of Pennsylvania Home page: http://www.sas.upenn.edu/~baron R search page: http://finzi.psych.upenn.edu/ __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Eclipse plugin for R or perhaps S-plus.
Richard Piper wrote: Does any one know of an eclipse (http://eclipse.org) plugin for R/S. thanks RIchard Hi, You can download a small Eclipse plug-in for R from my homepage: http://www.walware.de/rplugin.zip . Simply unzip the file into the Eclipse directory. The plug-in requires version 3.0 of Eclipse, it is not compatible with version 2.x. The plug-in provides syntax highlighting for R files and R documentations (Rd files). Furthermore, editor functions concerning matching brackets (highlighting, goto, select enclosing content on double click) are implemented. Naturally, you can use the language independent IDE features of Eclipse such as Local History, QuickDiff, CVS, ... You can configure the editors in the Eclipse preference dialog under StatET. Best regards, Stephan Wahlbrink __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Econometrics Packages On R
Dear Allan, I still use R principally in ts analysis. Tha main packages I employ are: ts, tseries, ast (it supplies some helpfull functions and can be downloaded from CRAN) and lmtest. Just in this period I preparing a summary of functions involved in ts analysis grouped by goal. I would send this short document to CRAN in next weeks when I end it. If you wish I'll send you a copy. Other functions can be found in: Rmetrics which is a collection of functions which may be useful for teaching Financial Engineering and Computational Finance. See: http://www.itp.phys.ethz.ch/econophysics/R/ Cordially Vito Hello, I have just started using R, maybe more like learning it. I am interested in using it for Time Series Analysis and I wanted to know if anyone was familiar with packages other than TS that might be appropriate. Allan = Diventare costruttori di soluzioni 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://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] X11 device problem on linux: 100% cpu usage
Hi, I'm using R 1.9.1 (patched, 5th July) on linux (Mandrake 9.2) and am having a problem with the X11() device. Trying to plot(1:10) results in my CPU going to 100% and I have to terminate the process. Using postscript() with the same plot is fine. Everything else on my system seems to work fine. I have googled the R site for X11 and (problem OR error OR cpu) and have not seen anything that is recent or looks relevent, so I think this is a problem I have created myself. I'm not sure where to start with identifying the cause. Can someone suggest some things that I should look at? Thanks. Dave. __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] covariate selection in cox model (counting process)
Hello everyone, I am searching for a covariate selection procedure in a cox model formulated as a counting process. I use intervals, my formula looks like coxph(Surv(start,stop,status)~ x1+x2+...+cluster(id),robust=T) where id is a country code (I study occurence of civil wars from 1962 to 1997). I'd like something not based on p-values, since they have several flaws for this purpose. I turned to other criteria but all the articles I read seems to apply to the classical formulation of the cox model, not the counting process one (or they apply to both but I am not aware of this) I've tried AIC with step(cox.fit) or stepAIC(cox.fit) and BIC using step(cox.fit,k = log(n)) but there seems to be 2 theoretical problems to address: (1) These values are based on partial loglikelihood (loglik) I wonder if this is correct with the cox model formulated as a *counting process*, with many (consecutive) observations for a given individual, and then some observation not being independent Since the likelihood ratio and score tests assume independence of observations within a cluster, the Wald and robust score tests do not (R warning), and the likelihood ratio being based on loglik, can I use loglik in BIC with some dependent observations? [I have 170 individuals (namely, countries) for 36 year, some single countries having up to 140 very short observation intervals, other having (on the other extreme) only 1 long interval per year. That's because I created artificial covariates measuring the proximity since some events: exp(-days.since.event/a.chosen.parameter). I splitted every yearly interval for which these covariates change rapidly (i.e. when the events are recent) yielding up to 11 intervals a year] (2) What penalized term to used? It seems natural to include the number of covariates, k. What about the number of observations? I found several definitions: AIC= -2 loglik(b) + 2.k Schwartz Bayesian information criteria: SBIC= -2 loglik(b) + k ln(n) Frédérique Letué (author of PhD thesis COX MODEL: ESTIMATION VIA MODEL SELECTION AND BIVARIATE SHOCK MODEL, http://www-lmc.imag.fr/lmc-sms/Frederique.Letue/These3.ps) suggested me AIC= - loglik(b) + 2.k/n BIC= - loglik(b) + 2.ln(n).k/n, with other possible values for parameter 2 in this case (see her thesis p.100, but this section is in French) All these do not tell *what to take for n*. There are 3 main possibilities: a) Taking the number of observations (including censored one) will give a huge n (around 6000 to 8000), which may seem meaningless since some observations are only a few days long. With n at the denominator (Letué's criteria), the penalized term would be so low that it's like not having it: log(7000)/7000 [1] 0.001264809 (where loglik from summary(cox.fit) range from -155 to -175, dependig on the model) b) Volinsky Raftery propose a revision of the penalty term in BIC so that the penalty is defined in terms of the number of uncensored events instead of the number of observations. (Volinsky Raftery , Bayesian Information Criterion for Censored Survival Models, June 16, 1999, http://www.research.att.com/~volinsky/papers/biocs.ps) This could be computed with sum(coxph.detail(cox.interac.dsi6mois)$nevent) Letué's BIC penalized trerm with 50 events will then be 2*log(50)/50 [1] 0.1564809 which will have more effects. However, adding or removing a country which has data for the 36 years but no event (then, it is censored) will not change this BIC. Thus, it is not suitable to account for missing data that do not reduce the number of event. I'd like the criteria to take this into account, because all covariates do not have the same missing data. The question is: When I have the choice with adding a covariate, x10 or x11, which have different (not nested) set of missing values, which one is best? Estimating all subsets of the full model (full model = all covariates) with a dataset containing no missing data for the full model would be a solution but would more than halve the dataset for many subsets of the covariates. I should mention that step(cox.fit) gives a warning and stops: Error in step(cox.fit) : number of rows in use has changed: remove missing values? which makes me ask whether the whole procedure is OK with model of different sample size. c) For discrete time event history analysis, the same choice has been made, while the total number of exposure time units has also been used, for consistency with logistic regresion (Raftery,Lewis,Aghajanian and Kahn,1993;Raftery Lewisand Aghajanian,1994) (Raftery, Bayesian Model Selection in Social Research, 1994, http://www.stat.washington.edu/tech.reports/bic.ps) I am not sure what exposure time units mean. But since I could have used a logit model with yearly observations [but with many flaws...], I suggest I could use the number of years (sum of length of intervals, in year) sum((fit$y)[,2]-(fit$y)[,1])/365.25 [1] 3759.537 This may still be too high. Since I have datas
Re: [R] X11 device problem on linux: 100% cpu usage
David Whiting wrote: I'm using R 1.9.1 (patched, 5th July) on linux (Mandrake 9.2) and am having a problem with the X11() device. Trying to plot(1:10) results in my CPU going to 100% I'm not sure where to start with identifying the cause. Can someone suggest some things that I should look at? First off, you can try and figure out if its the client (R) or the server (your X-windows display server). Can you connect to your problem machine from another host (preferably one with a different Linux distro, or different X server) and run R, sending the graphics over the network. Does it still cause your problem machine to go slow? Then its something on the client side. If that works fine, then its something to do with the X server on the problem machine. Or an interaction term between client and server! Baz __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] interpreting profiling output
On Sun, 25 Jul 2004, Peter Dalgaard wrote: Kasper Daniel Hansen [EMAIL PROTECTED] writes: I have some trouble interpreting the output from profiling. I have read the help pages Rprof, summaryRprof and consult the R extensions manual, but I still have problems understanding the output. Basically the output consist of self.time and total.time. I have the understanding that total.time is the time spent in a given function including any subcalls or child functions or whatever the technical term for that activity is. In contrasts self.time is the time spent in the function excluding subcalls. Now, in my understanding basically everything in R is functions. I would then guess that for almost any function (except the atomic ones) the self.time would be very small as it would spend most of its time calling other functions (again, since almost everything is a function). So how do R determine when a subfunction is called? ...brutal snippage... I guess some of the answers would be clear if I had a firm grasp of the inner workings of R :) In a word, yes... The profiling keeps track of R's *context stack* which is not quite the same as function calls. Essentially, it only counts R functions that are actually written in R, but not .Internal, .Primitive, etc. So self counts the amount of time that a function was at the top of the stack. This is done by a periodic poll which dumps out the context stack at regular intervals. Seeing cases where the self percentages don't add to 100% is, I believe, simply due to truncation of the tails -- that is, there is a large number of different functions which each are counted a few times, and these are not shown in the summary output. [Sorry about the late reply, but I was out of town, and noone seems to have answered this.] Just one additional clarification: There are two flavors of .Primitive, 'builtin' and 'special'. You can tell which is which using typeof(). Builtins are things like arithmetic operations and specials include control constructs like `for`. At present profiling does record builtins but not specials. Recording specials is something we would like to do eventually but it requires more changes to the call stack (and dealing with more interections with those changes) so it hasn't happened yet. .Internal is a special, so no .Internal calls are recorded. luke -- Luke Tierney University of Iowa Phone: 319-335-3386 Department of Statistics andFax: 319-335-3017 Actuarial Science 241 Schaeffer Hall email: [EMAIL PROTECTED] Iowa City, IA 52242 WWW: http://www.stat.uiowa.edu __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Re: smooth non cumulative baseline hazard in Cox model
