[R] [R-pkgs] new R package: UNTB
Dear List please find uploaded to CRAN a new R package for the simulation and analysis of biodiversity. The package implements simulations and diagnostics of ecological systems that obey the Unified Neutral Theory of Biodiversity (untb). The canonical reference is: The Unified Neutral Theory of Biodiversity and Biogeography, Stephen P. Hubbell, Princeton University Press, 2000. enjoy -- Robin Hankin Uncertainty Analyst National Oceanography Centre, Southampton European Way, Southampton SO14 3ZH, UK tel 023-8059-7743 ___ R-packages mailing list [EMAIL PROTECTED] https://stat.ethz.ch/mailman/listinfo/r-packages __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Legend Outside Plot Dimension
Hi I think you need to use par(xpd=TRUE). Try to search archives as similar question was answered few days ago. HTH Petr On 19 Jan 2006 at 12:19, Abd Rahman Kassim wrote: From: Abd Rahman Kassim [EMAIL PROTECTED] To: r-help@stat.math.ethz.ch Date sent: Thu, 19 Jan 2006 12:19:30 -0800 Subject:[R] Legend Outside Plot Dimension Dear All, I'm trying to attach a legend outside the plot (Inside plot OK), but failed. Any help is very much appreciated. Thanks. Abd. Rahman Kassim, PhD Forest Management Ecology Program Forestry Conservation Division Forest Research Institute Malaysia Kepong 52109 Selangor MALAYSIA * Checked by TrendMicro Interscan Messaging Security. For any enquiries, please contact FRIM IT Department. * [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html Petr Pikal [EMAIL PROTECTED] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] creating objects with a slot of class formula, using new
Gabor == Gabor Grothendieck [EMAIL PROTECTED] on Thu, 19 Jan 2006 00:27:42 -0500 writes: Gabor Create a virtual class that can either be a formula or be NULL: setClassUnion(formulaOrNULL, c(formula, NULL)) setClass(a,representation(b=list,c=formulaOrNULL)) new(a, b = list(7)) that's one possibility, and probably closest to what Steve was asking for, however read on Gabor On 1/18/06, Steven Lacey [EMAIL PROTECTED] wrote: Hi, . But, now suppose you want a slot to accept an object of class formula... setClass(a,representation(b=list,c=formula)) new(a,b=list(7)) Error in validObject(.Object) : invalid class a object: invalid object for slot c in class a: got class NULL, should be or extend class formula Why can't new handle this? Why must the slot be defined? the 'c' slot need not be defined, but it must be initialized to an object of class formula If I call new without any named arguments, it works fine new(a) An object of class a Slot b: list() Slot c: NULL No, it does not work fine; it has created an *invalid* object, since, for efficiency reasons, the internal equivalent of validObject() is not called in all cases of object creation {and that is good: basic object creation should be fast}: (aa - new(a)) An object of class a Slot b: list() Slot c: NULL validObject(aa)## gives an error as it should Error in validObject(aa) : invalid class a object: invalid object for slot c in class a: got class NULL, should be or extend class formula If I call new with only a formula, it works fine. new(a,c=formula(x~y)) An object of class a Slot b: list() Slot c: x ~ y yes, since 'c' now *is* a formula, and BTW, even the simpler new(a, c = x~y) is sufficient {recurring topic of yesterday: 'y ~ x' *is* a formula and does not need an as.formula(.) or formula(.) around it !!} How can I get R to do this? setClass(a,representation(b=list,c=formula)) new(a,b=list(7)) An object of class a Slot b: [[1]] [1] 7 Slot c: NULL you can't and shouldn't be able to: If slot 'c' is defined to be a formula, it should be a formula and not NULL. So you need to change the class definition. Apart from Gabor's possibility which I consider a bit unelegant and not ideal here, I'd strongly suggest you make use of the 'prototype' argument when you define the class, e.g. : setClass(a, representation(b = list, f = formula), + prototype = prototype(b = list(), f = y ~ x)) [1] a (aa - new(a)) An object of class a Slot b: list() Slot f: y ~ x validObject(aa) [1] TRUE -- Martin Maechler, ETH Zurich __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Legend Outside Plot Dimension
Dear Peter, Thanks for your promt response. Abd. Rahman - Original Message - From: Petr Pikal [EMAIL PROTECTED] To: Abd Rahman Kassim [EMAIL PROTECTED]; r-help@stat.math.ethz.ch Sent: Thursday, January 19, 2006 12:11 AM Subject: Re: [R] Legend Outside Plot Dimension Hi I think you need to use par(xpd=TRUE). Try to search archives as similar question was answered few days ago. HTH Petr On 19 Jan 2006 at 12:19, Abd Rahman Kassim wrote: From: Abd Rahman Kassim [EMAIL PROTECTED] To: r-help@stat.math.ethz.ch Date sent: Thu, 19 Jan 2006 12:19:30 -0800 Subject:[R] Legend Outside Plot Dimension Dear All, I'm trying to attach a legend outside the plot (Inside plot OK), but failed. Any help is very much appreciated. Thanks. Abd. Rahman Kassim, PhD Forest Management Ecology Program Forestry Conservation Division Forest Research Institute Malaysia Kepong 52109 Selangor MALAYSIA * Checked by TrendMicro Interscan Messaging Security. For any enquiries, please contact FRIM IT Department. * [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html Petr Pikal [EMAIL PROTECTED] * Outgoing mail is certified Virus Free. Checked by TrendMicro Interscan Messaging Security. For any enquiries, please contact FRIM IT Department. * __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Canonical Variance Analysis by any other name?
Canonical variates or canonical variance? Canonical variates in the sense of your quote is the same thing as multi-group LDA (the part of LDA not due to Fisher) Another sense (e.g. http://en.wikipedia.org/wiki/Canonical_analysis) is canonical correlation analysis (function cancor). And indeed, LDA can be derived from CCA: see my PRNN book. On Thu, 19 Jan 2006, Patrick Connolly wrote: I've been asked about Canonical Variance Analysis (CVA). I don't see any reference to it searching the R site. Does it go by other names? Genstat describes it thus: Canonical variates analysis operates on a within-group sums of squares and products matrix, calculated from a set of variates and factor that specifies the grouping of units. It finds linear combinations of the variates that maximize the ratio of between-group to within-group variation, thereby giving functions that can be used to discriminate between the groups. It's probably not particularly difficult to do, so I suspect someone has a package for doing it. What other name might I search for? Thnx -- Patrick Connolly HortResearch Mt Albert Auckland New Zealand Ph: +64-9 815 4200 x 7188 ~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~ I have the world`s largest collection of seashells. I keep it on all the beaches of the world ... Perhaps you`ve seen it. ---Steven Wright ~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~ __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- 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 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Tobit estimation?
Folks, Based on http://www.biostat.wustl.edu/archives/html/s-news/1999-06/msg00125.html I thought I should experiment with using survreg() to estimate tobit models. I start by simulating a data frame with 100 observations from a tobit model x1 - runif(100) x2 - runif(100)*3 ystar - 2 + 3*x1 - 4*x2 + rnorm(100)*2 y - ystar censored - ystar = 0 y[censored] - 0 D - data.frame(y, x1, x2) head(D) y x1x2 1 0.000 0.86848630 2.6275703 2 0.000 0.88675832 1.7199261 3 2.7559349 0.38341782 0.6247869 4 0.000 0.02679007 2.4617981 5 2.2634588 0.96974450 0.4345950 6 0.6563741 0.92623096 2.4983289 # Estimate it library(survival) tfit - survreg(Surv(y, y0, type='left') ~ x1 + x2, data=D, dist='gaussian', link='identity') It says: Error in survreg.control(...) : unused argument(s) (link ...) Execution halted My competence on library(survival) is zero. Is it still the case that it's possible to be clever and estimate the tobit model using library(survival)? I also saw the two-equation setup in the micEcon library. I haven't yet understood when I would use that and when I would use a straight estimation of a censored regression by MLE. Can someone shed light on that? My situation is: Foreign investment on the Indian stock market. Lots of firms have zero foreign investment. But many do have foreign investment. I thought this is a natural tobit situation. -- Ajay Shah http://www.mayin.org/ajayshah [EMAIL PROTECTED] http://ajayshahblog.blogspot.com *(:-? - wizard who doesn't know the answer. __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] some EPS rotated in journal preview
Knut Krueger schrieb: I am trying to send a manuscript to a journal. One of the figures build by R is in the right orientation and 4 are rotated clockwise 90 deg in the preview. So I realized that they rotated the Paper not the figure. I did not realize it because I did not set the Arcrobat reader to a full size view. So I saw only the rotaded figure not the hole page. maybe this is a better hint. And the hint from the journal: Please be advised that your eps figure file could have rotated in the built PDF due to its size which is larger than the paper. but I think that could not be the problem, because the figure is in the right rotation at the page. Regards Knut __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Tobit estimation?
