Re: [R] Drawing multiple plots on one page for publication.

On Wed, 4 Aug 2004, Zach Hu wrote: > I have been using R for a while but only recently tried to draw quality > plots for publications. I spent a few days tried to figure out how to > draw multiple plots on a single page to a postscript or pdf file but not > successful. The drawing is perfect OK

Re: [R] Strange Problem with "proj" and "aov" for split-plot analysis output

Ulrich Leopold wrote: # split-plot analysis - using "aov" with argument "data" > summary(aov.split.04 <- aov(ctime~brand*type+Error(subject),data=choco.split.04)) As far as I can see, maybe you should not use the redirect command in this case and skip the 'data' argument then it should work:

Re: [R] Order of messgaes/ missing messages

Jim Brennan rogers.com> writes: > Ah that is the answer I was looking for! Thanks. > I can see that a webmail site would/might also experience the same > phenomenon. I was just curious-- not that it bothered me. It depends on what you mean by "same". Any site can experience the phenomenon but s

Re: [R] Order of messgaes/ missing messages

Ah that is the answer I was looking for! Thanks. I can see that a webmail site would/might also experience the same phenomenon. I was just curious-- not that it bothered me. Cheers Jim - Original Message - From: "Murray Jorgensen" <[EMAIL PROTECTED]> To: "hadley wickham" <[EMAIL PROTECTE

Re: [R] Order of messgaes/ missing messages

hadley wickham gmail.com> writes: > > > Note that if this bothers you then you could try a web-based > > email systems (e.g. yahoo, hotmail, etc.) to receive your r-help > > messages since the path to any of them would be independent of your > > particular location on the net. > > I use gmail a

Re: [R] Order of messgaes/ missing messages

The TCP protocol sends a message as a stream of packets. When packets are lost over a particular link in the path from the sending machine at ETHZ to a recipient parts of the message will be re-transmitted. A message sent after another message can arrive before it if it experiences less packet

Re: [R] Order of messgaes/ missing messages

> Note that if this bothers you then you could try a web-based > email systems (e.g. yahoo, hotmail, etc.) to receive your r-help > messages since the path to any of them would be independent of your > particular location on the net. I use gmail and still often recieve replies before the original

Re: [R] Drawing multiple plots on one page for publication.

Zach, try: pdf("Name.pdf") par(mfrow=c(2,2)) par(mai=c(0.5,0.3, 0.6, 0.4)) plot(x, y, ..) plot(x, z ...) plot(z, y,...) plot(z+x, x-y, .) dev.off() Andrew __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/m

[R] dispersion for the inverse.gaussian family

Dear all, I am trying to get a more accurate estimate of the dispersion parameter of the inverse.gaussian family in a glm model. The one provided by the summary.glm looks like only a rough estimate, when you calculate the individual likelihoods and sum them using the dispersion reported by summary

[R] Drawing multiple plots on one page for publication.

Hi All, I have been using R for a while but only recently tried to draw quality plots for publications. I spent a few days tried to figure out how to draw multiple plots on a single page to a postscript or pdf file but not successful. The drawing is perfect OK if it is displayed on the screen

Re: [R] Order of messgaes/ missing messages

Note that if this bothers you then you could try a web-based email systems (e.g. yahoo, hotmail, etc.) to receive your r-help messages since the path to any of them would be independent of your particular location on the net. Jim Brennan rogers.com> writes: : Thanks for the answers. It is int

Re: new sep argument for interaction (was: Re: [R] Concatenating variables)

Deepayan Sarkar stat.wisc.edu> writes: : : On Wednesday 04 August 2004 15:50, Gabor Grothendieck wrote: : : > Several people have already mentioned paste, which returns a : > character result, and two other solutions, depending on what you are : > looking for, are: : > : >with(tenn, 100 * u

Re: [R] Order of messgaes/ missing messages

Thanks for the answers. It is interesting. I had thought everything would go to a central server and then be sent out in order from there, but I guess I just don't get the topology of the web. :-) I think there may be other issues though, since sometimes there are very long, what seem like random,

[R] Course***Advanced R/Splus Programming in San Francisco and Washington DC by XLsolutions Corp.