Hello everyone, I am searching for a covariate selection procedure in a cox model formulated as a counting process. I use intervals, my formula looks like coxph(Surv(start,stop,status)~ x1+x2+...+cluster(id),robust=T) where id is a country code (I study occurence of civil wars from 1962 to 1997). I'd like something not based on p-values, since they have several flaws for this purpose. I turned to other criteria but all the articles I read seems to apply to the classical formulation of the cox model, not the counting process one (or they apply to both but I am not aware of this) I've tried AIC with step(cox.fit) or stepAIC(cox.fit) and BIC using step(cox.fit,k = log(n)) but there seems to be 2 theoretical problems to address: (1) These values are based on partial loglikelihood (loglik) I wonder if this is correct with the cox model formulated as a *counting process*, with many (consecutive) observations for a given individual, and then some observation not being independent Since the likelihood ratio and score tests assume independence of observations within a cluster, the Wald and robust score tests do not (R warning), and the likelihood ratio being based on loglik, can I use loglik in BIC with some dependent observations? [I have 170 individuals (namely, countries) for 36 year, some single countries having up to 140 very short observation intervals, other having (on the other extreme) only 1 long interval per year. That's because I created artificial covariates measuring the proximity since some events: exp(-days.since.event/a.chosen.parameter). I splitted every yearly interval for which these covariates change rapidly (i.e. when the events are recent) yielding up to 11 intervals a year] (2) What penalized term to used? It seems natural to include the number of covariates, k. What about the number of observations? I found several definitions: AIC= -2 loglik(b) + 2.k Schwartz Bayesian information criteria: SBIC= -2 loglik(b) + k ln(n) Frédérique Letué (author of PhD thesis COX MODEL: ESTIMATION VIA MODEL SELECTION AND BIVARIATE SHOCK MODEL, http://www-lmc.imag.fr/lmc-sms/Frederique.Letue/These3.ps) suggested me AIC= - loglik(b) + 2.k/n BIC= - loglik(b) + 2.ln(n).k/n, with other possible values for parameter 2 in this case (see her thesis p.100, but this section is in French) All these do not tell *what to take for n*. There are 3 main possibilities: a) Taking the number of observations (including censored one) will give a huge n (around 6000 to 8000), which may seem meaningless since some observations are only a few days long. With n at the denominator (Letué's criteria), the penalized term would be so low that it's like not having it: log(7000)/7000 [1] 0.001264809 (where loglik from summary(cox.fit) range from -155 to -175, dependig on the model) b) Volinsky Raftery propose a revision of the penalty term in BIC so that the penalty is defined in terms of the number of uncensored events instead of the number of observations. (Volinsky Raftery , Bayesian Information Criterion for Censored Survival Models, June 16, 1999, http://www.research.att.com/~volinsky/papers/biocs.ps) This could be computed with sum(coxph.detail(cox.interac.dsi6mois)$nevent) Letué's BIC penalized trerm with 50 events will then be 2*log(50)/50 [1] 0.1564809 which will have more effects. However, adding or removing a country which has data for the 36 years but no event (then, it is censored) will not change this BIC. Thus, it is not suitable to account for missing data that do not reduce the number of event. I'd like the criteria to take this into account, because all covariates do not have the same missing data. The question is: When I have the choice with adding a covariate, x10 or x11, which have different (not nested) set of missing values, which one is best? Estimating all subsets of the full model (full model = all covariates) with a dataset containing no missing data for the full model would be a solution but would more than halve the dataset for many subsets of the covariates. I should mention that step(cox.fit) gives a warning and stops: Error in step(cox.fit) : number of rows in use has changed: remove missing values? which makes me ask whether the whole procedure is OK with model of different sample size. c) For discrete time event history analysis, the same choice has been made, while the total number of exposure time units has also been used, for consistency with logistic regresion (Raftery,Lewis,Aghajanian and Kahn,1993;Raftery Lewisand Aghajanian,1994) (Raftery, Bayesian Model Selection in Social Research, 1994, http://www.stat.washington.edu/tech.reports/bic.ps) I am not sure what exposure time units mean. But since I could have used a logit model with yearly observations [but with many flaws...], I suggest I could use the number of years (sum of length of intervals, in year) sum((fit$y)[,2]-(fit$y)[,1])/365.25 [1] 3759.537 This may still be too high. Since I have datas
[R] aggregate function
Hi all, I have the folowing frame(there are more columns than shown), 1 2 34 5 Year Total TusWhi Norw 1994 1.00 1830 0 355 1995 1.00 0 00 1995 1.00 0 00 1995 1.00 49104280 695 1997 1.00 0 0 110 1997 0.58 0 00 1997 1.00 0 00 1994 1.00 0 00 1997 1.00 0 40 70 1998 1.00 0 0 1252 1999 1.04 0 740 1999 1.00 0 00 1999 1.02 0 00 1999 1.00 0 00 1999 1.00 0 0 171 1999 1.00 1794 0 229 1999 1.00 035250 1997 1.00 13351185 147 1997 1.00 49251057 4801 1997 1.00 06275 1773 I try to get sum(Total) by Year in which Tus0, sum(Total) by Year in which Whi0,,,and so on. I have done something like this; a-as.list(numeric(3)) for (i in 3:5) { a[[i]]-aggregate(frame[,Total],list(Year=frame$Year, Tus=frame$i0),sum) } But I get Error in FUN(X[[as.integer(1)]], ...) : arguments must have same length Also by doing one by one aggregate(frame[,Total],list(Year=frame$Year, Tus=frame$Tus0),sum) The result is something like; Year Tus x 1994 FALSE 49.69 1995 FALSE 49.35 1996 FALSE 56.95 1997 FALSE 57.00 1998 FALSE 57.00 1999 FALSE 58.09 2000 FALSE 56.97 2001 FALSE 57.95 2002 FALSE 57.10 2003 FALSE 56.16 2000 TRUE 1.00 2002 TRUE 1.00 2003 TRUE 2.01 Help Thank you Luis Ridao Cruz Fiskirannsóknarstovan Nóatún 1 P.O. Box 3051 FR-110 Tórshavn Faroe Islands Phone: +298 353900 Phone(direct): +298 353912 Mobile: +298 580800 Fax: +298 353901 E-mail: [EMAIL PROTECTED] Web:www.frs.fo __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] R on AMD64 (Opteron)
We are using Fedora Core 2 and some version(s) of SuSe Linux on various dual Opteron servers. We also have a copy of RHEL, but AFAIK are not currently using it. I've been using a dual Opteron 248 under FC2 I don't know that Windows XP 64-Bit Edition is actually released yet (although there have beem public betas). However, as Peter D says, one would need a suitable compiler, binutils etc and the MinGW project is unlikely to provide them any time soon (if ever, although the project's FAQ suggests that it does intend to). On Sat, 24 Jul 2004, Jose Quesada wrote: Also, I'm curious... Not that this would be my first choice for a server, but... Anyone running Windows XP 64-Bit Edition? Any success compiling R? On Sat, 24 Jul 2004 18:07:18 +1000, Andrew Robinson [EMAIL PROTECTED] wrote: Professor Ripley, which operating system are you using for these servers, please? Thanks, Andrew - Original Message - From: Prof Brian Ripley [EMAIL PROTECTED] Date: Saturday, July 24, 2004 5:41 pm Subject: Re: [R] R on AMD64 (Opteron) On Fri, 23 Jul 2004, Asselin Jerome wrote: Hi, I was wondering if anyone has had good experiences using R on Linux with dual AMD64 (Opteron) processors. I'm thinking of buying a couple of such servers, but I'd like to make sure R would work fine. The R Installation and Administration guide notes that there may be some problems with BLAS libraries. That's all I could find about R on AMD64. Actually it says with ATLAS BLAS, not generically. Please share your experience using R on AMD64. Quite a few people, including us, are using R on such servers routinelywith no problems at all. There are still some issues about how to squeeze the maximum performance out of them (e.g. which BLAS to use -- we are using Goto's -- and which compiler to use, e.g. Portland Group or Intel). -- 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 -- 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://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] aggregate function
Hi, # x ... your frame attach(x) sum(Total[Year==1997 Tus 0]) I hope this helps Best, Matthias -Ursprüngliche Nachricht- Von: Luis Rideau Cruz [mailto:[EMAIL PROTECTED] Gesendet: Montag, 26. Juli 2004 14:52 An: [EMAIL PROTECTED] Betreff: [R] aggregate function Hi all, I have the folowing frame(there are more columns than shown), 1 2 34 5 Year Total TusWhi Norw 1994 1.00 1830 0 355 1995 1.00 0 00 1995 1.00 0 00 1995 1.00 49104280 695 1997 1.00 0 0 110 1997 0.58 0 00 1997 1.00 0 00 1994 1.00 0 00 1997 1.00 0 40 70 1998 1.00 0 0 1252 1999 1.04 0 740 1999 1.00 0 00 1999 1.02 0 00 1999 1.00 0 00 1999 1.00 0 0 171 1999 1.00 1794 0 229 1999 1.00 035250 1997 1.00 13351185 147 1997 1.00 49251057 4801 1997 1.00 06275 1773 I try to get sum(Total) by Year in which Tus0, sum(Total) by Year in which Whi0,,,and so on. I have done something like this; a-as.list(numeric(3)) for (i in 3:5) { a[[i]]-aggregate(frame[,Total],list(Year=frame$Year, Tus=frame$i0),sum) } But I get Error in FUN(X[[as.integer(1)]], ...) : arguments must have same length Also by doing one by one aggregate(frame[,Total],list(Year=frame$Year, Tus=frame$Tus0),sum) The result is something like; Year Tus x 1994 FALSE 49.69 1995 FALSE 49.35 1996 FALSE 56.95 1997 FALSE 57.00 1998 FALSE 57.00 1999 FALSE 58.09 2000 FALSE 56.97 2001 FALSE 57.95 2002 FALSE 57.10 2003 FALSE 56.16 2000 TRUE 1.00 2002 TRUE 1.00 2003 TRUE 2.01 Help Thank you Luis Ridao Cruz Fiskirannsóknarstovan Nóatún 1 P.O. Box 3051 FR-110 Tórshavn Faroe Islands Phone: +298 353900 Phone(direct): +298 353912 Mobile: +298 580800 Fax: +298 353901 E-mail: [EMAIL PROTECTED] Web:www.frs.fo __ [EMAIL PROTECTED] mailing list https://www.stat.math.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://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] aggregate function