If you look at ?survreg, you might notice that there is no link argument, but that reference is made to survreg.old that does contain a link argument. Thus, help(survreg,package=survival) x1 - runif(100) x2 - runif(100)*3 ystar - 2 + 3*x1 - 4*x2 + rnorm(100)*2 y - ystar censored - ystar = 0 y[censored] - 0 D - data.frame(y, x1, x2) head(D) yx1x2 1 0.00 0.8381902 2.3445745 2 2.834993 0.6603959 0.4572142 3 2.322114 0.6683632 0.2619112 4 0.00 0.3762860 1.8897217 5 1.977283 0.9713827 0.8079159 6 0.536224 0.8266868 1.1839211 library(survival) Loading required package: splines tfit - survreg(Surv(y, y0, type='left') ~ x1 + x2, + data=D, dist='gaussian', link='identity') Error in survreg.control(...) : unused argument(s) (link ...) + tfit - survreg.old(Surv(y, y0, type='left') ~ x1 + x2, + data=D, dist='gaussian', link='identity') tfit Call: survreg(formula = formula, data = data, dist = dist, scale = scale) Coefficients: (Intercept) x1 x2 1.5945012.825190 -2.985390 Scale= 1.493047 Loglik(model)= -66.1 Loglik(intercept only)= -109.7 Chisq= 87.28 on 2 degrees of freedom, p= 0 n= 100 -- Ken Knoblauch Inserm U371 Cerveau et Vision Dept. of Cognitive Neuroscience 18 avenue du Doyen Lépine 69500 Bron France tel: +33 (0)4 72 91 34 77 fax: +33 (0)4 72 91 34 61 portable: +33 (0)6 84 10 64 10 http://www.lyon.inserm.fr/371/ __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] html excel file
hallo, i have a problem reading in the above mentioned kind of a file. does anybody know an easy way how to read it in? i can save it as a text file that looks like: Datum des Fixings Restlaufzeit 1 Jahr 2 Jahre 3 Jahre 4 Jahre 5 Jahre 6 Jahre 7 Jahre 8 Jahre 9 Jahre 10 Jahre 12 Jahre 15 Jahre 13.01.06 2.819 2.983 3.073 3.137 3.194 3.247 3.302 3.355 3.409 3.459 3.548 3.649 12.01.06 2.847 3.013 3.102 3.164 3.217 3.268 3.322 3.373 3.426 3.475 3.564 3.665 ... after skipping the first four lines i want to read it in while the first 12 lines are the heades the next is the date followed by the singel values...(these lines are always repeated) it is supposed to look like 123456789101215 datum1abcdefghij k l datum2abcdefghij k l ... i tried to read it in as a normal excel file but it didn´t work out the way it was supposed to thank you for helping!!! stefan __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] R Commenting Style
I seem to remember reading somewhere about some style guide regarding R the number of comment characters (#) prior to the comment meaning something. Anyone know to what I'm referring? Where? -- SIGSIG -- signature too long (core dumped) __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] packages about microarray analysis
Dear R-helpers, Can anybody suggest me some common packages for standard microarray analysis, either from CRAN or Bioconductor? Many thanks... [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] se.fit in predict.nls
Sorry to be so persistent but I really need to get some measure of the error in the predictions of my nls model. I've tried to find out what predict.nls does and I've got down to MiModelo$m$predict function (newdata = list(), qr = FALSE) { eval(form[[3]], as.list(newdata), env) } environment: 0x88a076c But I can not find what is form. Any help, please. Manuel Manuel Gutierrez wrote: The option se.fit in predict.nls is currently ignored. Is there any other function available to calculate the error in the predictions? Thanks, Manuel __ LLama Gratis a cualquier PC del Mundo. Llamadas a fijos y móviles desde 1 céntimo por minuto. __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] packages about microarray analysis
Vincent Deng wrote: Dear R-helpers, Can anybody suggest me some common packages for standard microarray analysis, either from CRAN or Bioconductor? Many thanks... [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html Look at: http://ihome.cuhk.edu.hk/~b400559/arraysoft_rpackages.html Cheers, Andrej __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] ICC for Binary data
Brian, Have a look at package aod on CRAN, and more specifically the functions icc, donner and raoscott. Best, Renaud 2006/1/18, Brian Perron [EMAIL PROTECTED]: Hello R users: I am fairly new to R and am trying to figure out how to compute an intraclass correlation (ICC) and/or design effect for binary data? More specifically, I am trying to determine the amount of clustering in a data set - that is, whether certain treatment programs tend to work with more or less severe clients. The outcome variable is dichotomous (low severity / high severity) and the grouping variable is the treatment program. Any suggestions for some R code or the appropriate R package would be greatly appreciated. Thanks, Brian [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- Renaud LANCELOT Département Elevage et Médecine Vétérinaire (EMVT) du CIRAD Directeur adjoint chargé des affaires scientifiques CIRAD, Animal Production and Veterinary Medicine Department Deputy director for scientific affairs Campus international de Baillarguet TA 30 / B (Bât. B, Bur. 214) 34398 Montpellier Cedex 5 - France Tél +33 (0)4 67 59 37 17 Secr. +33 (0)4 67 59 39 04 Fax +33 (0)4 67 59 37 95 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] se.fit in predict.nls
I think you first need to understand how you would compute the standard errors. Since the model is non-linear, it is hard to see how this could be done accurately. If the parameters are estimated with negligible error compared to the non-linearity (and you can explore that since profiling gives you an idea of the variability), you can use local linearization to do this. If not, you can simulate. On Thu, 19 Jan 2006, Manuel Gutierrez wrote: Sorry to be so persistent but I really need to get some measure of the error in the predictions of my nls model. That is not what se.fit would tell you. It gives you a measure of the variability in the fitted mean curve at one point. If that is large compared to the variability about the true mean curve, you are likely to have trouble finding it (and the standard error may not an adequarte summary as it is likely to be an asymmetric distribution). I've tried to find out what predict.nls does and I've got down to MiModelo$m$predict function (newdata = list(), qr = FALSE) { eval(form[[3]], as.list(newdata), env) } environment: 0x88a076c But I can not find what is form. You really do need to understand all the code, and lexical scoping. Any help, please. Manuel Manuel Gutierrez wrote: The option se.fit in predict.nls is currently ignored. Is there any other function available to calculate the error in the predictions? Thanks, Manuel __ LLama Gratis a cualquier PC del Mundo. Llamadas a fijos y móviles desde 1 céntimo por minuto. __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- 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__ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] packages about microarray analysis
On 1/19/06 5:36 AM, Vincent Deng [EMAIL PROTECTED] wrote: Dear R-helpers, Can anybody suggest me some common packages for standard microarray analysis, either from CRAN or Bioconductor? You did look at the Bioconductor project? The vast majority of those packages are for microarray analysis. If you need more specific help, I would suggest using the bioconductor mailing list. Sean __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] R Commenting Style
I don't know if this is what you're referring to, but in ESS the number of octothorpes (#) affects the indentation in the emacs buffer. If I remember right, ### puts it at the beginning of the line, ## the current indentation level (eg. in a function) and # further right. Paul Roebuck wrote: I seem to remember reading somewhere about some style guide regarding R the number of comment characters (#) prior to the comment meaning something. Anyone know to what I'm referring? Where? -- Kevin E. Thorpe Biostatistician/Trialist, Knowledge Translation Program Assistant Professor, Department of Public Health Sciences Faculty of Medicine, University of Toronto email: [EMAIL PROTECTED] Tel: 416.946.8081 Fax: 416.946.3297 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Minimizing mahalanobis distance to negative orthant
Hi I have the following problem: given x (px1) and S (pXp positive definite), find y such that y_i=0 (i=1..p) minimizing the mahalanobis distance (x-y)'S^{-1}(x-y). Has anyone worked on this problem? Tips or R code would be appreciated. David David Edwards Principal scientist Biostatistics Novo Nordisk A/S Novo Allé 2880 Bagsvaerd Denmark +45 (phone) This e-mail (including any attachments) is intended for the addressee(s) stated above only and may contain confidential information protected by law. You are hereby notified that any unauthorised reading, disclosure, copying or distribution of this e-mail or use of information contained herein is strictly prohibited and may violate rights to proprietary information. If you are not an intended recipient, please return this e-mail to the sender and delete it immediately hereafter. Thank you. [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] empirical maximum likelihood estimation
Dear R-users Problem: Given the following system of ordinary differential euqations dM/dt = (-n)*M-h*M dS/dt = n*M-h*S+u*R dA/dt = h*S-q*A dI/dt = q*A-p*I dJ/dt = h*M-v*J dR/dt=p*I+v*J-u*R where M,S,A,I,J,R are state variables and n,h,u,q,p,v parameters. I'm able to calculate the likelihood value based on the solutions M,S,A,I,J,R of the ODE's given the data, but without an explicit formula. How can I now optimize the loglikelihood with respect to the parameter n,h,u,q,p,v? Is there any functions available in R for dealing with such empirical likelihood problems? Thanks a lot for your support. -- Dominik Heinzmann Master of Science in Mathematics, EPFL Ph.D. student in Biostatistics Institute of Mathematics University of Zurich Winterthurerstrasse 190 CH-8057 Zürich Office: Y36L90 E-Mail : [EMAIL PROTECTED] Phone : +41-(0)44-635 5858 Fax : +41-(0)1-63 55705 Homepage: http://www.math.unizh.ch/user/heinzmann __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Tobit estimation?