XSolutions Corp (www.xlsolutions-corp.com) is proud to announce a 2-day "Advanced R/Splus programming" taught by R Development Core Team Guru! *San Francisco ---> August 30-31, 2004 *Washington DC --> TBD (Please email us) Reserve your seat

new sep argument for interaction (was: Re: [R] Concatenating variables)

On Wednesday 04 August 2004 15:50, Gabor Grothendieck wrote: > Several people have already mentioned paste, which returns a > character result, and two other solutions, depending on what you are > looking for, are: > >with(tenn, 100 * up + 10 * down + stable) # numeric result > >with(tenn

[R] RE: Does tcltk matter for the plot

Hi Paul, I use executable codes of tex and latex from http://aixpdslib.seas.ucla.edu/packages/tetex.html) and compile the original R-1.9.1 source codes using C for AIX compiler V6.0 and Fortran for AIX compiler 7.1.1 and generate 64 bit R environments. It works well. Kexiao -Original Mess

Re: [R] Horizontal color bar in filled.contour()

Jenny Fox wrote: Hello. I was wondering if it is possible to put the color bar (key) on the bottom of the graph, like the "horizontal" toggle in image.plot, rather than on the right side. Does anyone know if this is possible? --jenny It does not appear so by taking a rough looking at code for

Re: [R] Concatenating variables

"Doran, Harold" <[EMAIL PROTECTED]> writes: > Hi all: > > > > I'm having difficulty with something I believe is very simple, but I'm > stuck. I have a large data frame that took days to clean and prepare. > All I now need to do is concatenate three variables into a single > column. For example

[R] Horizontal color bar in filled.contour()

Hello. I was wondering if it is possible to put the color bar (key) on the bottom of the graph, like the "horizontal" toggle in image.plot, rather than on the right side. Does anyone know if this is possible? --jenny __ [EMAIL PROTECTED] mailing list

Re: [R] ERROR: compilation failed for package 'rgl'

Korponai János <[EMAIL PROTECTED]> writes: > X-BeenThere: [EMAIL PROTECTED] > X-Mailman-Version: 2.1.5 ... > Sender: [EMAIL PROTECTED] > Errors-To: [EMAIL PROTECTED] [What happened with the mail headers? Confused my mail filtering.] > I could not install rgl package. What is missing? > > daphni

Re: [R] Concatenating variables

Doran, Harold air.org> writes: : I'm having difficulty with something I believe is very simple, but I'm : stuck. I have a large data frame that took days to clean and prepare. : All I now need to do is concatenate three variables into a single : column. For example, I have tenn$up, tenn$down, and

Re: [R] Concatenating variables

Doran, Harold wrote: Hi all: I'm having difficulty with something I believe is very simple, but I'm stuck. I have a large data frame that took days to clean and prepare. All I now need to do is concatenate three variables into a single column. For example, I have tenn$up, tenn$down, and tenn$st

RE: [R] Concatenating variables

Try something like: paste(tenn$up, tenn$down, tenn$stable, collapse="") HTH, Andy > From: Doran, Harold > > Hi all: > > > > I'm having difficulty with something I believe is very simple, but I'm > stuck. I have a large data frame that took days to clean and prepare. > All I now need to do i

Re: [R] cross random effects

On Wednesday 04 August 2004 01:13 pm, wrote: > Dear friends, > > I have asked last few days about cross-random effects > using PQL, but I have not receive any answer because > might my question was not clear. > > My question was about analysing the salamander mating > data using PQL. This data co

[R] Concatenating variables

Hi all: I'm having difficulty with something I believe is very simple, but I'm stuck. I have a large data frame that took days to clean and prepare. All I now need to do is concatenate three variables into a single column. For example, I have tenn$up, tenn$down, and tenn$stable which all have v