Hi, # x ... your frame attach(x) sum(Total[Year==1997 Tus 0]) I hope this helps Best, Matthias Templ -Ursprüngliche Nachricht- Von: Luis Rideau Cruz [mailto:[EMAIL PROTECTED] Gesendet: Montag, 26. Juli 2004 14:52 An: [EMAIL PROTECTED] Betreff: [R] aggregate function Hi all, I have the folowing frame(there are more columns than shown), 1 2 34 5 Year Total TusWhi Norw 1994 1.00 1830 0 355 1995 1.00 0 00 1995 1.00 0 00 1995 1.00 49104280 695 1997 1.00 0 0 110 1997 0.58 0 00 1997 1.00 0 00 1994 1.00 0 00 1997 1.00 0 40 70 1998 1.00 0 0 1252 1999 1.04 0 740 1999 1.00 0 00 1999 1.02 0 00 1999 1.00 0 00 1999 1.00 0 0 171 1999 1.00 1794 0 229 1999 1.00 035250 1997 1.00 13351185 147 1997 1.00 49251057 4801 1997 1.00 06275 1773 I try to get sum(Total) by Year in which Tus0, sum(Total) by Year in which Whi0,,,and so on. I have done something like this; a-as.list(numeric(3)) for (i in 3:5) { a[[i]]-aggregate(frame[,Total],list(Year=frame$Year, Tus=frame$i0),sum) } But I get Error in FUN(X[[as.integer(1)]], ...) : arguments must have same length Also by doing one by one aggregate(frame[,Total],list(Year=frame$Year, Tus=frame$Tus0),sum) The result is something like; Year Tus x 1994 FALSE 49.69 1995 FALSE 49.35 1996 FALSE 56.95 1997 FALSE 57.00 1998 FALSE 57.00 1999 FALSE 58.09 2000 FALSE 56.97 2001 FALSE 57.95 2002 FALSE 57.10 2003 FALSE 56.16 2000 TRUE 1.00 2002 TRUE 1.00 2003 TRUE 2.01 Help Thank you Luis Ridao Cruz Fiskirannsóknarstovan Nóatún 1 P.O. Box 3051 FR-110 Tórshavn Faroe Islands Phone: +298 353900 Phone(direct): +298 353912 Mobile: +298 580800 Fax: +298 353901 E-mail: [EMAIL PROTECTED] Web:www.frs.fo __ [EMAIL PROTECTED] mailing list https://www.stat.math.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://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
RE: [R] aggregate function
I would try something like: lapply(frame[3:5], function(i) tapply(frame$Total[i0], frame$Year[i0], sum)) $Tus 1994 1995 1997 1999 1121 $Whi 1995 1997 1999 1.00 4.00 2.04 $Norw 1994 1995 1997 1998 1999 11512 HTH, Andy From: Luis Rideau Cruz Hi all, I have the folowing frame(there are more columns than shown), 1 2 34 5 Year Total TusWhi Norw 1994 1.00 1830 0 355 1995 1.00 0 00 1995 1.00 0 00 1995 1.00 49104280 695 1997 1.00 0 0 110 1997 0.58 0 00 1997 1.00 0 00 1994 1.00 0 00 1997 1.00 0 40 70 1998 1.00 0 0 1252 1999 1.04 0 740 1999 1.00 0 00 1999 1.02 0 00 1999 1.00 0 00 1999 1.00 0 0 171 1999 1.00 1794 0 229 1999 1.00 035250 1997 1.00 13351185 147 1997 1.00 49251057 4801 1997 1.00 06275 1773 I try to get sum(Total) by Year in which Tus0, sum(Total) by Year in which Whi0,,,and so on. I have done something like this; a-as.list(numeric(3)) for (i in 3:5) { a[[i]]-aggregate(frame[,Total],list(Year=frame$Year, Tus=frame$i0),sum) } But I get Error in FUN(X[[as.integer(1)]], ...) : arguments must have same length Also by doing one by one aggregate(frame[,Total],list(Year=frame$Year, Tus=frame$Tus0),sum) The result is something like; Year Tus x 1994 FALSE 49.69 1995 FALSE 49.35 1996 FALSE 56.95 1997 FALSE 57.00 1998 FALSE 57.00 1999 FALSE 58.09 2000 FALSE 56.97 2001 FALSE 57.95 2002 FALSE 57.10 2003 FALSE 56.16 2000 TRUE 1.00 2002 TRUE 1.00 2003 TRUE 2.01 Help Thank you Luis Ridao Cruz Fiskirannsóknarstovan Nóatún 1 P.O. Box 3051 FR-110 Tórshavn Faroe Islands Phone: +298 353900 Phone(direct): +298 353912 Mobile: +298 580800 Fax: +298 353901 E-mail: [EMAIL PROTECTED] Web:www.frs.fo __ [EMAIL PROTECTED] mailing list https://www.stat.math.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://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
RE: [R] R on AMD64 (Opteron)
Just one more thing for folks intending to try Opterons with 1 cpu: You'll probably want to use a NUMA kernel, rather than a SMP one. Cheers, Andy From: Prof Brian Ripley We are using Fedora Core 2 and some version(s) of SuSe Linux on various dual Opteron servers. We also have a copy of RHEL, but AFAIK are not currently using it. I've been using a dual Opteron 248 under FC2 I don't know that Windows XP 64-Bit Edition is actually released yet (although there have beem public betas). However, as Peter D says, one would need a suitable compiler, binutils etc and the MinGW project is unlikely to provide them any time soon (if ever, although the project's FAQ suggests that it does intend to). On Sat, 24 Jul 2004, Jose Quesada wrote: Also, I'm curious... Not that this would be my first choice for a server, but... Anyone running Windows XP 64-Bit Edition? Any success compiling R? On Sat, 24 Jul 2004 18:07:18 +1000, Andrew Robinson [EMAIL PROTECTED] wrote: Professor Ripley, which operating system are you using for these servers, please? Thanks, Andrew - Original Message - From: Prof Brian Ripley [EMAIL PROTECTED] Date: Saturday, July 24, 2004 5:41 pm Subject: Re: [R] R on AMD64 (Opteron) On Fri, 23 Jul 2004, Asselin Jerome wrote: Hi, I was wondering if anyone has had good experiences using R on Linux with dual AMD64 (Opteron) processors. I'm thinking of buying a couple of such servers, but I'd like to make sure R would work fine. The R Installation and Administration guide notes that there may be some problems with BLAS libraries. That's all I could find about R on AMD64. Actually it says with ATLAS BLAS, not generically. Please share your experience using R on AMD64. Quite a few people, including us, are using R on such servers routinelywith no problems at all. There are still some issues about how to squeeze the maximum performance out of them (e.g. which BLAS to use -- we are using Goto's -- and which compiler to use, e.g. Portland Group or Intel). -- 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 -- 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://www.stat.math.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://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] R on AMD64 (Opteron)
- Original Message - From: Liaw, Andy [EMAIL PROTECTED] To: 'Prof Brian Ripley' [EMAIL PROTECTED]; Jose Quesada [EMAIL PROTECTED] Cc: [EMAIL PROTECTED] Sent: Monday, July 26, 2004 9:18 AM Subject: RE: [R] R on AMD64 (Opteron) Just one more thing for folks intending to try Opterons with 1 cpu: You'll probably want to use a NUMA kernel, rather than a SMP one. Cheers, Andy Thanks for the advice, but is there another reason why you write this beside a large (I mean 8) number of CPUs? At http://lse.sourceforge.net/numa/faq/ I read, What is the difference between NUMA and SMP? The NUMA architecture was designed to surpass the scalability limits of the SMP architecture. With SMP, which stands for Symmetric Multi-Processing, all memory access are posted to the same shared memory bus. This works fine for a relatively small number of CPUs, but the problem with the shared bus appears when you have dozens, even hundreds, of CPUs competing for access to the shared memory bus. NUMA alleviates these bottlenecks by limiting the number of CPUs on any one memory bus, and connecting the various nodes by means of a high speed interconnect. __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] covariate selection in cox model (counting process)
On Mon, 26 Jul 2004, Mayeul KAUFFMANN wrote: Hello everyone, I am searching for a covariate selection procedure in a cox model formulated as a counting process. I use intervals, my formula looks like coxph(Surv(start,stop,status)~ x1+x2+...+cluster(id),robust=T) where id is a country code (I study occurence of civil wars from 1962 to 1997). I'd like something not based on p-values, since they have several flaws for this purpose. You may be out of luck. In the case of recurrent events coxph() is not using maximum likelihood or even maximum partial likelihood. It is maximising the quantity that (roughly speaking) would be the partial likelihood if the covariates explained all the cluster differences. Partial likelihood for single events does have an AIC analogue that works reasonably well (not surprisingly, since the partial likelihood is also a perfectly valid marginal likelihood for the ranks of the survival times). For recurrent events this isn't going to work. If you absolutely have to do covariate selection you may need to look for a maximum likelihood approach, such as a parametric model with random effects to describe the dependence. You might be able to use survreg() with frailty() terms. -thomas Thomas Lumley Assoc. Professor, Biostatistics [EMAIL PROTECTED] University of Washington, Seattle __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Read SPSS data (*.sav) in R 1.8.0 (ok) and R1.9.1(error)
On Mon, 26 Jul 2004, [iso-8859-1] Karl Knoblick wrote: Hallo! I read SPSS data in the following way: library(Hmisc) library(foreign) dat-spss.get(surv_abb.sav) In R1.9.1 I got the message: Error in all(arg == choices) : Object typeDate not found In R1.8.0 the same script works fine. Does anybody know a possibilty to read a SPSS file under R1.9.1? YOu should just be able to use read.spss in the foreign package. -thomas __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] binning a vector
Hello, I was wondering wether there's a function in R that takes two vectors (of same length) as input and computes mean values for bins (intervals) or even a sliding window over these vectros. I've several x/y data set (input/response) that I'd like plot together. Say the x-data for one data set goes from -5 to 14 with 12,000 values, then I'd like to bin the x-vector in steps of +1 and calculate and plot the mean of the x-values and the y-values within each bin. I was browsing the R-docs but couldn't find anything appropiate. thanks for hints + kind regads, Arne __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] choosing constraints for function optim method=L-BFGS-B when they are in terms of other parameter values
I have a function of several variables which I wish to minimise over four variables, two of the upper bounds for which are defined in terms of other variables in the model over which minimisation will take place. I cannot work out how to code this in such a way as to avoid getting an error message when I run the code. If anyone can provide any assistance I will be most grateful. Best Regards Tom Stone __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] help(package)-sink()
On Sun, 25 Jul 2004, Thomas Lumley wrote: On Sat, 24 Jul 2004, Spencer Graves wrote: 4. A request for packageInfo.print returned object ... not found. I think someone may have been contaminated by Java or some such. It should be print.packageInfo A request for class(mclustInfo) confirmed that it was a packageInfo object, so I tried getMethod(print, packageInfo); I got, 'No generic function defined for print'. Then I tried, getMethod(show, packageInfo); I got, 'No method defined for function show and signature object = packageInfo'. For S3 methods you need getS3method(print,packageInfo) rather than getMethod. People often recommend getAnywhere(print.packageInfo), which does take less typing, but I prefer getS3method. They are not exactly equivalent, though. Although I know of no actual examples, it is possible to register something like printPackageInfo() as the S3 method for print() for class packageInfo. Then getS3method will work and getAnywhere will not. The advantage of getAnywhere is that it is blunderbuss designed to pick up all possible matches for any sort of R object, which can be useful. -- 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://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] installing problems repeated.tgz linux