On Thu, 19 Jan 2006 14:05:58 +0530 Ajay Narottam Shah wrote: Folks, Based on http://www.biostat.wustl.edu/archives/html/s-news/1999-06/msg00125.html I thought I should experiment with using survreg() to estimate tobit models. I've been working on a convenience interface to survreg() that makes it particularly easy to fit tobit models re-using the survreg() infrastructure. The package containing the code will hopefully be release soon - anyone who wants a devel snapshot, please contact me off-list. Ajay, I'll send you the code in a separate mail. Best, Z I start by simulating a data frame with 100 observations from a tobit model x1 - runif(100) x2 - runif(100)*3 ystar - 2 + 3*x1 - 4*x2 + rnorm(100)*2 y - ystar censored - ystar = 0 y[censored] - 0 D - data.frame(y, x1, x2) head(D) y x1x2 1 0.000 0.86848630 2.6275703 2 0.000 0.88675832 1.7199261 3 2.7559349 0.38341782 0.6247869 4 0.000 0.02679007 2.4617981 5 2.2634588 0.96974450 0.4345950 6 0.6563741 0.92623096 2.4983289 # Estimate it library(survival) tfit - survreg(Surv(y, y0, type='left') ~ x1 + x2, data=D, dist='gaussian', link='identity') It says: Error in survreg.control(...) : unused argument(s) (link ...) Execution halted My competence on library(survival) is zero. Is it still the case that it's possible to be clever and estimate the tobit model using library(survival)? I also saw the two-equation setup in the micEcon library. I haven't yet understood when I would use that and when I would use a straight estimation of a censored regression by MLE. Can someone shed light on that? My situation is: Foreign investment on the Indian stock market. Lots of firms have zero foreign investment. But many do have foreign investment. I thought this is a natural tobit situation. -- Ajay Shah http://www.mayin.org/ajayshah [EMAIL PROTECTED] http://ajayshahblog.blogspot.com *(:-? - wizard who doesn't know the answer. __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Minimizing mahalanobis distance to negative orthant
On Thu, 19 Jan 2006, DED (David George Edwards) wrote: I have the following problem: given x (px1) and S (pXp positive definite), find y such that y_i=0 (i=1..p) minimizing the mahalanobis distance (x-y)'S^{-1}(x-y). Has anyone worked on this problem? Tips or R code would be appreciated. If I read this correctly (some spaces would help) you want y such that y = 0 and y minimizes (x-y)'Q(x-y) for a symmetric pos def Q. That is a quadratic program, so see package quadprog. -- 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 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] R Commenting Style
Le 19.01.2006 11:19, Paul Roebuck a écrit : I seem to remember reading somewhere about some style guide regarding R the number of comment characters (#) prior to the comment meaning something. Anyone know to what I'm referring? Where? Hi, If you edit your R code with eclipse + statET plugin (http://www.walware.de/goto/statet) you can associate task tags to your comments, ie : # TODO : bla bla # FIXME : replace that for loop by some vectorized incantation # BUG : ... you can create new task tags according to your taste ... so that the comments are managed by a separate window. Pretty useful. Romain -- visit the R Graph Gallery : http://addictedtor.free.fr/graphiques mixmod 1.7 is released : http://www-math.univ-fcomte.fr/mixmod/index.php +---+ | Romain FRANCOIS - http://francoisromain.free.fr | | Doctorant INRIA Futurs / EDF | +---+ __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] empirical maximum likelihood estimation
Look at optim, or mle in package stats4. There are a lot of similar problems addressed in R: few real-world likelihoods have `an explicit formula'. One quite similar example is ARIMA fitting. On Thu, 19 Jan 2006, Dominik Heinzmann wrote: Dear R-users Problem: Given the following system of ordinary differential euqations dM/dt = (-n)*M-h*M dS/dt = n*M-h*S+u*R dA/dt = h*S-q*A dI/dt = q*A-p*I dJ/dt = h*M-v*J dR/dt=p*I+v*J-u*R where M,S,A,I,J,R are state variables and n,h,u,q,p,v parameters. I'm able to calculate the likelihood value based on the solutions M,S,A,I,J,R of the ODE's given the data, but without an explicit formula. How can I now optimize the loglikelihood with respect to the parameter n,h,u,q,p,v? Is there any functions available in R for dealing with such empirical likelihood problems? Thanks a lot for your support. -- Dominik Heinzmann Master of Science in Mathematics, EPFL Ph.D. student in Biostatistics Institute of Mathematics University of Zurich Winterthurerstrasse 190 CH-8057 Zürich Office: Y36L90 E-Mail : [EMAIL PROTECTED] Phone : +41-(0)44-635 5858 Fax : +41-(0)1-63 55705 Homepage: http://www.math.unizh.ch/user/heinzmann __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- 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__ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] princomp() with missing values in panel data?