RE: [R] Order of messgaes/ missing messages

It has to do with the topology of the web - if you are web-wise closer to the responder than the original sender you can receive the answer before the question - even if both answer and question go only to the list. I learned this suscribed to SAS-L when I was at UF - I was downstream from Bob Ham

Re: [R] ERROR: compilation failed for package 'rgl'

On Wed, 4 Aug 2004, Korponai [iso-8859-2] János wrote: > I could not install rgl package. What is missing? OpenGL, or at least its header files. For Fedora Core 2, the GL headers seems to be in xorg-x11-devel-6.7.0-5, for RH8.0 XFree86-devel-4.2.1-21. In both cases, the same place as the X11 hea

Re: [R] ERROR: compilation failed for package 'rgl'

OpenGL or MESA librares. Korponai János <[EMAIL PROTECTED]> writes: > X-BeenThere: [EMAIL PROTECTED] > X-Mailman-Version: 2.1.5 > Precedence: list > Reply-To: [EMAIL PROTECTED] > List-Id: "Main R Mailing List: Primary help" > List-Unsubscribe:

Re: [R] ERROR: compilation failed for package 'rgl'

On Wed, Aug 04, 2004 at 09:35:32PM +0200, Korponai J?nos wrote: > I could not install rgl package. What is missing? [...] > config.status: creating src/Makevars > ** libs > g++ -I/usr/lib/R/include -I/usr/X11R6/include -DHAVE_PNG_H > -mieee-fp -Wall -pedantic -fno-exceptions -fno-rtti -fPIC -g

[R] ERROR: compilation failed for package 'rgl'

X-BeenThere: [EMAIL PROTECTED] X-Mailman-Version: 2.1.5 Precedence: list Reply-To: [EMAIL PROTECTED] List-Id: "Main R Mailing List: Primary help" List-Unsubscribe: , List-Archive:

Re: [R] dots expansion

That's a good point. Your original solution is simpler than the poster's and likely faster than mine. At any rate, continuing the with simplicity, rather than performance, vein if one does want to allow matrices or data frames then the solution I posted won't work, even if you take away the ch

[R] Re: R-help Digest, Vol 18, Issue 3

__ [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] Asymptotic Regression Model

Hi listers, I have some data (see attachment), and I fitted it to the Asymptotic Regression Model with NLSstAsymptotic(xy). But I want to know the significance of these fits. How can I accomplish this using R? Can anyone suggest some theoretical reading on this subject? Thanks, Miguel -- M

[R] cross random effects

Dear friends, I have asked last few days about cross-random effects using PQL, but I have not receive any answer because might my question was not clear. My question was about analysing the salamander mating data using PQL. This data contain cross-random effects for (male) and for (female). By op

Re: [R] How to extract z value from coxph

Thomas Lumley <[EMAIL PROTECTED]> writes: > > to build a linear classification model. Although the function outputs > > the z value, but I can't access to it, so that I can write code to > > extract them automatically and pass them to the next function. Can > > someone help? > > > > Use the acces

[R] about the systemfit package

Hi, I had a problem to get some of the values when I used 'systemfit()' function. I specified arguments of 'method (2SLS), eqns, eqnlables, inst, data' in 'systemfit()' function. And it failed to return the values such as 'residuals', 'x'(matrix of all regressors) etc as displayed on its refer

[R] spatial econometric model for a simultaneous system

Hi, Is there any package or functions in R that can perform tests and estimation for a spatial econometric model in a simultaneous system? Thank you!!! Xia Feng __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help

Re: [R] How to extract z value from coxph

On Wed, 4 Aug 2004, Man, Chris T. wrote: > Hi all, > > I have tried to use coxph to determine which variables are significant > in survival analysis. I also would like to use their z scores as weights > to build a linear classification model. Although the function outputs > the z value, but I can'

[R] fitting distributions

Hello, I also try to fit a skewed distribution (like skewed student t) to data points. Do you have an idee howto do this??? thank you fabrice dusonchet *** This email and any files transmitted with it are confiden