Hi, i try several possibilities adn looking in the archive, but didn't getting success to install j.lindsey's usefuel library repeated on my linux (suse9.0 with kernel 2.6.7,R.1.9.1) P.S. Windows, works fine Many thanks for help Christian [EMAIL PROTECTED]:/space/downs R CMD INSTALL - l /usr/lib/R/library repeated WARNING: invalid package '-' WARNING: invalid package 'l' WARNING: invalid package '/usr/lib/R/library' * Installing *source* package 'repeated' ... ** libs /usr/lib/R/share/make/shlib.mk:5: *** Target-Muster enthält kein »%«. Schluss. ERROR: compilation failed for package 'repeated' ** Removing '/usr/lib/R/library/repeated' __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] binning a vector
On Monday 26 July 2004 10:11, [EMAIL PROTECTED] wrote: Hello, I was wondering wether there's a function in R that takes two vectors (of same length) as input and computes mean values for bins (intervals) or even a sliding window over these vectros. I've several x/y data set (input/response) that I'd like plot together. Say the x-data for one data set goes from -5 to 14 with 12,000 values, then I'd like to bin the x-vector in steps of +1 and calculate and plot the mean of the x-values and the y-values within each bin. I was browsing the R-docs but couldn't find anything appropiate. Do you know about loess? It's not exactly what you describe, but maybe it's what you really want. Deepayan __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] zsh and R
In the process of evaluating new shells, I've run into a few problems with zsh and the R CMD build, R CMD check scripts. I'd like to ask a few questions off-line if anyone has experience with R and the zsh completion/substitution functionality. Note that bash continues to work as well as ever, just that zsh is being finicky. best, -tony -- Anthony Rossini Research Associate Professor [EMAIL PROTECTED]http://www.analytics.washington.edu/ Biomedical and Health Informatics University of Washington Biostatistics, SCHARP/HVTN Fred Hutchinson Cancer Research Center UW (Tu/Th/F): 206-616-7630 FAX=206-543-3461 | Voicemail is unreliable FHCRC (M/W): 206-667-7025 FAX=206-667-4812 | use Email CONFIDENTIALITY NOTICE: This e-mail message and any attachme...{{dropped}} __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
RE: [R] installing problems repeated.tgz linux
From: Christian Schulz Hi, i try several possibilities adn looking in the archive, but didn't getting success to install j.lindsey's usefuel library repeated on my linux (suse9.0 with kernel 2.6.7,R.1.9.1) P.S. Windows, works fine Many thanks for help Christian R CMD INSTALL - l /usr/lib/R/library repeated ^ Try again without that space. Andy __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] factanal - rotation = oblimin
Hi list. To the best of mylimited understandig currently R (unlike S) does not support oblimin criterion for exploratory factor analysis. Searching through the contributed packages I did not notice any additional package for factor analysis. Does anybody know if such function is present within any package? Saluti, Antonio Prioglio -- We are what we repeatedly do. Excellence, then, is not an act, but a habit. Aristoteles /\ \ /ASCII RIBBON CAMPAIGN - AGAINST HTML MAIL X - AGAINST MS ATTACHMENTS / \ http://www.gnu.org/philosophy/no-word-attachments.html __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Building Windows Package
I am using R-1.9.1 with windows 2000 and trying to build a package. However, when I issue the command: RCMD build --binary BSDA I get: Building/Updating help pages for package 'BSDA' Formats: chm hhc: not found cp: cannot stat `C:/R191/R191/JUNK/BSDA/chm/BSDA.chm': No such file or direc tory make[1]: *** [chm-BSDA] Error 1 make: *** [pkg-BSDA] Error 2 *** Installation of BSDA failed *** My path is: .;C:\RStools;C:\MinGW\bin;C:\perl\bin;C:\texmf\miktex\bin;C:\Rstools\zip.exe; C:\Rstools\unzip.exe;C:\HTMLws\hhc.exe;C:\R191\R191\bin;%SystemRoot%\system32; %SystemRoot%;%SystemRoot%\System32\Wbem;C:\Program Files\CommonFiles\AdaptecShared\System; C:\Program Files\ggobi;C:\Program Files\R\rw1091\library\Rggobi\libs (HTML Help Workshop lives in- C:\HTMLws\hhc.exe) I have the directory for HTML Help workshop in MkRules set as: # Where does 'HTML Help Workshop' live? (unused if compiled HTML help is # not requested. Spaces allowed.) HHWDIR=C:/HTMLws After I issue RCMD build --binary BSDA and get the error messages, if I go to `C:/R191/R191/JUNK/BSDA/chm/BSDA.hhp' and manually compile the file (with HTML Help workshop) then issue the command RCMD build --binary BSDA again...the package builds without problems. Any ideas what I am doing wrong? Thanks in advance for the help. Alan Alan T. Arnholt Associate Professor Dept. of Mathematical Sciences Appalachian State University 2003-2004 International Exchange Scholar Universidad Publica de Navarra - Nafarroako Unibertsitate Publikoa Pamplona, Spain TEL : +34 948 169 205 CELL: +34 656 668 621 __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] installing problems repeated.tgz linux
On Mon, 2004-07-26 at 09:34, Christian Schulz wrote: Hi, i try several possibilities adn looking in the archive, but didn't getting success to install j.lindsey's usefuel library repeated on my linux (suse9.0 with kernel 2.6.7,R.1.9.1) P.S. Windows, works fine Many thanks for help Christian [EMAIL PROTECTED]:/space/downs R CMD INSTALL - l /usr/lib/R/library repeated WARNING: invalid package '-' WARNING: invalid package 'l' WARNING: invalid package '/usr/lib/R/library' * Installing *source* package 'repeated' ... ** libs /usr/lib/R/share/make/shlib.mk:5: *** Target-Muster enthlt kein %. Schluss. ERROR: compilation failed for package 'repeated' ** Removing '/usr/lib/R/library/repeated' Christian, There is a space (' ') between the '-' and the 'l', which will be parsed as two separate arguments. Hence the initial WARNING messages. You need to use: R CMD INSTALL -l /usr/lib/R/library repeated Also note that you need to have 'root' privileges in order to install the packages into the /usr/lib/R tree. Thus, you should 'su' to root before running the command. You should verify that your R tree is in /usr/lib, as the default is /usr/local/lib, for which you would not require the '-l /usr/lib/R/library' argument. Presumably Windows worked fine because you typically do not require administrator privileges to install the package locally on Windows or your account has administrative privileges, which is typical (and bad) on Windows NT/XP. HTH, Marc Schwartz __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] ordering of levels.
Hi! Have the following factors with the following levels. tmp$norm [1] rank rank rank rank rank log log log rank sqrt sqrt sqrt log log rank [16] rank rank sqrt sqrt sqrt sqrt log log log log sqrt none none none none [31] none none none none sqrt none Levels: log none rank sqrt I would like to add an ordering to the levels. nonesqrtlogrank I tried with tmp$norm -factor(tmp$norm,labels = c(none,sqrt,log,rank),ordered=T) tmp$norm [1] log log log log log none none none log rank rank rank none none log [16] log log rank rank rank rank none none none none rank sqrt sqrt sqrt sqrt [31] sqrt sqrt sqrt sqrt rank sqrt Levels: none sqrt log rank But this is not what I would like to have because the command not only superimposes an ordering but also changes the factors! Eryk __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
RE: [R] installing problems repeated.tgz linux
Sorry, Christian. I have no idea what those error messages in German say. Andy From: [EMAIL PROTECTED] Hello, thanks for your and Marc's hint, but it seems not the probleme!? Is there any probleme with my make? many thanks and regards, christian [EMAIL PROTECTED]:/usr/lib/R R CMD INSTALL -l /usr/lib/R/library /space/downs/repeated.tgz * Installing *source* package 'repeated' ... ** libs /usr/lib/R/share/make/shlib.mk:5: *** Target-Muster enthält kein »%«. Schluss. ERROR: compilation failed for package 'repeated' ** Removing '/usr/lib/R/library/repeated' [EMAIL PROTECTED]:/usr/lib/R R CMD INSTALL -l /usr/lib/R/library /space/downs/repeated * Installing *source* package 'repeated' ... ** libs /usr/lib/R/share/make/shlib.mk:5: *** Target-Muster enthält kein »%«. Schluss. ERROR: compilation failed for package 'repeated' ** Removing '/usr/lib/R/library/repeated' ...with your great RandomForest and other packages it works! [EMAIL PROTECTED]:/usr/lib/R R CMD INSTALL -l /usr/lib/R/library /space/downs/randomForest*.tar.gz * Installing *source* package 'randomForest' ... ** libs gcc -I/usr/lib/R/include -I/usr/local/include -I/opt/gnome/include -D__NO_MATH_INLINES -mieee-fp -fPIC -c regrf.c -o regrf.o g77 -mieee-fp -fPIC -c regrfsub.f -o regrfsub.o gcc -I/usr/lib/R/include -I/usr/local/include -I/opt/gnome/include -D__NO_MATH_INLINES -mieee-fp -fPIC -c rf.c -o rf.o g77 -mieee-fp -fPIC -c rfsub.f -o rfsub.o gcc -shared -L/usr/local/lib -L/opt/gnome/lib -o randomForest.so regrf.o regrfsub.o rf.o rfsub.o -L/usr/local/lib -L/opt/gnome/lib -L/usr/lib/gcc-lib/i586-suse-linux/3.3.1 -L/usr/lib/gcc-lib/i586-suse-linux/3.3.1/../../../../i586-suse -linux/lib -L/usr/lib/gcc-lib/i586-suse-linux/3.3.1/../../.. -lfrtbegin -lg2c -lm -lgcc_s -L/usr/lib/R/bin -lR ** R ** inst ** help Building/Updating help pages for package 'randomForest' Formats: text html latex example MDSplot texthtmllatex example combine texthtmllatex example getTree texthtmllatex example grow texthtmllatex example importancetexthtmllatex margintexthtmllatex example na.roughfix texthtmllatex example partialPlot texthtmllatex example plot.randomForest texthtmllatex example predict.randomForest texthtmllatex example randomForest texthtmllatex example rfImpute texthtmllatex example treesize texthtmllatex example tuneRFtexthtmllatex example varImpPlottexthtmllatex example varUsed texthtmllatex example * DONE (randomForest) Am Montag, 26. Juli 2004 18:56 schrieb Liaw, Andy: From: Christian Schulz Hi, i try several possibilities adn looking in the archive, but didn't getting success to install j.lindsey's usefuel library repeated on my linux (suse9.0 with kernel 2.6.7,R.1.9.1) P.S. Windows, works fine Many thanks for help Christian R CMD INSTALL - l /usr/lib/R/library repeated ^ Try again without that space. Andy -- - --- Notice: This e-mail message, together with any attachments, contains information of Merck Co., Inc. (One Merck Drive, Whitehouse Station, New Jersey, USA 08889), and/or its affiliates (which may be known outside the United States as Merck Frosst, Merck Sharp Dohme or MSD and in Japan, as Banyu) that may be confidential, proprietary copyrighted and/or legally privileged. It is intended solely for the use of the individual or entity named on this message. If you are not the intended recipient, and have received this message in error, please notify us immediately by reply e-mail and then delete it from your system. -- - --- __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] ordering of levels.