ivo welch said the following on 2006-01-18 14:56: thank you. I am still not sure how to get the scores in princomp, though: ds= as.data.frame( cbind(rnorm(10),rnorm(10)) ) names(ds)=c(x1,x2) ds[5,]=c(NA,NA) pc= princomp( formula = ~ ds$x1 + ds$x2, na.action=na.omit) ds$pc1 = pc$scores[,1] #-- error, scores has 9 obs, ds has 10 obs is there an elegant method to do this, or do I need to learn how to operate Prof Ripley told you how to do it: `na.action = na.exclude'. with pc$loadings? (may I also humbly suggest that the default behavior or $scores should be to contain NA in row 5?) Choosing sensible defaults in the case of NAs is a tricky business. Personally, I'd like the default to be `na.fail', so that I don't miss out on NAs if I've been sloppy while screening the data. Genrally, just ignoring missings and analysing the data as if it were complete may lead to seriously biased results. Incidentally, R is a lot cleverer than I understand. pc$loadings by itself Sometimes R is almost too clever, and I end up feeling humliated when finding out that I'm the stupid one... ;-) HTH, Henric gives me wonderfully intuitive output, with names, text, different components---but I can still use p$loadings[,2]. I presume that the array operator on the loadings object is overloaded. very nice. [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] html excel file
Hi your question is a bit cryptic. What file you want to read? xls or some exported file from Excel? There is many different ways how to read data into R. See read.table, RODBC, R data Import Export Manual I personally use in Excel select the data with header and Ctrl-C in R myfile - read.delim(clipboard) HTH Petr On 19 Jan 2006 at 10:38, Stefan Semmeling wrote: From: Stefan Semmeling [EMAIL PROTECTED] To: r-help@stat.math.ethz.ch Date sent: Thu, 19 Jan 2006 10:38:18 +0100 Subject:[R] html excel file hallo, i have a problem reading in the above mentioned kind of a file. does anybody know an easy way how to read it in? i can save it as a text file that looks like: Datum des Fixings Restlaufzeit 1 Jahr 2 Jahre 3 Jahre 4 Jahre 5 Jahre 6 Jahre 7 Jahre 8 Jahre 9 Jahre 10 Jahre 12 Jahre 15 Jahre 13.01.06 2.819 2.983 3.073 3.137 3.194 3.247 3.302 3.355 3.409 3.459 3.548 3.649 12.01.06 2.847 3.013 3.102 3.164 3.217 3.268 3.322 3.373 3.426 3.475 3.564 3.665 ... after skipping the first four lines i want to read it in while the first 12 lines are the heades the next is the date followed by the singel values...(these lines are always repeated) it is supposed to look like 123456789101215 datum1abcdefghij k l datum2abcdefghij k l ... i tried to read it in as a normal excel file but it didn´t work out the way it was supposed to thank you for helping!!! stefan __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html Petr Pikal [EMAIL PROTECTED] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Can't load Matrix 0.995-1 for lme4
Dear useRs, I can no longer run lme4 because I think I upgraded lme4 without being able to upgrade Matrix. I am using: Mac OS 10.4.4 R v. 2.2.1 (updated from 2.2.0 this morning) lme4 v. 0.995-1 I tried to use the RGUI to load the package source of Matrix 0.995-1 and it seemed to be progressing quite well and then it failed providing this message: make: *** [Matrix.so] Error 1 ERROR: compilation failed for package 'Matrix' I could not find a binary of Matrix =0.995-1 on any of the URL respositoires that I investigated (us,uk,at,au). I would very grateful for any ideas or assistance. Cheers, Hank Dr. Martin Henry H. Stevens, Assistant Professor 338 Pearson Hall Botany Department Miami University Oxford, OH 45056 Office: (513) 529-4206 Lab: (513) 529-4262 FAX: (513) 529-4243 http://www.cas.muohio.edu/~stevenmh/ http://www.muohio.edu/ecology/ http://www.muohio.edu/botany/ E Pluribus Unum __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] html excel file
Read ?scan very carefully and play with the settings. What makes your file difficult is that it is multi line, meaning that the headings have carriage returns between them instead of being one line separated with spaces or tabs or commas. Can you change the way the file is outputted? If not, you will have to play with scan to get the file in. Anything is possible, but it looks like it will be tricky. HTH, Roger On 1/19/06, Stefan Semmeling [EMAIL PROTECTED] wrote: hallo, i have a problem reading in the above mentioned kind of a file. does anybody know an easy way how to read it in? i can save it as a text file that looks like: Datum des Fixings Restlaufzeit 1 Jahr 2 Jahre 3 Jahre 4 Jahre 5 Jahre 6 Jahre 7 Jahre 8 Jahre 9 Jahre 10 Jahre 12 Jahre 15 Jahre 13.01.06 2.819 2.983 3.073 3.137 3.194 3.247 3.302 3.355 3.409 3.459 3.548 3.649 12.01.06 2.847 3.013 3.102 3.164 3.217 3.268 3.322 3.373 3.426 3.475 3.564 3.665 ... after skipping the first four lines i want to read it in while the first 12 lines are the heades the next is the date followed by the singel values...(these lines are always repeated) it is supposed to look like 123456789101215 datum1abcdefghij k l datum2abcdefghij k l ... i tried to read it in as a normal excel file but it didn´t work out the way it was supposed to thank you for helping!!! stefan __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] princomp() with missing values in panel data?
On Thu, 19 Jan 2006, Henric Nilsson wrote: ivo welch said the following on 2006-01-18 14:56: thank you. I am still not sure how to get the scores in princomp, though: ds= as.data.frame( cbind(rnorm(10),rnorm(10)) ) names(ds)=c(x1,x2) ds[5,]=c(NA,NA) pc= princomp( formula = ~ ds$x1 + ds$x2, na.action=na.omit) ds$pc1 = pc$scores[,1] #-- error, scores has 9 obs, ds has 10 obs is there an elegant method to do this, or do I need to learn how to operate Prof Ripley told you how to do it: `na.action = na.exclude'. with pc$loadings? (may I also humbly suggest that the default behavior or $scores should be to contain NA in row 5?) Choosing sensible defaults in the case of NAs is a tricky business. Personally, I'd like the default to be `na.fail', so that I don't miss out on NAs if I've been sloppy while screening the data. Genrally, just ignoring missings and analysing the data as if it were complete may lead to seriously biased results. I tend to agree (and so does S). You can achieve this with options(na.action=na.fail), almost everywhere. -- 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 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Can't load Matrix 0.995-1 for lme4
Martin Henry H. Stevens [EMAIL PROTECTED] writes: Dear useRs, I can no longer run lme4 because I think I upgraded lme4 without being able to upgrade Matrix. I am using: Mac OS 10.4.4 R v. 2.2.1 (updated from 2.2.0 this morning) lme4 v. 0.995-1 I tried to use the RGUI to load the package source of Matrix 0.995-1 and it seemed to be progressing quite well and then it failed providing this message: make: *** [Matrix.so] Error 1 ERROR: compilation failed for package 'Matrix' You're chopping too much of the output there. This gives no information as to why it failed. Missing tools or compile error? I could not find a binary of Matrix =0.995-1 on any of the URL respositoires that I investigated (us,uk,at,au). Someone needs to build it... Delays appear to be slightly larger for Mac than for Windows (which is still 1 revision out of sync with the sources, though). I would very grateful for any ideas or assistance. You *did* read section 5.2 of the MacOSX FAQ, didn't you? Cheers, Hank Dr. Martin Henry H. Stevens, Assistant Professor 338 Pearson Hall Botany Department Miami University Oxford, OH 45056 Office: (513) 529-4206 Lab: (513) 529-4262 FAX: (513) 529-4243 http://www.cas.muohio.edu/~stevenmh/ http://www.muohio.edu/ecology/ http://www.muohio.edu/botany/ E Pluribus Unum __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- O__ Peter Dalgaard Øster Farimagsgade 5, Entr.B c/ /'_ --- Dept. of Biostatistics PO Box 2099, 1014 Cph. K (*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918 ~~ - ([EMAIL PROTECTED]) FAX: (+45) 35327907 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] html excel file
roger bos [EMAIL PROTECTED] writes: Read ?scan very carefully and play with the settings. What makes your file difficult is that it is multi line, meaning that the headings have carriage returns between them instead of being one line separated with spaces or tabs or commas. Can you change the way the file is outputted? If not, you will have to play with scan to get the file in. Anything is possible, but it looks like it will be tricky. I'd try reading the whole thing as a character vector x - scan(, what=) then M - matrix(x[-(1:3)], byrow=TRUE) cn - M[1,-1] rn - M[-1,1] n - M[-1,-1] mode(n) - numeric dimnames(n) - list(rn,cn) and then (possibly) data.frame(n) [Notice that this is only partially tested, so no guarantees] HTH, Roger On 1/19/06, Stefan Semmeling [EMAIL PROTECTED] wrote: hallo, i have a problem reading in the above mentioned kind of a file. does anybody know an easy way how to read it in? i can save it as a text file that looks like: Datum des Fixings Restlaufzeit 1 Jahr 2 Jahre 3 Jahre 4 Jahre 5 Jahre 6 Jahre 7 Jahre 8 Jahre 9 Jahre 10 Jahre 12 Jahre 15 Jahre 13.01.06 2.819 2.983 3.073 3.137 3.194 3.247 3.302 3.355 3.409 3.459 3.548 3.649 12.01.06 2.847 3.013 3.102 3.164 3.217 3.268 3.322 3.373 3.426 3.475 3.564 3.665 ... after skipping the first four lines i want to read it in while the first 12 lines are the heades the next is the date followed by the singel values...(these lines are always repeated) it is supposed to look like 123456789101215 datum1abcdefghij k l datum2abcdefghij k l ... i tried to read it in as a normal excel file but it didn´t work out the way it was supposed to thank you for helping!!! stefan __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- O__ Peter Dalgaard Øster Farimagsgade 5, Entr.B c/ /'_ --- Dept. of Biostatistics PO Box 2099, 1014 Cph. K (*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918 ~~ - ([EMAIL PROTECTED]) FAX: (+45) 35327907 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] obtaining ROC curve from Nearest Shrunken Centroids (pamr)
Hello, I have binary labels from a nearest shrunken centroids prediction (package pamr). I need to obtain a ROC curve for this test. What is the easiest way to obtain one? Paolo Sonego __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Creating dipole field
Hello, I'm looking to perform some statistical analysis on some idealised data cases, and was wondering if someone could point me in the direction of how to create a simple dipole field within R? I basically require a rectangular grid with a distinct high/low pressure dipole. Any pointers appreciated, thank you! Laura Quinn Institute of Atmospheric Science School of Earth and Environment University of Leeds Leeds LS2 9JT tel: +44 113 343 1596 fax: +44 113 343 6716 mail: [EMAIL PROTECTED] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Tobit estimation?
