[R] Deviance function in regression trees

Hello all. I have heard over and over that CART and its various tree-like brethren are non-parametric techniques. When I read the chapter in Chambers and Hastie on tree-based models it states that tree-based models can be generalized (GTMs) in a manner similar to GLMs by specifying a different

[R] Legend box line thickness

I am making a plot and am merely trying to increase the line thickness, or width, of the box drawn around the legend. The help page on 'legend' was of no use. Does anyone have any ideas? [[alternative HTML version deleted]] __

Re: [R] Type II and III sum of square in Anova (R, car package)

I cannot resist a very brief entry into this old and seemingly immortal issue, but I will be very brief, I promise! Amasco Miralisus suggests: As I understood form R FAQ, there is disagreement among Statisticians which SS to use

Re: [R] Help with Functions

Hi check out R-and-octave.txt on the contributed docs section of CRAN. HTH Robin On 28 Aug 2006, at 17:50, Lord Tyranus wrote: Hello wizards, I need to convert the following functions (prestd, poststd, prepca) of matlab to R. Does Somebody knows how to do it. A description of the

Re: [R] Deviance function in regression trees

The short answer is that a Poisson distribution is a discrete distribution: if that is appropriate to your data the rpart function (in the package of that name) has a suitable option. On Mon, 28 Aug 2006, Solomon Dobrowski wrote: Hello all. I have heard over and over that CART and its various

Re: [R] Firefox extension fo R Site Search

ecatchpole a écrit : Romain Francois wrote on 08/28/2006 04:23 PM: = Search for your R routines directly from Firefox! http://addictedtor.free.fr/rsitesearch = When I try to search

Re: [R] standardized partial regression coefficients

Yuval Sapir wrote: Hi all, I am relatively new to R, so let me know if I missed something trivial. I want to perform path-analysis with at least three levels of explaining variables (i.e., A affects B that affects C). I perform multiple regression for each set of variables, and get

[R] EOF and CCA analysis

Hello! I would like to do Empirical Orthogonal functions and Canonical correlation analysis on satellite data. My matrices are going to be very big (more than 10,000 locations). Are there limitations in R regarding the size of the matrix? thanks a lot regards Isidora

[R] AffyChip Background Analysis

Dear list, I want to analyse some HG133Plus2.0 Affymetrix chips. The first thing I intent to do, is just to perform a background correction (mas, rma, gcrma,...) with the cel files. Then I want to take a look at the files. How can I do this ? Gunther

Re: [R] Remove empty list from list - remove only one row and make as matrix

Dear all, After I work around, I found in my list of data with only one row which need to remove or make it as matrix. Here I write again my other toy example: x - list(matrix(1:20, 5, 4),matrix(1:20, 5, 4),matrix(1:20, 5, 4),matrix(1:20, 5, 4),matrix(1:20, 5, 4)) y - list(c(1, -1, -1, 1,

Re: [R] Type II and III sum of square in Anova (R, car package)

Amasco, In general it is dangerous to attempt to interpret a main effect that is included in an interaction, regardless of wether or not the interaction is significant. If you want to make a valid inference about a main effect it is safest to do so after dropping any interaction that contains the

Re: [R] screen resolution effects on graphics

In thinking about this some more Romain's idea of using the browser to get this information can be done like this. This solution only works with Internet Explorer: library(RDCOMClient) ie - COMCreate(InternetExplorer.Application) ie$Navigate(about:blank) width -

Re: [R] Remove empty list from list - remove only one row and make as matrix

try the following: # a dff[sapply(dff, is.matrix)] # b lapply(dff, function(x) if(!is.matrix(x)) rbind(x) else x) I hope it helps. Best, Dimitris Dimitris Rizopoulos Ph.D. Student Biostatistical Centre School of Public Health Catholic University of Leuven Address: Kapucijnenvoer 35,

Re: [R] EOF and CCA analysis

More than 10,000 locations but how many variables? Like all computer programs there are limitations, but they are largely imposed by your environment, so what OS and how much RAM do you have? On Tue, 29 Aug 2006, isidora k wrote: Hello! I would like to do Empirical Orthogonal functions and