Wolski wrote: Hi! Have the following factors with the following levels. tmp$norm [1] rank rank rank rank rank log log log rank sqrt sqrt sqrt log log rank [16] rank rank sqrt sqrt sqrt sqrt log log log log sqrt none none none none [31] none none none none sqrt none Levels: log none rank sqrt I would like to add an ordering to the levels. nonesqrtlogrank I tried with tmp$norm -factor(tmp$norm,labels = c(none,sqrt,log,rank),ordered=T) tmp$norm [1] log log log log log none none none log rank rank rank none none log [16] log log rank rank rank rank none none none none rank sqrt sqrt sqrt sqrt [31] sqrt sqrt sqrt sqrt rank sqrt Levels: none sqrt log rank But this is not what I would like to have because the command not only superimposes an ordering but also changes the factors! Eryk Eryk, See ?factor or ?ordered which will help. I think what you want is: lev - c(none, sqrt, log, rank) tmp$norm - ordered(tmp$norm, levels = lev) or tmp$norm - factor(tmp$norm, levels = lev, ordered = TRUE) Note the use of levels and not labels. --sundar __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
RE: [R] aggregate function
[Sorry if this gets posted twice. I have been having some problems with gmane posting.] We can use rowsum like this: rowsum(frame$Total * (frame[,3:5]0), frame$Year) Tus Whi Norw 1994 1 0.00 1 1995 1 1.00 1 1997 2 4.00 5 1998 0 0.00 1 1999 1 2.04 2 Note that only years that are actually present will be in the resulting matrix. 1996 is not in the sample data in your post so there is no row for 1996. If that's not a problem or if your real data covers all the years anyways we are done. If missing years is a problem then merge in some zero rows with the years first. The first two lines below do this and the third line is the same as the line above: frame - merge(frame, 1994:1999, by = 1, all = TRUE) frame[is.na(frame)] - 0 rowsum(frame$Total * (frame[,3:5]0), frame$Year) Tus Whi Norw 1994 1 0.00 1 1995 1 1.00 1 1996 0 0.00 0 -- now we have a row for 1996 1997 2 4.00 5 1998 0 0.00 1 1999 1 2.04 2 Luis Rideau Cruz [EMAIL PROTECTED] : I have the folowing frame(there are more columns than shown), 1 2 3 4 5 Year Total Tus Whi Norw 1994 1.00 1830 0 355 1995 1.00 0 0 0 1995 1.00 0 0 0 1995 1.00 4910 4280 695 1997 1.00 0 0 110 1997 0.58 0 0 0 1997 1.00 0 0 0 1994 1.00 0 0 0 1997 1.00 0 40 70 1998 1.00 0 0 1252 1999 1.04 0 74 0 1999 1.00 0 0 0 1999 1.02 0 0 0 1999 1.00 0 0 0 1999 1.00 0 0 171 1999 1.00 1794 0 229 1999 1.00 0 3525 0 1997 1.00 1335 1185 147 1997 1.00 4925 1057 4801 1997 1.00 0 6275 1773 I try to get sum(Total) by Year in which Tus0, sum(Total) by Year in which Whi0,,,and so on. I have done something like this; a-as.list(numeric(3)) for (i in 3:5) { a[[i]]-aggregate(frame[,Total],list(Year=frame$Year, Tus=frame$i0),sum) } But I get Error in FUN(X[[as.integer(1)]], ...) : arguments must have same length Also by doing one by one aggregate(frame[,Total],list(Year=frame$Year, Tus=frame$Tus0),sum) The result is something like; Year Tus x 1994 FALSE 49.69 1995 FALSE 49.35 1996 FALSE 56.95 1997 FALSE 57.00 1998 FALSE 57.00 1999 FALSE 58.09 2000 FALSE 56.97 2001 FALSE 57.95 2002 FALSE 57.10 2003 FALSE 56.16 2000 TRUE 1.00 2002 TRUE 1.00 2003 TRUE 2.01 __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
RE: [R] installing problems repeated.tgz linux
I downloaded repeated.tgz and tried it myself on one of our AMD Opterons running SLES8, and it worked (R-1.9.1 compiled as 64-bit). Notice that I do get a couple of warnings from gcc about labels, and from g77 about the use of `sum' function. Andy [EMAIL PROTECTED]:lindsey]% R CMD INSTALL -l ~/rlibs repeated * Installing *source* package 'repeated' ... ** libs g77 -fPIC -O2 -m64 -msse2 -march=k8 -mcpu=k8 -g -c chidden.f -o chidden.o g77 -fPIC -O2 -m64 -msse2 -march=k8 -mcpu=k8 -g -c cphidden.f -o cphidden.o gcc -I/usr/local/lib/R/include -I/usr/local/include -fPIC -O7 -m64 -msse2 -march=k8 -mcpu=k8 -g -c cutil.c -o cutil.o gcc -I/usr/local/lib/R/include -I/usr/local/include -fPIC -O7 -m64 -msse2 -march=k8 -mcpu=k8 -g -c dist.c -o dist.o gcc -I/usr/local/lib/R/include -I/usr/local/include -fPIC -O7 -m64 -msse2 -march=k8 -mcpu=k8 -g -c gar.c -o gar.o g77 -fPIC -O2 -m64 -msse2 -march=k8 -mcpu=k8 -g -c hidden.f -o hidden.o gcc -I/usr/local/lib/R/include -I/usr/local/include -fPIC -O7 -m64 -msse2 -march=k8 -mcpu=k8 -g -c kcountb.c -o kcountb.o kcountb.c: In function `kcountb': kcountb.c:263: warning: deprecated use of label at end of compound statement kcountb.c:270: warning: deprecated use of label at end of compound statement gcc -I/usr/local/lib/R/include -I/usr/local/include -fPIC -O7 -m64 -msse2 -march=k8 -mcpu=k8 -g -c kserieb.c -o kserieb.o g77 -fPIC -O2 -m64 -msse2 -march=k8 -mcpu=k8 -g -c logitord.f -o logitord.o g77 -fPIC -O2 -m64 -msse2 -march=k8 -mcpu=k8 -g -c binnest.f -o binnest.o binnest.f: In subroutine `calcbn': binnest.f:537: warning: J_Prod = J_Prod * Sum(H2,uph2) ! Calculate the product of J ^ Reference to unimplemented intrinsic `SUM' at (^) (assumed EXTERNAL) binnest.f: In subroutine `calcbn2': binnest.f:1255: warning: J_Prod = J_Prod * Sum(H2,uph2) ! Calculate the product of J ^ Reference to unimplemented intrinsic `SUM' at (^) (assumed EXTERNAL) g77 -fPIC -O2 -m64 -msse2 -march=k8 -mcpu=k8 -g -c gausscop.f -o gausscop.o gcc -I/usr/local/lib/R/include -I/usr/local/include -fPIC -O7 -m64 -msse2 -march=k8 -mcpu=k8 -g -c gaps.c -o gaps.o gcc -I/usr/local/lib/R/include -I/usr/local/include -fPIC -O7 -m64 -msse2 -march=k8 -mcpu=k8 -g -c calcs.c -o calcs.o gcc -I/usr/local/lib/R/include -I/usr/local/include -fPIC -O7 -m64 -msse2 -march=k8 -mcpu=k8 -g -c calcs1.c -o calcs1.o gcc -I/usr/local/lib/R/include -I/usr/local/include -fPIC -O7 -m64 -msse2 -march=k8 -mcpu=k8 -g -c calcs2.c -o calcs2.o gcc -I/usr/local/lib/R/include -I/usr/local/include -fPIC -O7 -m64 -msse2 -march=k8 -mcpu=k8 -g -c calcs3.c -o calcs3.o gcc -I/usr/local/lib/R/include -I/usr/local/include -fPIC -O7 -m64 -msse2 -march=k8 -mcpu=k8 -g -c calcs4.c -o calcs4.o gcc -shared -o repeated.so chidden.o cphidden.o cutil.o dist.o gar.o hidden.o kcountb.o kserieb.o logitord.o binnest.o gausscop.o gaps.o calcs.o calcs1.o calcs2.o calcs3.o calcs4.o -L/usr/local/lib -L/opt/gcc33/lib64/gcc-lib/x86_64-suse-linux/3.3 -L/opt/gcc33/lib64/gcc-lib/x86_64-suse-linux/3.3/../../../../lib64 -L/opt/gcc33/lib64/gcc-lib/x86_64-suse-linux/3.3/../../.. -L/lib/../lib64 -L/usr/lib/../lib64 -lfrtbegin -lg2c -lm -lgcc_s ** R ** help Building/Updating help pages for package 'repeated' Formats: text html latex example [snipped. I think you get the idea...] From: Liaw, Andy Sorry, Christian. I have no idea what those error messages in German say. Andy From: [EMAIL PROTECTED] Hello, thanks for your and Marc's hint, but it seems not the probleme!? Is there any probleme with my make? many thanks and regards, christian [EMAIL PROTECTED]:/usr/lib/R R CMD INSTALL -l /usr/lib/R/library /space/downs/repeated.tgz * Installing *source* package 'repeated' ... ** libs /usr/lib/R/share/make/shlib.mk:5: *** Target-Muster enthält kein »%«. Schluss. ERROR: compilation failed for package 'repeated' ** Removing '/usr/lib/R/library/repeated' [EMAIL PROTECTED]:/usr/lib/R R CMD INSTALL -l /usr/lib/R/library /space/downs/repeated * Installing *source* package 'repeated' ... ** libs /usr/lib/R/share/make/shlib.mk:5: *** Target-Muster enthält kein »%«. Schluss. ERROR: compilation failed for package 'repeated' ** Removing '/usr/lib/R/library/repeated' ...with your great RandomForest and other packages it works! [EMAIL PROTECTED]:/usr/lib/R R CMD INSTALL -l /usr/lib/R/library /space/downs/randomForest*.tar.gz * Installing *source* package 'randomForest' ... ** libs gcc -I/usr/lib/R/include -I/usr/local/include -I/opt/gnome/include -D__NO_MATH_INLINES -mieee-fp -fPIC -c regrf.c -o regrf.o g77 -mieee-fp -fPIC -c regrfsub.f -o regrfsub.o gcc -I/usr/lib/R/include -I/usr/local/include -I/opt/gnome/include -D__NO_MATH_INLINES -mieee-fp -fPIC -c rf.c -o rf.o g77
Re: [R] ordering of levels.