Re: [R] Order of messgaes/ missing messages

Might this depend on whether someone responds to all or only to the list? If one responds to all, then the originator should receive 2 copies, If s/he subscribes to the list. The copy via the list is often delayed hours by the listserve. Might this explain the issue? spencer graves Ji

[R] How to extract z value from coxph

Hi all, I have tried to use coxph to determine which variables are significant in survival analysis. I also would like to use their z scores as weights to build a linear classification model. Although the function outputs the z value, but I can't access to it, so that I can write code to extrac

RE: [R] dots expansion

In addition to Gabor's comments: There's a reason why I didn't coerce the grouping variable to a factor. rbind()ing data frames is much more expensive than rbind()ing arrays/matrices. Unless your data really have different data types in different columns, it would mostly likely be better to work

Re: [R] dots expansion

Viet Nguyen fastmail.fm> writes: > > Thanks to all who helped. > > I used your ideas and code samples to write the following (for the > benefit of people who will search this list later): > > rbind.case <- function(..., name="case", values) { > dots <- list(...); > if (missing(values)

[R] RODBC with MS Microsoft Access

Hi all, I tried to retrieve a table from a desktop database and got an error. The thing is that when I changed the table name it worked out. The former names was "length-spring" The new was test Is "-" character not valid for tables? Thank you Luis Ridao Cruz Fiskirannsóknarstovan Nóatún 1 P.O

Re: [R] R Matrix package solve

On Wed, 4 Aug 2004, Matt Nunes wrote: > hello. > > I have a query about the Matrix package for R. I wrote some code a while > ago using the Matrix package version 1.6.2 with an early version of R, to > do some linear least squares for regression: > > xn > [,1] [,2] [,3] [,4]

Re: [R] Constructing a VAR model using dse

Wolfgang Abele wrote: Hi everybody, I'm trying to construct a VAR model where the output variables can influence each other in the same time period, for example: x1_t = ax1_t-1 + bx2_t-1 + e1 x2_t = cx1_t + dx2_t-1 + e2 So x2_t is influenced by x1_t. Does anybody know how to construct such a model

RE: [R] What's ``impres''?

Seems like you are using code that someone other than yourself had written. The best person to ask would be the original author of that code. The way you quote the code, there's no context for anyone to guess what `impres' is, other than that the author probably expected it to be either a logical,

Re: [R] installing package with version number using namespaces & dynamic library

Prof Brian Ripley wrote: On Wed, 4 Aug 2004, Matthias Burger wrote: I wonder whether a package with namespace & dynamic library can be installed with the version number attached, ie. with the argument --with-package-versions. Is this currently possible? I've just successfully done this with pa

[R] What's ``impres''?

Dear all, In one S+ program, I found the following code. if (impres) cat("blah blah blah \n") Would someone here like to tell me what's the counterpart in R to impres in S+? Thanks in advance! Best wishes, Jinsong = (Mr.) Jinsong Zhao Ph.D. Candidate School of the Environment Nanjing Un

Re: [R] installing package with version number using namespaces & dynamic library

On Wed, 4 Aug 2004, Matthias Burger wrote: > I wonder whether a package with namespace & dynamic library can be installed > with the version number attached, ie. with the argument --with-package-versions. > Is this currently possible? I've just successfully done this with package tree, so yes.

Re: [R] How to select a whole column? Thanks!

Thank all of you for your kindly help. --- Jinsong Zhao <[EMAIL PROTECTED]> wrote: > Dear all, > > I hope to remove a whole column from a data frame or matrix (> 2000 > columns). All value in the column are same. The first thing is to > select those columns. > > For instance, I hope to remove

Re: [R] keep.source.pkgs()

Thomas Lumley wrote: > The reason why detach and reload doesn't work but restarting does work for > utils is that detach() does not unload the package, it only detaches it. > This distinction was introduced with namespaces. A package can be loaded > but not in the search path. Ah-ha. The disti

[R] installing package with version number using namespaces & dynamic library

Hi, I wonder whether a package with namespace & dynamic library can be installed with the version number attached, ie. with the argument --with-package-versions. Is this currently possible? Using R 1.9.1 on Debian 3.0 I encounter a problem when trying to load a package installed with R91 CMD

[R] Constructing a VAR model using dse

Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Received-SPF: none (hypatia: domain of [EMAIL PROTECTED] does not designate permitted sender hosts) X-Virus-Scanned: by amavisd-new at stat.math.ethz.ch X-Spam-Checker-Version: SpamAssassin 2.63 (2004-01-11) on hypatia.