For adventurous, but skeptical souls who lack faith in the usual Gaussian tobit assumptions, I could mention that there is new fcen method for the quantreg rq() function that implements Powell's tobit estimator using an algorithm of Bernd Fitzenberger. url:www.econ.uiuc.edu/~rogerRoger Koenker email[EMAIL PROTECTED]Department of Economics vox: 217-333-4558University of Illinois fax: 217-244-6678Champaign, IL 61820 On Jan 19, 2006, at 6:04 AM, Achim Zeileis wrote: On Thu, 19 Jan 2006 14:05:58 +0530 Ajay Narottam Shah wrote: Folks, Based on http://www.biostat.wustl.edu/archives/html/s-news/1999-06/ msg00125.html I thought I should experiment with using survreg() to estimate tobit models. I've been working on a convenience interface to survreg() that makes it particularly easy to fit tobit models re-using the survreg() infrastructure. The package containing the code will hopefully be release soon - anyone who wants a devel snapshot, please contact me off-list. Ajay, I'll send you the code in a separate mail. Best, Z I start by simulating a data frame with 100 observations from a tobit model x1 - runif(100) x2 - runif(100)*3 ystar - 2 + 3*x1 - 4*x2 + rnorm(100)*2 y - ystar censored - ystar = 0 y[censored] - 0 D - data.frame(y, x1, x2) head(D) y x1x2 1 0.000 0.86848630 2.6275703 2 0.000 0.88675832 1.7199261 3 2.7559349 0.38341782 0.6247869 4 0.000 0.02679007 2.4617981 5 2.2634588 0.96974450 0.4345950 6 0.6563741 0.92623096 2.4983289 # Estimate it library(survival) tfit - survreg(Surv(y, y0, type='left') ~ x1 + x2, data=D, dist='gaussian', link='identity') It says: Error in survreg.control(...) : unused argument(s) (link ...) Execution halted My competence on library(survival) is zero. Is it still the case that it's possible to be clever and estimate the tobit model using library(survival)? I also saw the two-equation setup in the micEcon library. I haven't yet understood when I would use that and when I would use a straight estimation of a censored regression by MLE. Can someone shed light on that? My situation is: Foreign investment on the Indian stock market. Lots of firms have zero foreign investment. But many do have foreign investment. I thought this is a natural tobit situation. -- Ajay Shah http://www.mayin.org/ajayshah [EMAIL PROTECTED] http://ajayshahblog.blogspot.com *(:-? - wizard who doesn't know the answer. __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting- guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] factor or not factor that is a question
Dear all I encountered strange problem with split factor. I tried to use boxplot(split(, factor)) but I got an error message split(test$asar,kvartaly) Error in split(x, f) : second argument must be a factor str(kvartaly) Factor w/ 8 levels 1Q.04,2Q.04,..: 1 1 1 1 1 1 1 1 1 1 ... str(test$asar) num [1:731] 16.8 16.6 16.6 16.4 16.7 ... is.factor(kvartaly) [1] TRUE I used formula interface boxplot(formula) which worked OK. What can be wrong with my factor kvartaly? Where to look? Why it is not accepted by split? W2000 version _ platform i386-pc-mingw32 arch i386 os mingw32 system i386, mingw32 status major2 minor2.1 year 2005 month12 day 20 svn rev 36812 language R Best regards. Petr Pikal [EMAIL PROTECTED] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Plotting an lme( ) object
Greg Tarpinian said the following on 2006-01-18 23:37: I apologize for the second posting, my other email address died today. I am using R for Windows, version 2.2. Here is my code: plot(FOO.lme4, resid(.,type = p) ~ fitted(.) | GROUP, id = 0.05, adj = -0.3, idLabels = FOO$value, main = Pearson Residuals vs. Fitted Values, by Group, between = list(x = .5, y = .5)) The plot looks fine, but the adj = -0.3 option seems to have no effect on the labels that are added to identify potential outliers. I would like to offset the FOO$value text that is currently being displayed right on top of several pearson residuals. How can I do this? I just checked the code for `plot.lme', and it builds a panel function that uses the `adj' argument of the `ltext'. Unfortunately, according to the help page for `ltext' (from the Details section), ... For 'ltext', only values 0, .5 and 1 for 'adj' have any effect. It wouldn't categorize this as a bug in R, since R's `ltext' function behaves according to its documentation. But it sure is irritating. I've CC:ed Deepayan Sarkar, maintainer of the lattice package, and hopefully he's able to advise or, even better, extend `ltext' to accept a wider range of `adj' values. HTH, Henric Thanks much, Greg __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] how to select a node in dendrogram/tree
Dear R-users, Can someone help me select a node/ nodes in a dendrogram or tree, like colouring the ones that are selected? Also, I'm quite interested in any kind of interactive expandable dendrogram (like showing different levels of details at a time). I have a pretty large dataset and I really want to interact with the graph. Thanks indeed. ___ Zhesi He Computational Biology Laboratory, University of York York YO10 5YW, U.K. Phone: +44-(0)1904-328279 Email: [EMAIL PROTECTED] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] aggregating variables with pca
hello R_team having perfomed a PCA on my fitted model with the function: data- na.omit(dataset) data.pca-prcomp(data,scale =TRUE), I´ve decided to aggregate two variables that are highly correlated. My first question is: How can I combine the two variables into one new predictor? and secondly: How can I predict with the newly created variable in a new dataset? Guess I need the predict and new data command but I´m having problems with the syntax and the help function was not sufficient on this issue. many thanks in advance Christian [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] R Commenting Style
Kevin == Kevin E Thorpe [EMAIL PROTECTED] on Thu, 19 Jan 2006 06:26:31 -0500 writes: Kevin I don't know if this is what you're referring to, but in ESS the number Kevin of octothorpes (#) affects the indentation in the emacs buffer. If I Kevin remember right, ### puts it at the beginning of the line, ## the current Kevin indentation level (eg. in a function) and # further right. That's correct, thank you, Kevin, and it's further supported by ESS in emacs, e.g., if you comment a region (M-;) two # are used automatically. There's also a little not well-known function M-x ess-fix-comments with documentation string Fix ess-mode buffer so that single-line comments start with at least `##'. and ess-fix-comments is implicitly called by the function M-x ess-MM-fix-src which I use all the time when I get source files from some people in order to ``clean them'' to my taste... Note that a current (development) version of the ESS manual is also only at the ESS website, specifically, http://ess.r-project.org/Manual/ess.html where the section on indenting (and the comments) is http://ess.r-project.org/Manual/ess.html#Indenting I have exceptionally broken the rule of crossposting, and am sending this to ESS-help mailing list as well, just to make sure it'll be seen (and found) there as well. Martin Maechler, ETH Zurich Kevin Paul Roebuck wrote: I seem to remember reading somewhere about some style guide regarding R the number of comment characters (#) prior to the comment meaning something. Anyone know to what I'm referring? Where? __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] help on statistics and code
Hi, I need some advise on statistics. I have written the code below. What i'm trying to do here is that i read 1000 distance matrices derived from the same original data set. Afterwards I wan to create a consensus matix out of those 1000 distance matrices to see the relevance of the original matrix. Is that correct ?? should i be doing something else ? library(stats) library(ade4) library(cluster) library(ape) nb_runs - 1000 first_matrix=TRUE #Reading 1000 distance matrices for (i in 1:nb_runs) { infile=input_matrix infile-paste(infile,i,sep=_) cat(\nReading ,infile,) data-read.table(infile,header=FALSE,sep=\t,row.names=1) # # First matrix we read if (first_matrix) { first_matrix=FALSE Mdist=dist.binary(data,method=1,diag=TRUE) } else { #the other 999 matrices dis-dist.binary(data,method=1,diag=TRUE) Mdist - Mdist+dis } #Get the consensus matrix based on 1000 matrices Matallp-(Mdist/nb_runs ) clust-hclust(Matall) ... Is that correct ?? the code works properly. Thanks for your help __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] html excel file
On Do, 19.01.2006, 10:38, Stefan Semmeling wrote: hallo, i have a problem reading in the above mentioned kind of a file. One way of transferring data between R and Excel is using the RExcel package contained in R(D)COM server available from CRAN in category Other. The package rcom (available from CRAN) can turn R into a COM server for Excel and with a little bit of VBA programming it is possible to transfer data both ways also. __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Using svm.plot with mlbench.spirals.