Hi! Thanks a lot. Eryk *** REPLY SEPARATOR *** On 7/26/2004 at 2:07 PM Sundar Dorai-Raj wrote: Wolski wrote: Hi! Have the following factors with the following levels. tmp$norm [1] rank rank rank rank rank log log log rank sqrt sqrt sqrt log log rank [16] rank rank sqrt sqrt sqrt sqrt log log log log sqrt none none none none [31] none none none none sqrt none Levels: log none rank sqrt I would like to add an ordering to the levels. nonesqrtlogrank I tried with tmp$norm -factor(tmp$norm,labels = c(none,sqrt,log,rank),ordered=T) tmp$norm [1] log log log log log none none none log rank rank rank none none log [16] log log rank rank rank rank none none none none rank sqrt sqrt sqrt sqrt [31] sqrt sqrt sqrt sqrt rank sqrt Levels: none sqrt log rank But this is not what I would like to have because the command not only superimposes an ordering but also changes the factors! Eryk Eryk, See ?factor or ?ordered which will help. I think what you want is: lev - c(none, sqrt, log, rank) tmp$norm - ordered(tmp$norm, levels = lev) or tmp$norm - factor(tmp$norm, levels = lev, ordered = TRUE) Note the use of levels and not labels. --sundar Dipl. bio-chem. Eryk Witold Wolski@MPI-Moleculare Genetic Ihnestrasse 63-73 14195 Berlin 'v' tel: 0049-30-83875219 / \ mail: [EMAIL PROTECTED]---W-Whttp://www.molgen.mpg.de/~wolski __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Building Windows Package
You want the directory in your path specification, not the executables. As in .;C:\RStools;C:\MinGW\bin;C:\perl\bin;C:\texmf\miktex\bin; C:\HTMLws;C:\R191\R191\bin;%SystemRoot%\system32; %SystemRoot%;%SystemRoot%\System32\Wbem;C:\Program Files\CommonFiles\AdaptecShared\System; C:\Program Files\ggobi;C:\Program Files\R\rw1091\library\Rggobi\libs On Mon, 26 Jul 2004, Alan Arnholt wrote: I am using R-1.9.1 with windows 2000 and trying to build a package. However, when I issue the command: RCMD build --binary BSDA I get: Building/Updating help pages for package 'BSDA' Formats: chm hhc: not found cp: cannot stat `C:/R191/R191/JUNK/BSDA/chm/BSDA.chm': No such file or direc tory make[1]: *** [chm-BSDA] Error 1 make: *** [pkg-BSDA] Error 2 *** Installation of BSDA failed *** My path is: .;C:\RStools;C:\MinGW\bin;C:\perl\bin;C:\texmf\miktex\bin;C:\Rstools\zip.exe; C:\Rstools\unzip.exe;C:\HTMLws\hhc.exe;C:\R191\R191\bin;%SystemRoot%\system32; %SystemRoot%;%SystemRoot%\System32\Wbem;C:\Program Files\CommonFiles\AdaptecShared\System; C:\Program Files\ggobi;C:\Program Files\R\rw1091\library\Rggobi\libs (HTML Help Workshop lives in- C:\HTMLws\hhc.exe) I have the directory for HTML Help workshop in MkRules set as: # Where does 'HTML Help Workshop' live? (unused if compiled HTML help is # not requested. Spaces allowed.) HHWDIR=C:/HTMLws After I issue RCMD build --binary BSDA and get the error messages, if I go to `C:/R191/R191/JUNK/BSDA/chm/BSDA.hhp' and manually compile the file (with HTML Help workshop) then issue the command RCMD build --binary BSDA again...the package builds without problems. Any ideas what I am doing wrong? Thanks in advance for the help. Alan Alan T. Arnholt Associate Professor Dept. of Mathematical Sciences Appalachian State University 2003-2004 International Exchange Scholar Universidad Publica de Navarra - Nafarroako Unibertsitate Publikoa Pamplona, Spain TEL : +34 948 169 205 CELL: +34 656 668 621 __ [EMAIL PROTECTED] mailing list https://www.stat.math.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://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
RE: [R] installing problems repeated.tgz linux
I echo Andy's experience on FC2. I was able to install the package here and got the same warning messages. Despite trying to use some web sites to translate the german text, I am unsure of the 'true' meaning. I think it is something pertaining to target patterns not being found, which leads me to think that this might be a locale/character encoding issue in the package. Anyone? Marc On Mon, 2004-07-26 at 14:16, Liaw, Andy wrote: I downloaded repeated.tgz and tried it myself on one of our AMD Opterons running SLES8, and it worked (R-1.9.1 compiled as 64-bit). Notice that I do get a couple of warnings from gcc about labels, and from g77 about the use of `sum' function. Andy SNIPPED From: Liaw, Andy Sorry, Christian. I have no idea what those error messages in German say. Andy From: [EMAIL PROTECTED] Hello, thanks for your and Marc's hint, but it seems not the probleme!? Is there any probleme with my make? many thanks and regards, christian [EMAIL PROTECTED]:/usr/lib/R R CMD INSTALL -l /usr/lib/R/library /space/downs/repeated.tgz * Installing *source* package 'repeated' ... ** libs /usr/lib/R/share/make/shlib.mk:5: *** Target-Muster enthlt kein %. Schluss. ERROR: compilation failed for package 'repeated' ** Removing '/usr/lib/R/library/repeated' [EMAIL PROTECTED]:/usr/lib/R R CMD INSTALL -l /usr/lib/R/library /space/downs/repeated * Installing *source* package 'repeated' ... ** libs /usr/lib/R/share/make/shlib.mk:5: *** Target-Muster enthlt kein %. Schluss. ERROR: compilation failed for package 'repeated' ** Removing '/usr/lib/R/library/repeated' SNIPPED __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
RE: [R] choosing constraints for function optim method=L-BFGS-B whenthey are in terms of other parameter values
Hi Tom, I am not entirely sure what the problem, you haven't been very specific. If you want general linear constraints on your parameters, ie linear combinations of parameters summing to some value, constrOptim may be of help. hth, ingmar Ingmar Visser Developmental Processes Research Group Department of Psychology University of Amsterdam http://users.fmg.uva.nl/ivisser/ -Original Message- From: [EMAIL PROTECTED] on behalf of Tom Stone Sent: Mon 7/26/2004 4:57 PM To: [EMAIL PROTECTED] Subject: [R] choosing constraints for function optim method=L-BFGS-B whenthey are in terms of other parameter values I have a function of several variables which I wish to minimise over four variables, two of the upper bounds for which are defined in terms of other variables in the model over which minimisation will take place. I cannot work out how to code this in such a way as to avoid getting an error message when I run the code. If anyone can provide any assistance I will be most grateful. Best Regards Tom Stone __ [EMAIL PROTECTED] mailing list https://www.stat.math.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://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] spec.pgram() possible bug
test=spec.pgram(rnorm(128,0,1), kernel(daniell,1)) test$df [1] 5.374771 df should be 6= 2*(2*m+1) where m=1 in this case ... and so on __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Significance Test for Correlation Coefficients
Hello all, I have a set of microarray timeseries (approx. 18000 genes and 7 time points per gene) data that I have correlated with a template (a vector of length 7). I have also correlated random data from a normal distribution with the same mean and standard deviation as my data set with the template, as well as, correlating a random permutation of my data set with the template. So I now have 3 vectors of length 18000 contains correlation coefficients. I was wondering if there was a test in R to determine if the correlation coefficients are significantly different. In particular, I want to compare the correlation coefficients from my data set with each of the other two. Thank you for any help you can give me. Sincerely, Matt __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Problem with a while loop embedded in a function.
Hello all. I have been working on a (fairly simple) function for way too long. Ive really hit a wall and I was hoping someone might be able to point me in the right direction. I have (attempted) to create a function that has an embedded while loop. The while loop works fine by itself, however, when the while loop is embedded in the function, the function fails. Im not sure why this happens as the function really doesnt add much above and beyond the while loop. I believe it might have something to do with the list I define in the while loop as nlme.control.parms. Because I included print(nlme.control.parms) when the while loop runs by itself the paramers of nlme.control.parms can be seen to be fine. However, when I run the function print(nlme.control.parms) is full of NAs. Im not sure if the function fails because the list nlme.control.parms is full of NAs or if nlme.control.parms is full of NAs because the function failed. I should mention that the function is (supposed to be!) used with nlme so that multiple sets of parameters can be defined (each next set being less restrictive than the previous), and nlme runs until it outputs results given the particular set of parameters. The values I used in the simplified example that follows would never be used in a real situation, but for purposes of this illustrative example, the parameters are fine. The result should be a list of the nlme object and 'OK' (which should be 5 for the example). I'm using R version 1.9.1 on Windows XP. Thanks for any thoughts, Ken library(nlme) data(Loblolly) maxIter - c(1, 1, 1, 1, 1) returnObject - c(FALSE, FALSE, FALSE, FALSE, TRUE) nlsList.Object - nlsList(SSasymp, Loblolly) M1 - function(maxIter, returnObject) { ok - FALSE OK - 0 while(ok==FALSE) { OK - OK + 1 nlme.control.parms - list(maxIter=maxIter[OK], returnObject=returnObject[OK]) fm1 - try(nlme(nlsList.Object, fixed = Asym + R0 + lrc ~ 1, random = Asym ~ 1, control = nlme.control.parms), silent=TRUE) ok - is.numeric(fm1$numIter) print(OK) print(nlme.control.parms) } return(list(fm1, OK)) } Test - M1(maxIter=maxIter, returnObject=returnObject) - [[alternative HTML version deleted]] __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] spec.pgram() possible bug
Perhaps you could take the trouble to read the references (or the code)? Hint: do you know about tapering and how to work out its effect? On Mon, 26 Jul 2004, David Stoffer wrote: test=spec.pgram(rnorm(128,0,1), kernel(daniell,1)) test$df [1] 5.374771 df should be 6= 2*(2*m+1) where m=1 in this case ... and so on spec.pgram(rnorm(128,0,1), kernel(daniell,1), taper=0)$df [1] 6 is what you have calculated, inappropriately for the call you actually used. -- 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://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] binning a vector
Also, you can use cut and tapply to calculate means by bins. Andrew - Original Message - From: Deepayan Sarkar [EMAIL PROTECTED] Date: Tuesday, July 27, 2004 3:38 am Subject: Re: [R] binning a vector On Monday 26 July 2004 10:11, [EMAIL PROTECTED] wrote: Hello, I was wondering wether there's a function in R that takes two vectors (of same length) as input and computes mean values for bins (intervals) or even a sliding window over these vectros. I've several x/y data set (input/response) that I'd like plot together. Say the x-data for one data set goes from -5 to 14 with 12,000 values, then I'd like to bin the x-vector in steps of +1 and calculate and plot the mean of the x-values and the y-values within each bin. I was browsing the R-docs but couldn't find anything appropiate. Do you know about loess? It's not exactly what you describe, but maybe it's what you really want. Deepayan __ [EMAIL PROTECTED] mailing list https://www.stat.math.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://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Building Windows Package