[R] R Matrix package solve

hello. I have a query about the Matrix package for R. I wrote some code a while ago using the Matrix package version 1.6.2 with an early version of R, to do some linear least squares for regression: xn [,1] [,2] [,3] [,4] [1,]1 0.7429352 0.5519528 0.4100652 [2,]1 0.744

Re: [R] load shared object

I run R version 1.9.1 and i tried using other name... Il mer, 2004-08-04 alle 11:57, Prof Brian Ripley ha scritto: > Which version of R is this? (See the posting guide, please.) > > Some versions of R (e.g. 1.8.0) already had "convolve" loaded and you need > to use another name or use the PACK

Re: [R] load shared object

Which version of R is this? (See the posting guide, please.) Some versions of R (e.g. 1.8.0) already had "convolve" loaded and you need to use another name or use the PACKAGE argument. It works in the current 1.9.1. On Wed, 4 Aug 2004, Federico Cantini wrote: > Hi all, > i have some problem in

[R] load shared object

Hi all, i have some problem in using shared objects. I tried the example found in "Writing R Extension", pg. 33 I used the .c file prova.c : --- #include #include void convolve(double *a, int *na, double *b, int *nb, double *ab) {

[R] undesirable arima() return code "feature"

hi, the return value 'code' from optim in arima() does not match the warning message code if (method != "CSS") && (tranform.pars==TRUE) && (final iteration MA estimate is not invertible) (res in the source code is overwritten by a re-fitting with invertible MA estimates.) is this a desirable feat

Re: [R] which package for spatial autocorr.

I think you are looking for the spatial correlogram or variogram. Try help.search("variogram"). There is a long list, and of those fields, geoR, gstat, sgeostat, spatial look the most relevant. As spatial ships with R and is simple I would start with that. On Wed, 4 Aug 2004, temiz wrote: >

[R] profile mle in stats4 with ndeps option for optim

Hi! When I use fit <- mle(pnbd.ll, start=list(r=1,a=1,s=1,b=1), method="BFGS", control=list(trace=traceLevel, REPORT=1, ndeps=c(1e-3,1e-3,5e-4,1e-3))) and afterward profile(fit), the fit contains only NAs. This is due to the fact, that optim still gets ndeps of original length while one

Re: [R] which package for spatial autocorr.

Prof Brian Ripley wrote: On Wed, 4 Aug 2004, temiz wrote: hello which package do you recommend for spatial autocorrelation ? regards Ahmet Temiz Spatial autocorrelation of what? sampled continuous surfaces lattice data aggregate data on irregularly-shaped units such as counties point pa

Re: [R] which package for spatial autocorr.

Have a look at fields, grasper, spatstat packages. Bye A.S. Alessandro Semeria Models and Simulations Laboratory Montecatini Environmental Research Center (Edison Group), Via Ciro Menotti 48, 48023 Marina di Ravenna (RA), Italy Tel. +39 544 536811 Fax. +39 544 538663

Re: [R] which package for spatial autocorr.

On Wed, 4 Aug 2004, temiz wrote: > hello > > which package do you recommend for spatial autocorrelation ? > > regards > > Ahmet Temiz Spatial autocorrelation of what? sampled continuous surfaces lattice data aggregate data on irregularly-shaped units such as counties point patterns a

[R] which package for spatial autocorr.

hello which package do you recommend for spatial autocorrelation ? regards Ahmet Temiz __ Inflex - installed on mailserver for domain @deprem.gov.tr Queries to: [EMAIL PROTECTED] __ The views and opinions expressed in this e-ma