Hi. I'm trying to plot a pair of intertwined spirals and an svm that separates them. I'm having some trouble. Here's what I tried. library(mlbench) library(e1071) Loading required package: class raw - mlbench.spirals(200,2) spiral - data.frame(class=as.factor(raw$classes), x=raw$x[,1], y=raw$x[,2]) m - svm(class~., data=spiral) plot(m, spiral) Error in -x$index : invalid argument to unary operator So we delve into e1071:::plot.svm. When I run the code in plot.svm everything is fine up until points(formula, data = data[-x$index, ], pch = dataSymbol, col = symbolPalette[colind[-x$index]]) That gives me the same error message, Error in -x$index : invalid argument to unary operator. The weird thing is that I can run either of the those statements in isolation data[-x$index, ] symbolPalette[colind[-x$index]] and neither gives me an error. I looked in the two points functions I can see (points.default and points.formula) but neither calls x$index. I was following along the documentation for plot.svm, which has a simple example (that works) ## a simple example library(MASS) data(cats) m - svm(Sex~., data = cats) plot(m, cats) I don't see what the difference between their example and mine. Can anyone help me? Thank you, Josh. __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] empirical maximum likelihood estimation
BDR == Prof Brian Ripley [EMAIL PROTECTED] on Thu, 19 Jan 2006 12:38:12 + (GMT) writes: BDR Look at optim, or mle in package stats4. BDR There are a lot of similar problems addressed in R: few real-world BDR likelihoods have `an explicit formula'. One quite similar example is BDR ARIMA fitting. Further note the package 'nlmeODE' which efficiently addresses a problem very similar to yours. Martin Maechler, ETH Zurich BDR On Thu, 19 Jan 2006, Dominik Heinzmann wrote: Dear R-users Problem: Given the following system of ordinary differential euqations dM/dt = (-n)*M-h*M dS/dt = n*M-h*S+u*R dA/dt = h*S-q*A dI/dt = q*A-p*I dJ/dt = h*M-v*J dR/dt=p*I+v*J-u*R where M,S,A,I,J,R are state variables and n,h,u,q,p,v parameters. I'm able to calculate the likelihood value based on the solutions M,S,A,I,J,R of the ODE's given the data, but without an explicit formula. How can I now optimize the loglikelihood with respect to the parameter n,h,u,q,p,v? Is there any functions available in R for dealing with such empirical likelihood problems? Thanks a lot for your support. -- Dominik Heinzmann Master of Science in Mathematics, EPFL Ph.D. student in Biostatistics Institute of Mathematics University of Zurich Winterthurerstrasse 190 CH-8057 Zürich Office: Y36L90 E-Mail : [EMAIL PROTECTED] Phone : +41-(0)44-635 5858 Fax : +41-(0)1-63 55705 Homepage: http://www.math.unizh.ch/user/heinzmann __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html BDR -- BDR Brian D. Ripley, [EMAIL PROTECTED] BDR Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ BDR University of Oxford, Tel: +44 1865 272861 (self) BDR 1 South Parks Road, +44 1865 272866 (PA) BDR Oxford OX1 3TG, UKFax: +44 1865 272595__ BDR R-help@stat.math.ethz.ch mailing list BDR https://stat.ethz.ch/mailman/listinfo/r-help BDR PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] (no subject)
Good evening, I am Marta Colombo, student at Milan's Politecnico. Thank you very much for your kindness, this mailing list is really useful. I am using the function kde2d for two-dimensional kernel density estimation and I'd like to know something more about this kind of density estimator. In particular I'd like to know: what bandwidth is used ? Thank you in advance for your attention Marta Colombo __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] function kde2d
Good evening, I am Marta Colombo, student at Milan's Politecnico. Thank you very much for your kindness, this mailing list is really useful. I am using the function kde2d for two-dimensional kernel density estimation and I'd like to know something more about this kind of density estimator. In particular I'd like to know: what bandwidth is used ? Thank you in advance for your attention Marta Colombo __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Downloads -- possible bug?
Hi, When I go to the CRAN page to download a new version of R, there are not the same versions available depending on which mirror I pick. When I go to http://cran.cnr.berkeley.edu/, for example, I get 2.2.1, but if I go http://cran.stat.ucla.edu/ the option is 2.2.0 (I'm downloading the Windows base file). Neither refreshing nor clearing my cache changes it. For future reference, I'd like to know if this is a mistake or if different mirrors are just updated at different times? Thanks, Elizabeth Purdom __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] function kde2d
Do you mean the one in package MASS? If so, you need to consult the reference on its help page (although the bandwidth is actually given on the help page). It is courteous to credit other people's work in contributed packages. The author of MASS::kde2d On Thu, 19 Jan 2006, Marta Colombo wrote: Good evening, I am Marta Colombo, student at Milan's Politecnico. Thank you very much for your kindness, this mailing list is really useful. I am using the function kde2d for two-dimensional kernel density estimation and I'd like to know something more about this kind of density estimator. In particular I'd like to know: what bandwidth is used ? Thank you in advance for your attention Marta Colombo -- 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 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Downloads -- possible bug?
Elizabeth Purdom wrote: Hi, When I go to the CRAN page to download a new version of R, there are not the same versions available depending on which mirror I pick. When I go to http://cran.cnr.berkeley.edu/, for example, I get 2.2.1, but if I go http://cran.stat.ucla.edu/ the option is 2.2.0 (I'm downloading the Windows base file). Neither refreshing nor clearing my cache changes it. For future reference, I'd like to know if this is a mistake or if different mirrors are just updated at different times? Looks like http://cran.stat.ucla.edu/ has not been synced for a couple of months, since Kurt Hornik's *daily* check has the date 08-Oct-2005 on that mirror. Fritz? Uwe Thanks, Elizabeth Purdom __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Downloads -- possible bug?
Elizabeth Purdom [EMAIL PROTECTED] writes: Hi, When I go to the CRAN page to download a new version of R, there are not the same versions available depending on which mirror I pick. When I go to http://cran.cnr.berkeley.edu/, for example, I get 2.2.1, but if I go http://cran.stat.ucla.edu/ the option is 2.2.0 (I'm downloading the Windows base file). Neither refreshing nor clearing my cache changes it. For future reference, I'd like to know if this is a mistake or if different mirrors are just updated at different times? Thanks, Elizabeth Purdom It depends on the mirroring sites' policy and maintenance. UCLA apparently hasn't updated since October, which is quite extreme. My guess would be that it is a local bug rather than deliberate policy. -- O__ Peter Dalgaard Øster Farimagsgade 5, Entr.B c/ /'_ --- Dept. of Biostatistics PO Box 2099, 1014 Cph. K (*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918 ~~ - ([EMAIL PROTECTED]) FAX: (+45) 35327907 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] matrix export
Dear listers, I need to export a distance matrix in the following format : a 0.0 1.0 0.2 1.0 1.0 b 1.0 0.0 1.0 1.0 1.0 c 0.2 1.0 0.0 1.0 1.0 d 1.0 1.0 1.0 0.0 1.0 e 1.0 1.0 1.0 1.0 0.0 I tried write.matrix() from the MASS library, which gives: a b c d e 0.0 1.0 0.2 1.0 1.0 1.0 0.0 1.0 1.0 1.0 0.2 1.0 0.0 1.0 1.0 1.0 1.0 1.0 0.0 1.0 1.0 1.0 1.0 1.0 0.0 Does anyone know of an R trick to change the location of the headers ?or do I need to do this externally, through perl or bash ? Thanks in advance for your help, Eric Eric Pante College of Charleston, Grice Marine Laboratory 205 Fort Johnson Road, Charleston SC 29412 On ne force pas la curiosite, on l'eveille ... Daniel Pennac __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] [R-pkgs] RSQLite
Version 0.4-1 of the RSQLite package has been uploaded to CRAN. RSQLite embeds the SQLite engine in R (see http://www.sqlite.org) Changes include: * Fixed problems exporting/importing NA's * An new experimental dbWriteTable() method to create SQLite tables from simple files (delimited unquoted fields), e.g., dbWriteTable(con, table_name, file_name, ...) methods?dbWriteTable ## see documentation for details * dbConnect() now accepts values for the cache_size and synchronous to tune/improve SQLite performance (see methods?dbConnect for details). Thanks to Seth Falcon, Ronggui Huang, and Charles Loboz for their patches, suggestions, bug reports and testing. -- David ___ R-packages mailing list [EMAIL PROTECTED] https://stat.ethz.ch/mailman/listinfo/r-packages __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] gam