Thanks. It works great now! Alan Alan T. Arnholt Associate Professor Dept. of Mathematical Sciences Appalachian State University 2003-2004 International Exchange Scholar Universidad Publica de Navarra - Nafarroako Unibertsitate Publikoa Pamplona, Spain TEL : +34 948 169 205 CELL: +34 656 668 621 On Mon, 26 Jul 2004, Prof Brian Ripley wrote: You want the directory in your path specification, not the executables. As in .;C:\RStools;C:\MinGW\bin;C:\perl\bin;C:\texmf\miktex\bin; C:\HTMLws;C:\R191\R191\bin;%SystemRoot%\system32; %SystemRoot%;%SystemRoot%\System32\Wbem;C:\Program Files\CommonFiles\AdaptecShared\System; C:\Program Files\ggobi;C:\Program Files\R\rw1091\library\Rggobi\libs On Mon, 26 Jul 2004, Alan Arnholt wrote: I am using R-1.9.1 with windows 2000 and trying to build a package. However, when I issue the command: RCMD build --binary BSDA I get: Building/Updating help pages for package 'BSDA' Formats: chm hhc: not found cp: cannot stat `C:/R191/R191/JUNK/BSDA/chm/BSDA.chm': No such file or direc tory make[1]: *** [chm-BSDA] Error 1 make: *** [pkg-BSDA] Error 2 *** Installation of BSDA failed *** My path is: .;C:\RStools;C:\MinGW\bin;C:\perl\bin;C:\texmf\miktex\bin;C:\Rstools\zip.exe; C:\Rstools\unzip.exe;C:\HTMLws\hhc.exe;C:\R191\R191\bin;%SystemRoot%\system32; %SystemRoot%;%SystemRoot%\System32\Wbem;C:\Program Files\CommonFiles\AdaptecShared\System; C:\Program Files\ggobi;C:\Program Files\R\rw1091\library\Rggobi\libs (HTML Help Workshop lives in- C:\HTMLws\hhc.exe) I have the directory for HTML Help workshop in MkRules set as: # Where does 'HTML Help Workshop' live? (unused if compiled HTML help is # not requested. Spaces allowed.) HHWDIR=C:/HTMLws After I issue RCMD build --binary BSDA and get the error messages, if I go to `C:/R191/R191/JUNK/BSDA/chm/BSDA.hhp' and manually compile the file (with HTML Help workshop) then issue the command RCMD build --binary BSDA again...the package builds without problems. Any ideas what I am doing wrong? Thanks in advance for the help. Alan Alan T. Arnholt Associate Professor Dept. of Mathematical Sciences Appalachian State University 2003-2004 International Exchange Scholar Universidad Publica de Navarra - Nafarroako Unibertsitate Publikoa Pamplona, Spain TEL : +34 948 169 205 CELL: +34 656 668 621 __ [EMAIL PROTECTED] mailing list https://www.stat.math.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://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
RE: [R] R on AMD64 (Opteron)
From: Jerome Asselin From: Liaw, Andy [EMAIL PROTECTED] Just one more thing for folks intending to try Opterons with 1 cpu: You'll probably want to use a NUMA kernel, rather than a SMP one. Cheers, Andy Thanks for the advice, but is there another reason why you write this beside a large (I mean 8) number of CPUs? At http://lse.sourceforge.net/numa/faq/ I read, What is the difference between NUMA and SMP? The NUMA architecture was designed to surpass the scalability limits of the SMP architecture. With SMP, which stands for Symmetric Multi-Processing, all memory access are posted to the same shared memory bus. This works fine for a relatively small number of CPUs, but the problem with the shared bus appears when you have dozens, even hundreds, of CPUs competing for access to the shared memory bus. NUMA alleviates these bottlenecks by limiting the number of CPUs on any one memory bus, and connecting the various nodes by means of a high speed interconnect. I was told by folks at Penguin Computing (where we bought our Opterons) and AMD that because of the way memory controller is integrated in the Opteron, when running two CPU intensive processes on a dual CPU box, one cpu will be at near 100% while the other will be only around 90%, if you use a SMP kernel. Indeed that's what we saw when we ran two R processes simultaneously. Switching to the NUMA kernel for the most part `solves' that problem. Andy __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] qcc package syndromic surveillance (multivar CUSUM?)
Dear R Community: I am working on a public health early warning system, and I see that the qcc package allows for CUSUM and other statistical quality tests but I am not sure if my project is a good match for qcc functions as written. Any advice you may have is very much appreciated. I have four years worth of daily counts of emergency room admissions for different conditions (e.g. respiratory, neurologic, etc) from several local hospitals. the data looks like this... DAY 1 Respiratory Neuro ... Hospital A: 1012 . . . . . . Hospital F:714 DAY 2 Respiratory Neuro ... Hospital A: 1012 . . . . . . Hospital F:714... etc., and my goal is to do a kind of multivariate quality control test (without fitting a GLM), that would run each day after the data is updated and be able to answer the question: Has there been a significant variation in the central tendency of the data? An analogous problem would be detecting the early signs of a shift in global trading patterns by examining stock market indexes in different countries around the world, updating and testing the data each business day. Thank you, Alexis Diamond __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] bad restore file magic number
I'm running R 1.9.1 and trying to load a macro I've written. It gives the e Error: bad restore file magic number (file may be corrupted)-- no data loaded what does this error mean, and how can I fix this problem. thanks, jordan __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] bad restore file magic number
I'm running R 1.9.1 and trying to load a macro I've written. It gives the e Error: bad restore file magic number (file may be corrupted)-- no data loaded You probably want to use source() here, if you have the code in a file. The load() command is for use with stuff saved via the save() command. -J __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] covariate selection in cox model (counting process)
Thank you a lot for your time and your answer, Thomas. Like all good answers, it raised new questions for me ;-) In the case of recurrent events coxph() is not using maximum likelihood or even maximum partial likelihood. It is maximising the quantity that (roughly speaking) would be the partial likelihood if the covariates explained all the cluster differences. I could have non repeating events by removing countries once they have experienced a war. But I'm not sure it will change the estimation procedure since this will change the dataset only, not the formula coxph(Surv(start,stop,status)~x1+x2+...+cluster(id),robust=T) I am not sure I understood you well: do you really mean recurrent events alone or any counting process notation (including allowing for recurrent events). I thought the counting process notation did not differ really from the Cox model in R, since Terry M. Therneau (A Package for Survival Analysis in S, April 22, 1996) concludes his mathematical section 3.3 Cox Model by The above notation is derived from the counting process representation [...] It allows very naturally for several extensions to the original Cox model formulation: multiple events per subject, discontinuous intervals of risk [...],left truncation. (I used it to introduce 1. time-dependent covariates, some covariates changing yearly, other irregularly, and 2. left truncation: not all countries existed at the beginning of the study) In the case of recurrent events coxph() is not using maximum likelihood or even maximum partial likelihood. Then, what does fit$loglik give in this case? Still a likelihood or a valid criterion to maximise ? If not, how to get (manually) the criterion that was maximsed? That's of interest for me since I created artificial covariates measuring the proximity since some events: exp(-days.since.event/a.chosen.parameter). ...and I used fit$loglik to chose a.chosen.parameter from 8 values, for 3 types of events: la-c(263.5, 526.9,1053.9,2107.8,4215.6,8431.1) #list of values to choose from z-NULL;for(a1 in la) for(a2 in la) for(a3 in la) {coxtmp - (coxph(Surv(start,stop,status)~ +I(exp(-days.since.event.of.type.one/a1)) +I(exp(-days.since.event.of.type.two/a2)) +I(exp(-days.since.event.of.type.three/a3)) + other.time.dependent.covariates +cluster(id) ,data=x,robust=T)) rbind(z,c(a1,a2,a3,coxtmp$wald.test, coxtmp$rscore, coxtmp$loglik, coxtmp$score))-z } z - data.frame(z) names(z) - c(a1,a2, a3,wald.test, rscore, NULLloglik,loglik, score) z[which.max(z$rscore),] z[which.max(z$loglik),] The last two commands gave me almost always the same set for c(a1,a2,a3). But they sometimes differed significantly on some models. Which criteria (if any ?!) should I use to select the best set c(a1,a2,a3) ? (If you wish to see what the proximity variables look like, run the following code. The dashed lines show the half life of the proximity variable,here=6 months, which is determined by a.chosen.parameter, e.g. a1=la[1]: #start of code curve(exp(-(x)/263.5),0,8*365.25,xlab=number of days since last political regime change (dsrc),ylab=Proximity of political regime change = exp(-dsrc/263.5),las=1) axis(1,at=365.25/2, labels= (6 months));axis(2,at=seq(0,1,.1),las=1) lines(c(365.25/2,365.25/2,-110),c(-.05,0.5,0.5),lty=dashed) #end of code) Thanks a lot again. Mayeul KAUFFMANN Univ. Pierre Mendes France Grenoble - France __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] lattice / pdf bug ?
I've been scrathing my head over this one. Suppose I have a data.frame which maps to a 'n x k' lattice, and that one of those cells is empty. An artificial example is generated by Q-data.frame(x1=sample(c(A,B),10,replace=TRUE), x2=c(C, rep(D,9)), y=rnorm(10)) where by having only one obs. for the first level of the second factor x2, we ensure that there won't be full combinations of x1 and x2. This seems to trip panel.mathdensity(), but only when printing to pdf, and I can't find a way to avoid it. Consider stopifnot(require(lattice)) stopifnot(require(grid)) pdf(testfile.pdf) Q-data.frame(x1=sample(c(A,B),10,replace=TRUE), x2=c(C, rep(D,9)), y=rnorm(10)) print(histogram(~ y | x1+x2, data=Q, panel = function(x, ...) { if (length(x) 0) { panel.histogram(x, ...) panel.mathdensity(dmath = dnorm, col = black, args = list(mean=mean(x, na.rm=TRUE), sd=sd(x, na.rm=TRUE))) } })) dev.off() where the resulting pdf file is broken if and only if the panel.mathdensity call is present. Without it, it works. To the screen, it works with and without -- but copying to pdf again breaks the pdf file if panel.mathdensity is used. It is possible that I am overlooking something simple -- or is it a genuine bug? Platform is win2k, R version is 1.9.1. Thanks for any pointers, Dirk -- Those are my principles, and if you don't like them... well, I have others. -- Groucho Marx __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] binning a vector
?tapply *** REPLY SEPARATOR *** On 7/26/2004 at 5:11 PM [EMAIL PROTECTED] wrote: Hello, I was wondering wether there's a function in R that takes two vectors (of same length) as input and computes mean values for bins (intervals) or even a sliding window over these vectros. I've several x/y data set (input/response) that I'd like plot together. Say the x-data for one data set goes from -5 to 14 with 12,000 values, then I'd like to bin the x-vector in steps of +1 and calculate and plot the mean of the x-values and the y-values within each bin. I was browsing the R-docs but couldn't find anything appropiate. thanks for hints + kind regads, Arne __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html Dipl. bio-chem. Eryk Witold Wolski@MPI-Moleculare Genetic Ihnestrasse 63-73 14195 Berlin 'v' tel: 0049-30-83875219 / \ mail: [EMAIL PROTECTED]---W-Whttp://www.molgen.mpg.de/~wolski __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] lattice / pdf bug ?