Re: [R] Remove empty list from list - remove only one row and make as matrix

Dear all, Dimitris, thanks for your great help and quick response. Best, Muhammad Subianto dff[sapply(dff, is.matrix)] [[1]] [,1] [,2] [,3] [,4] [,5] [1,]16 11 161 [2,]49 14 191 [3,]5 10 15 201 [[2]] [,1] [,2] [,3] [,4] [,5] [1,]

Re: [R] EOF and CCA analysis

I have got windows and 1Gb ram. my matrices are monthly data for 10 years for sometimes more than 10,000 locations. I am going to perform the EOF on one variable at a time and then the CCA on the principal components that I will get from EOF. Do you think I could do that in R?I could also find a

[R] MODWT exceeds sample size

Hello, I get the following message when I try to load a time series of 128 stock returns. Error in modwt(stock, wf = la8, n.levels = 8, boundary = periodic) : wavelet transform exceeds sample size in modwt I thought that MODWT had no restrictions on the sample size? Any help? --

Re: [R] EOF and CCA analysis

That's a 10,000 x 120 matrix, if I understand you right. That is quite modest. The key issue is to be able to do an SVD: A - matrix(rnorm(1e4*120), 1e4, 120) dim(A) [1] 1 120 system.time(svd(A)) [1] 2.79 0.13 2.93 NA NA on a similar machine to yours, using 50Mb. It would be

Re: [R] AffyChip Background Analysis

Gunther Höning [EMAIL PROTECTED] writes: Dear list, I want to analyse some HG133Plus2.0 Affymetrix chips. The first thing I intent to do, is just to perform a background correction (mas, rma, gcrma,...) with the cel files. Then I want to take a look at the files. How can I do this ? You

[R] First elements of a list.

Suppose I have the following list: a - strsplit(c(John;Smith, Jane;Doe, koda, gunner), ;) I want to get to these two vectors without looping... firstNames:c(John, Jane, koda, gunner) lastNames:c(Jane, Doe, NA, NA) Thanks cn [[alternative HTML version deleted]]

Re: [R] First elements of a list.

sapply(a, [, 1) [1] John Jane koda gunner sapply(a, [, 2) [1] Smith Doe NA NA --- Jacques VESLOT CNRS UMR 8090 I.B.L (2ème étage) 1 rue du Professeur Calmette B.P. 245 59019 Lille Cedex Tel : 33 (0)3.20.87.10.44 Fax

[R] symbols in coplots

Kind folks, I have a data frame of mean values for 14 levels and 5 factors. I'd like to use a coplot to illustrate how the mean values change. Can anyone provide an example of how I can specify different ploting symbols in this plot. I'd like to use either use a five different colors (col) for

[R] Bioconductor installation errors

Hello, I follow the Bioconductor instruction (http://www.bioconductor.org/download http://www.bioconductor.org/download ) to install Biocoductor, there have some errors: /usr/lib/R/bin/SHLIB: line 115: make: command not found chmod: cannot access `/usr/local/lib/R/site-library/affyio/libs/*':

Re: [R] Bioconductor installation errors

Ge, Weigong* [EMAIL PROTECTED] writes: Hello, I follow the Bioconductor instruction (http://www.bioconductor.org/download http://www.bioconductor.org/download ) to install Biocoductor, there have some errors: Please post questions about Bioconductor to the bioconductor mailing list:

Re: [R] Bioconductor installation errors

Hi, You don't say, but the errors make me think you are using Linux. (Please specify your OS when you have problems). It sounds like you are missing some of the Essential programs under Unix - they really are essential. I think you need to reread the R admin manual, as instructed on the

[R] spectral clustering

Is there a function in R that does spectral clustering? Thanks ../Murli [[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

Re: [R] spectral clustering

Nair, Murlidharan T a écrit : Is there a function in R that does spectral clustering? Thanks ../Murli ** PLEASE do read the posting guide http://www.R-project.org/posting-guide.html ** Hi, You would get a faster answer asking to RSiteSearch rather than this list. Romain

[R] passing namees

R 2.3.1 I wrote a little script to do some cross correlations. The symbols are in a text file like so: symbols.txt ibm dd csco require(tseries) symbols - scan(symbols.txt, what = 'character') for(line in 1:(length(symbols)-1)) { assign(symbols[line], get.hist.quote(instrument =

Re: [R] how to contrast with factorial experiment

Hello, R experts, If I understand Ted's anwser correctly, then I can not contrast the mean yields between sections 1-8 and 9-11 under Trt but I can contrast mean yields for sections 1-3 and 6-11 because there exists significant interaction between two factors (Trt:section4, Trt:section5).