Dear R users, I'm new to both R and to this list and would like to get advice on how to build generalized additive models in R. Based on the description of gam, which I found on the R website, I specified the following model: model1-gam(ST~s(MOWST1),family=binomial,data=strikes.S), in which ST is my binary response variable and MOWST1 is a categorical independent variable. I get the following error message: Error in smooth.construct.tp.smooth.spec(object, data, knots) : NA/NaN/Inf in foreign function call (arg 1) In addition: Warning messages: 1: argument is not numeric or logical: returning NA in: mean.default(xx) 2: - not meaningful for factors in: Ops.factor(xx, shift[i]) I would greatly appreciate if someone could tell me what I did wrong. Can I use categorical independents in gam at all? Many thanks, Istvan __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Editing Partial Correlation Matrix
Hi, I created a matrix of correlation coefficients and their respective scatterplots using the commands hetcor() and panel.cor(). Can I edit this matrix? I would like to have the scale values display at the top, as opposed to the alternating top-bottom scale approach. Also, I would like to increase the font size of the graphic for print purposes. Any help on how to accomplish this would be greatly appreciated! Thanks, Mark Here is the code I am using for this analysis: data - read.table(X:/GWRclip/corrmatrix.txt, header = T) ASHDEP - data [,1] ELE - data [,2] SLP - data [,3] ASP - data [,4] PLCU - data [,5] PRCU - data [,6] CTI - data [,7] STI - data [,8] SPI - data [,9] data - data.frame(ASHDEP, ELE, SLP, ASP, PLCU, PRCU, CTI, STI, SPI) hetcor(data) # Pearson, polychoric, and polyserial correlations, 2-step est. hetcor(ASHDEP, ELE, SLP, ASP, PLCU, PRCU, CTI, STI, SPI, ML=TRUE) # Pearson, polychoric, polyserial correlations, ML est. panel.cor - function(x, y, digits=2, prefix=, cex.cor) { usr - par(usr); on.exit(par(usr)) par(usr = c(0,1,0,1)) r - (cor(x, y)) txt - format(c(r, 0.123456789), digits=digits)[1] txt - paste(prefix, txt, sep=) if(missing(cex.cor)) text(0.5, 0.5, txt) } pairs( data[c(1, 2:9 )], main = Partial Correlation Coefficients for Selected Soil-Terrain Attributes, upper.panel=panel.smooth, lower.panel=panel.cor ) Mark Kimsey Research Assistant Intermountain Forest Tree Nutrition Cooperative University of Idaho Moscow, Idaho 83844-1133 Work: 208.885.7520 Mobile: 509.330.0640 Fax: 208.885.7442 [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] matrix export
Thanks, Bert write.table won't do the trick, because distance matrices in R are presented as lower triangular matrices. write.table cannot coerce class dist into a data.frame. maybe there is a way to transform the lower triangular matrix into a full matrix, and then use write.table ? cheers, Eric On Jan 19, 2006, at 1:38 PM, Berton Gunter wrote: Just use write.table() from the base package with row.names=TRUE (the default). -- Bert Gunter Genentech Non-Clinical Statistics South San Francisco, CA The business of the statistician is to catalyze the scientific learning process. - George E. P. Box -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Eric Pante Sent: Thursday, January 19, 2006 10:09 AM To: r-help@stat.math.ethz.ch Subject: [R] matrix export Dear listers, I need to export a distance matrix in the following format : a 0.0 1.0 0.2 1.0 1.0 b 1.0 0.0 1.0 1.0 1.0 c 0.2 1.0 0.0 1.0 1.0 d 1.0 1.0 1.0 0.0 1.0 e 1.0 1.0 1.0 1.0 0.0 I tried write.matrix() from the MASS library, which gives: a b c d e 0.0 1.0 0.2 1.0 1.0 1.0 0.0 1.0 1.0 1.0 0.2 1.0 0.0 1.0 1.0 1.0 1.0 1.0 0.0 1.0 1.0 1.0 1.0 1.0 0.0 Does anyone know of an R trick to change the location of the headers ?or do I need to do this externally, through perl or bash ? Thanks in advance for your help, Eric Eric Pante College of Charleston, Grice Marine Laboratory 205 Fort Johnson Road, Charleston SC 29412 On ne force pas la curiosite, on l'eveille ... Daniel Pennac __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html Eric Pante College of Charleston, Grice Marine Laboratory 205 Fort Johnson Road, Charleston SC 29412 On ne force pas la curiosite, on l'eveille ... Daniel Pennac __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] matrix export
On 1/19/06 2:05 PM, Eric Pante [EMAIL PROTECTED] wrote: Thanks, Bert write.table won't do the trick, because distance matrices in R are presented as lower triangular matrices. write.table cannot coerce class dist into a data.frame. maybe there is a way to transform the lower triangular matrix into a full matrix, and then use write.table ? Did you try as.matrix()? From the dist() help page: 'as.dist()' is a generic function. Its default method handles objects inheriting from class 'dist', or coercible to matrices using 'as.matrix()'. Sean __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] change fitted line colour in lme() trellis plot?
If I used a groupedData object, if I do fit-lme(blah) then plot(augPred(fit)) produces a nice trellis plot of the data along with the fitted lines However I find that the lines and the data points are in the same colour (light blue against a medium grey background). Is there a way to make the lines in a different colour (e.g. black)? It would also be nice if the line were plotted after the points so it is visible (I have a lot of points and the line is obscured). I have looked at par(). Thanks very much for any help. Bill __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Canonical Variance Analysis by any other name?
On Thu, 19-Jan-2006 at 08:35AM +, Prof Brian Ripley wrote: | Canonical variates or canonical variance? | It was canonical variance I was asked about and I wasn't careful enough getting the Genstat quote to make sure I was referring to the same thing. It seems SAS uses the term Canonical Variance Analysis and the reference mentioned for it is: Dixon, W. H., and M. B. Brown [eds.]. 1979 Biomedical computer programs P-series. University of California Press, Los Angeles, CA. Does anyone know for sure if they are the same thing? It appears to me that someone misheard variates as variance, but that might not be the case. Perhaps SAS likes to use different terminology. Thank you Brian for the wikipedia link. It doesn't have anything relating to canonical variance analysis which seems to support my suspicions. -- Patrick Connolly HortResearch Mt Albert Auckland New Zealand Ph: +64-9 815 4200 x 7188 ~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~ I have the world`s largest collection of seashells. I keep it on all the beaches of the world ... Perhaps you`ve seen it. ---Steven Wright ~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~ __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Plotting an lme( ) object
On 1/19/06, Henric Nilsson [EMAIL PROTECTED] wrote: Greg Tarpinian said the following on 2006-01-18 23:37: I apologize for the second posting, my other email address died today. I am using R for Windows, version 2.2. Here is my code: plot(FOO.lme4, resid(.,type = p) ~ fitted(.) | GROUP, id = 0.05, adj = -0.3, idLabels = FOO$value, main = Pearson Residuals vs. Fitted Values, by Group, between = list(x = .5, y = .5)) The plot looks fine, but the adj = -0.3 option seems to have no effect on the labels that are added to identify potential outliers. I would like to offset the FOO$value text that is currently being displayed right on top of several pearson residuals. How can I do this? I just checked the code for `plot.lme', and it builds a panel function that uses the `adj' argument of the `ltext'. Unfortunately, according to the help page for `ltext' (from the Details section), ... For 'ltext', only values 0, .5 and 1 for 'adj' have any effect. It wouldn't categorize this as a bug in R, since R's `ltext' function behaves according to its documentation. But it sure is irritating. I've CC:ed Deepayan Sarkar, maintainer of the lattice package, and hopefully he's able to advise or, even better, extend `ltext' to accept a wider range of `adj' values. The grid.text argument 'just' does support numeric values like 'adj' now, but it didn't when ltext was originally written (or at least I was under the impression that it didn't). I have updated ltext accordingly, which in future releases of lattice should support other values of adj. I wasn't planning any updates for R 2.2.x, but I can if anyone needs this desperately enough. Deepayan -- http://www.stat.wisc.edu/~deepayan/ __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Dynamic Programming in R
Hi R users, I am looking to numerically solve a dynamic program in the R environment. I was wondering if there were people out there who had expereinced success at using R for such applications. I'd rather continue in R than learn Mathlab. A concern that has been cited that may discourage R use for solving dynamic programs is its memory handling abilities. A senior researcher had a lot of trouble with R becuase on any given run it would eat up all the computers memory and need to start using the hard disk. Yet, the memory needed was not substantial - saving the worksapce, exiting and recalling would noticebly start of tthe progam at a much lower memory use, level and a quick deteroration in a few thousand iterations. Is this a problem other people have come across? Perhaps, its a problem already fixed, since the researcher was working on this in 2002 (he claimed he had tried it on windows, mac, and unix versions to check). Thanks. Arnab __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] change fitted line colour in lme() trellis plot?