On Monday 26 July 2004 18:17, Dirk Eddelbuettel wrote: I've been scrathing my head over this one. Suppose I have a data.frame which maps to a 'n x k' lattice, and that one of those cells is empty. An artificial example is generated by Q-data.frame(x1=sample(c(A,B),10,replace=TRUE), x2=c(C, rep(D,9)), y=rnorm(10)) where by having only one obs. for the first level of the second factor x2, we ensure that there won't be full combinations of x1 and x2. The empty cell is not the issue, rather it's the fact that the panel that gets the first observation (x2 = C) has only that one single observation. So for that panel, sd(x, na.rm = TRUE) = NA, hence dnorm(mesh points, mean = whatever, sd = NA) eventually produces a bunch of NA's, which grid.lines tries to draw. grid.lines has known issues with NA's, and I would guess that's what causes the broken pdf. The good news is that there doesn't seem to be any problems in r-devel (possibly because grid handles NA's better now). The natural workaround for your code would be to skip the panel.mathdensity call unless length(x) 1. Deepayan This seems to trip panel.mathdensity(), but only when printing to pdf, and I can't find a way to avoid it. Consider stopifnot(require(lattice)) stopifnot(require(grid)) pdf(testfile.pdf) Q-data.frame(x1=sample(c(A,B),10,replace=TRUE), x2=c(C, rep(D,9)), y=rnorm(10)) print(histogram(~ y | x1+x2, data=Q, panel = function(x, ...) { if (length(x) 0) { panel.histogram(x, ...) panel.mathdensity(dmath = dnorm, col = black, args = list(mean=mean(x, na.rm=TRUE), sd=sd(x, na.rm=TRUE))) } })) dev.off() where the resulting pdf file is broken if and only if the panel.mathdensity call is present. Without it, it works. To the screen, it works with and without -- but copying to pdf again breaks the pdf file if panel.mathdensity is used. It is possible that I am overlooking something simple -- or is it a genuine bug? Platform is win2k, R version is 1.9.1. Thanks for any pointers, Dirk __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] qcc package syndromic surveillance (multivar CUSUM?)
What do you think is most plausible: an abrupt jump or a gradual drift? To detect an abrupt jump from a null hypothesis H0 to an alternative H1, the tool of choice seems to be a cumulative sum (CUSUM) of log(likelihood ratio). If H0 and H1 are normal distributions with equal variances, this general rule specializes to a one-sided cumulative sum of (y[t]-mu.bar), where mu.bar is the average of the means under H0 and H1. However, to detect a gradual drift modeled as a random walk, the theory says that the best tool is something like an exponentially weighted moving average (EWMA). For monitor design, I like to write the following: joint = observation * prior = posterior * predictive f(y mu) = f(y | mu)*f(mu) = f(mu | y)*f(y). When each observation arrives, I test to see if it is consistent with the predictive distribution f(y). If it is not consistent, I report a potential problem. If it is consistent, I incorporate it into the EWMA [or CUSUM], as described by the posterior f(mu | y). For more information on this, see Bayes' Rule of Information and other foundations of monitoring reports downloadable from www.prodsyse.com. This kind if use of the predictive distribution is discussed in the West and Harrison (1999) book cited in the Bayes' Rule paper, and a Poisson EWMA is derived on p. 5. What you use, of course, depends on the events you hope to capture. For your applications, I might consider running separate monitors on each condition-hospital pair plus monitors on the totals for each hospital and for each condition, plus one for overall. I might use the qcc package to calibrate my thresholds, but do the daily computations in some data base system. Selecting thresholds is not easy, in part because the assumptions you make for monitor design will never hold exactly in practice. The result of this is that any thresholds you compute based purely on theory will be wrong. However, if you tune your thresholds based on the years of historical data you have, you should be on safer ground. This theory should get you close to an optimal arrangement. I think I would use quite loose thresholds for the hospital-condition (interaction) monitors, thighter thresholds for the condition and hospital totals, and the tightest threshold for the overall. Monitors on specific conditions should be sensitive to epidemics or to an effective biological warfare terrorist attack; if this is your concern, a CUSUM might be best. Monitors on specific hospitals should be sensitive to changes in the competence of local staff (suggesting a preference for an EWMA) or to a sudden local outbreak of something (suggesting a CUSUM). Monitors on condition-hospital pairs might be sensitive to local changes in preferred diagnoses. I would run Cusums or EWMAs but not both: Either will catch conditions most quickly caught by the other, with possible a little longer delay. hope this helps. spencer graves [EMAIL PROTECTED] wrote: Dear R Community: I am working on a public health early warning system, and I see that the qcc package allows for CUSUM and other statistical quality tests but I am not sure if my project is a good match for qcc functions as written. Any advice you may have is very much appreciated. I have four years worth of daily counts of emergency room admissions for different conditions (e.g. respiratory, neurologic, etc) from several local hospitals. the data looks like this... DAY 1 Respiratory Neuro ... Hospital A: 1012 . . . . . . Hospital F:714 DAY 2 Respiratory Neuro ... Hospital A: 1012 . . . . . . Hospital F:714... etc., and my goal is to do a kind of multivariate quality control test (without fitting a GLM), that would run each day after the data is updated and be able to answer the question: Has there been a significant variation in the central tendency of the data? An analogous problem would be detecting the early signs of a shift in global trading patterns by examining stock market indexes in different countries around the world, updating and testing the data each business day. Thank you, Alexis Diamond __ [EMAIL PROTECTED] mailing list https://www.stat.math.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://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] dumpClass
What do people do in R to get something comparable to the functionality of dumpClass described by Chambers (1998) Programming with Data (Springer)? Thanks, spencer graves __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Reading SPSS file
Hi Karl: a possible solution: require(foreign) mydata - read.spss(somedata.sav, use.value.labels = TRUE, to.data.frame = TRUE) - for more information, try library(foreign) ?read.spss HTH, Arin Message: 21 Date: Mon, 26 Jul 2004 10:36:33 +0200 (CEST) From: Karl Knoblick [EMAIL PROTECTED] Subject: [R] Read SPSS data (*.sav) in R 1.8.0 (ok) and R1.9.1(error) To: [EMAIL PROTECTED] Message-ID: [EMAIL PROTECTED] Content-Type: text/plain; charset=iso-8859-1 Hallo! snipped Does anybody know a possibilty to read a SPSS file under R1.9.1? Thanks! Karl Arindam Basu MD MPH DBI Assistant Director Fogarty International Program on Environmental Health in India IPGMER 244 AJC Bose Road, Kolkata 700027 India [[alternative HTML version deleted]] __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] re: help with lattice plot
Dear List, I have been using R to create an xyplot using the panel function within lattice libraries. This plot is based on the data supplied in R named 'Oats'. The graph represents oat yield by nitro level with an overlay of each variety of oats for each nitro level. I have three questions regarding this graph: 1) I cannot seem to specify the type of symbol used by the plot, even though it is included in the code below, it will change when the code is changed? 2) I have managed to include a legend on the graph using the key function; however the labels of the legend do not seem to correspond to the right coloured symbol as used in the plot itself for Variety. How can I get the symbols and text in the legend to match that used in the graph itself? 3) Also, I am interested to know how I can manipulate the order in which each graph (in this instance Nitro level) appears? For example, at the moment the graphs do not appear in numerical order (based on the levels of the factor nitro) can I reorder them so that they appear in the order I, II, III, IV, V, VI ? The code I have used is included below: ##Data library(nlme) data(Oats) ##Factors Oats$Block-factor(Oats$Block) Oats$Variety-factor(Oats$Variety) Oats$nitro-factor(Oats$nitro) attach(oats) ##Plot library(lattice) lset(col.whitebg()) xyplot(yield~nitro|Block, data=Oats,xlab=Nitrogen Level,ylab=Yield of oats,subscripts=T, groups=Oats$Variety, as.table=T, panel=function(x,y,groups,subscripts){ panel.superpose(x=x, y=y, groups=Oats$Variety, subscripts=subscripts,pch=18) panel.superpose(x=x, y=y, groups=Oats$Variety, subscripts=subscripts, type =r) } ,key = list(points = Rows(trellis.par.get(superpose.line),c(1:2,3)),text = list(lab = as.character(unique(Oats$Variety))),pch=18) ) I would greatly appreciate anyone's time in assisting me with this request. I look forward to your reply Regards Eve Eve McDonald-Madden Fauna Ecology Arthur Rylah Institute for Environmental Research Heidelberg, Victoria.Australia Email: [EMAIL PROTECTED] __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] re: help with lattice plot
On Monday 26 July 2004 21:51, [EMAIL PROTECTED] wrote: Dear List, I have been using R to create an xyplot using the panel function within lattice libraries. This plot is based on the data supplied in R named 'Oats'. The graph represents oat yield by nitro level with an overlay of each variety of oats for each nitro level. I have three questions regarding this graph: 1) I cannot seem to specify the type of symbol used by the plot, even though it is included in the code below, it will change when the code is changed? You are doing several things wrong. There's more than one way to fix it. For example, the approach you have taken may be modified to give (after the lset(col.whitebg()) call in your example): lset(list(superpose.symbol = list(pch = 18))) xyplot(yield ~ nitro | Block, data = Oats, xlab = Nitrogen Level, ylab = Yield of oats, groups = Variety, as.table = T, panel = function(x, y, groups, subscripts) { panel.superpose(x = x, y = y, groups = groups, subscripts = subscripts) panel.superpose(x = x, y = y, groups = groups, subscripts = subscripts, type =r) }, key = list(points = Rows(trellis.par.get(superpose.symbol), 1:3 ), text = list(lab = levels(Oats$Variety A line by line comparison with your code should indicate the differences. But since you are using some lattice-specific features (not available in S-PLUS) anyway, I would take it a bit further and simplify this to (again, after the lset(col.whitebg()) call in your example): xyplot(yield ~ nitro | Block, data = Oats, xlab = Nitrogen Level, ylab = Yield of oats, groups = Variety, as.table = TRUE, type = c(p, r), par.settings = list(superpose.symbol = list(pch = 18)), auto.key = TRUE) 2) I have managed to include a legend on the graph using the key function; however the labels of the legend do not seem to correspond to the right coloured symbol as used in the plot itself for Variety. How can I get the symbols and text in the legend to match that used in the graph itself? Wherever there's the need for 'ordering' a factor, the order is determined by its levels - given by the levels() function. In this case, the order would be given by levels(Oats$Variety), and not as.character(unique(Oats$Variety)) which you were using for some reason. This fact is relevant to your next question as well. 3) Also, I am interested to know how I can manipulate the order in which each graph (in this instance Nitro level) appears? For example, at the moment the graphs do not appear in numerical order (based on the levels of the factor nitro) can I reorder them so that they appear in the order I, II, III, IV, V, VI ? Surely you mean Block and not nitro? It behaves in this way because that's the order given by levels(Oats$Block) (the reason should be apparent after reading ?groupedData from nlme). You can choose your own order when using the factor function (your current use doesn't do anything, by the way): Oats$Block - factor(Oats$Block, levels = c(I, II, III, IV, V, VI)) Hope that helps, Deepayan __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html