On 1/19/06, Bill Simpson [EMAIL PROTECTED] wrote: If I used a groupedData object, if I do fit-lme(blah) then plot(augPred(fit)) produces a nice trellis plot of the data along with the fitted lines However I find that the lines and the data points are in the same colour (light blue against a medium grey background). Is there a way to make the lines in a different colour (e.g. black)? plot(augPred(fit), col.line = 'black') It would also be nice if the line were plotted after the points so it is visible (I have a lot of points and the line is obscured). The order is hard-coded in the panel function: plot(augPred(fit))$panel function (x, y, subscripts, groups, ...) { if (grid) panel.grid() orig - groups[subscripts] == original panel.xyplot(x[orig], y[orig], ...) panel.xyplot(x[!orig], y[!orig], ..., type = l) } You can change it by supplying your own panel function, e.g. plot(augPred(fit), col.line = black, panel = function (x, y, subscripts, groups, ...) { panel.grid() orig - groups[subscripts] == original panel.xyplot(x[orig], y[orig], ...) panel.xyplot(x[!orig], y[!orig], ..., type = l) }) Deepayan __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] change fitted line colour in lme() trellis plot?
On 1/19/06, Deepayan Sarkar [EMAIL PROTECTED] wrote: On 1/19/06, Bill Simpson [EMAIL PROTECTED] wrote: If I used a groupedData object, if I do fit-lme(blah) then plot(augPred(fit)) produces a nice trellis plot of the data along with the fitted lines However I find that the lines and the data points are in the same colour (light blue against a medium grey background). Is there a way to make the lines in a different colour (e.g. black)? plot(augPred(fit), col.line = 'black') It would also be nice if the line were plotted after the points so it is visible (I have a lot of points and the line is obscured). The order is hard-coded in the panel function: plot(augPred(fit))$panel function (x, y, subscripts, groups, ...) { if (grid) panel.grid() orig - groups[subscripts] == original panel.xyplot(x[orig], y[orig], ...) panel.xyplot(x[!orig], y[!orig], ..., type = l) } Actually, this is already what you want, so you shouldn't need to do anything. Deepayan __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Dynamic Programming in R
1. I have no experience in dynamic programming (so you may want to ignore the rest of this message) 2. Your message is vague (to me) -- more specifics about what you want to do might result in a better answer. 3. R has become **much** better at loop management since 2002 4. Nevertheless, there are undoubtedly still situations where R may require an unacceptably large amount of memory overhead. Recursion is one, I believe. Usually the best advice is: try it and see. -- Bert Gunter Genentech Non-Clinical Statistics South San Francisco, CA -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Arnab mukherji Sent: Thursday, January 19, 2006 1:55 PM To: r-help@stat.math.ethz.ch Subject: [R] Dynamic Programming in R Hi R users, I am looking to numerically solve a dynamic program in the R environment. I was wondering if there were people out there who had expereinced success at using R for such applications. I'd rather continue in R than learn Mathlab. A concern that has been cited that may discourage R use for solving dynamic programs is its memory handling abilities. A senior researcher had a lot of trouble with R becuase on any given run it would eat up all the computers memory and need to start using the hard disk. Yet, the memory needed was not substantial - saving the worksapce, exiting and recalling would noticebly start of tthe progam at a much lower memory use, level and a quick deteroration in a few thousand iterations. Is this a problem other people have come across? Perhaps, its a problem already fixed, since the researcher was working on this in 2002 (he claimed he had tried it on windows, mac, and unix versions to check). Thanks. Arnab __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Dynamic Programming in R
[Arnab mukherji] A concern that has been cited that may discourage R use for solving dynamic programs is its memory handling abilities. For a dynamic programming problem defined over N steps, one usually needs a N*N matrix, so problems should be tractable for N being not too big. In those I studied, CPU time usually was the scarse resource. As extreme paths were known to be very unlikely, this (and memory as well) could be alleviated somehow by limiting the solution search into bands (more or less wide) following the diagonal of the solution matrix. I also had some success in splitting big problems into a sequence of smaller subproblems, and recursively: such approximations are likely not acceptable in the general case. I would guess that most dynamic programming problems have their own specific artifacts and speed-up techniques, a universal solution might be uneasy. Who knows (I'm not sure): R might well offer a powerful environment for building a dynamic programming framework. -- François Pinard http://pinard.progiciels-bpi.ca __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Loop through factors without changing to numerics
Hi all, If I want to write a for loop to loop through a set of factors, which are not coded in 1,2,3, for e.g in character, possible to write the for loop without changing it to categorical variables? I saw the manual mentions for loop will take a list, but I'm not sure how to create a list here. Any input will be appreciated. Thanks. Yen Lin [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Loop through factors without changing to numerics
An example would have helped to give you a better answer. You can use characters in the seq argument of the for loop. i.e x=letters[1:4] x [1] a b c d for(i in x) {print(i)} [1] a [1] b [1] c [1] d Is this what you were looking for? Francisco From: Chia, Yen Lin [EMAIL PROTECTED] To: r-help@stat.math.ethz.ch Subject: [R] Loop through factors without changing to numerics Date: Thu, 19 Jan 2006 16:42:00 -0800 Hi all, If I want to write a for loop to loop through a set of factors, which are not coded in 1,2,3, for e.g in character, possible to write the for loop without changing it to categorical variables? I saw the manual mentions for loop will take a list, but I'm not sure how to create a list here. Any input will be appreciated. Thanks. Yen Lin [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Dynamic Programming in R
The lpSolve package can handle integer programming problems. Here is an example of using dynamic programming in R from first principles in another setting: http://tolstoy.newcastle.edu.au/R/help/06/01/18845.html On 1/19/06, Arnab mukherji [EMAIL PROTECTED] wrote: Hi R users, I am looking to numerically solve a dynamic program in the R environment. I was wondering if there were people out there who had expereinced success at using R for such applications. I'd rather continue in R than learn Mathlab. A concern that has been cited that may discourage R use for solving dynamic programs is its memory handling abilities. A senior researcher had a lot of trouble with R becuase on any given run it would eat up all the computers memory and need to start using the hard disk. Yet, the memory needed was not substantial - saving the worksapce, exiting and recalling would noticebly start of tthe progam at a much lower memory use, level and a quick deteroration in a few thousand iterations. Is this a problem other people have come across? Perhaps, its a problem already fixed, since the researcher was working on this in 2002 (he claimed he had tried it on windows, mac, and unix versions to check). Thanks. Arnab __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Plotting an lme( ) object
Based on the suggestions, the following yielded satisfactory results: plot(FOO.lme4, resid(.,type = p) ~ fitted(.) | GROUP, id = 0.05, adj = 1, idLabels = paste( round(FOO$VALUE,1), rep( ,length(FOO$VALUE)) ), main = Pearson Residuals vs. Fitted Values, by GROUP, between = list(x = .5, y = .5)) Using paste() to hardcode an extra space provided me with the necessary graphical offsets. Regards, Greg --- Deepayan Sarkar [EMAIL PROTECTED] wrote: On 1/19/06, Henric Nilsson [EMAIL PROTECTED] wrote: Greg Tarpinian said the following on 2006-01-18 23:37: I apologize for the second posting, my other email address died today. I am using R for Windows, version 2.2. Here is my code: plot(FOO.lme4, resid(.,type = p) ~ fitted(.) | GROUP, id = 0.05, adj = -0.3, idLabels = FOO$value, main = Pearson Residuals vs. Fitted Values, by Group, between = list(x = .5, y = .5)) The plot looks fine, but the adj = -0.3 option seems to have no effect on the labels that are added to identify potential outliers. I would like to offset the FOO$value text that is currently being displayed right on top of several pearson residuals. How can I do this? I just checked the code for `plot.lme', and it builds a panel function that uses the `adj' argument of the `ltext'. Unfortunately, according to the help page for `ltext' (from the Details section), ... For 'ltext', only values 0, .5 and 1 for 'adj' have any effect. It wouldn't categorize this as a bug in R, since R's `ltext' function behaves according to its documentation. But it sure is irritating. I've CC:ed Deepayan Sarkar, maintainer of the lattice package, and hopefully he's able to advise or, even better, extend `ltext' to accept a wider range of `adj' values. The grid.text argument 'just' does support numeric values like 'adj' now, but it didn't when ltext was originally written (or at least I was under the impression that it didn't). I have updated ltext accordingly, which in future releases of lattice should support other values of adj. I wasn't planning any updates for R 2.2.x, but I can if anyone needs this desperately enough. Deepayan -- http://www.stat.wisc.edu/~deepayan/ __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html