[R] [R-pkgs] The rpanel package

The rpanel package builds on the tcltk package to provide simple interactive controls for R functions, in particular to provide simple forms of dynamic graphics. The intention is to make this form of control particularly easy for R users to implement, with full documentation. The necessary

Re: [R] passing namees

Put the data into a list, not into individual variables. Something like this (untested): L - sapply(symbols[-length(symbols)], get.hist.quote, start = 2005-01-09, quote = Close, simplify = FALSE) mat - do.call(cbind, L) cor.mat - cor(mat, use = complete) symnum(cor.mat) On 8/29/06,

[R] Write signed short into a binary file (follow up and conclusion)(for real)

Somebody pointed me to the right spot in the documentation, and kindly and humorously 'suggested' to me to do the following: My Apologies, everybody! I should have read docs a bit better, actually... ...will do better next time! luca - Original Message - From: [EMAIL PROTECTED] To:

[R] forestplot fucntion in rmeta package

Dear R users, I would like to adjust the x axis the way I wanted using forestplot(labeltext, mean, lower, upper, align = NULL, xlab = , zero = 0, graphwidth = unit(2, inches), col = meta.colors(), xlog = FALSE). I tried using xaxt=n and then redefine the axis using axis(1, at=c(0,0.5,1.0

[R] Dendrogram troubles

Hi, I am making a dendrogram with 180 terminal values. Whether I keep it horizontal or vertical, it gives a 'squished' graph that refuses to be stretched beyond the window size and I cannot read the labels. (I'm using hclust and then plot to make the tree.) Is there a way to stretch the graph in

[R] Key() and par(mfrow)

Hi Folks, I want to use key() to position the legend on top of the page in the following example. Prefer not to use locator() par(mfrow = c(2,2)) plot(1:4, title=Plot Number1) plot(rnorm(10), title=Plot Number2) plot(1:10, title=Plot Number3) key(x,y, text=list(c(Alpha,Beta)),

[R] lattice/xyplot: plotting 4 variables in two panels - can this be done?

Hi, I would like to create a plot of y1,y2,y3,y4 against x for several subjects such that y1 and y2 are plotted against x in one panel and y3 and y4 against x in another panel. Thus if there are 3 subjects I should end up with 6 panels. Is there a simple way of doing so (i.e. without calling

[R] subset by two variables

I'm using this syntax to create data subsets for plots: subset=source==Both. Now I would like to create a subset defined by two different variables like this: subset=source==Both subset=site==home but this syntax is not correct. The documents in the manual for subset seem to be creating

[R] lattice and several groups

Dear R-list, I would like to use the lattice library to show several groups on the same graph. Here's my example : ## the data f1 - factor(c(mod1,mod2,mod3),levels=c(mod1,mod2,mod3)) f1 - rep(f1,3) f2 - factor(rep(c(g1,g2,g3),each=3),levels=c(g1,g2,g3)) df -

[R] Producing R demos

Hello! I have found terrific demo or R package functionality at http://had.co.nz/reshape/french-fries-demo.html Author has told me off-list that he is using SnapzProX (on mac), and ghostwriter (http://had.co.nz/ghostwriter/) to automate the typing. Unfortunatelly, I do not have mac ;) Can

[R] my email: jonathan gheyssens (université de Montreal)

Jonathan Gheyssens M.Sc Economie Appliquée IEA - HEC Montréal [EMAIL PROTECTED] 514-581-8009 514-678-5231 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide

Re: [R] lattice and several groups

I would like to use the lattice library to show several groups on the same graph. Here's my example : ## the data f1 - factor(c(mod1,mod2,mod3),levels=c(mod1,mod2,mod3)) f1 - rep(f1,3) f2 - factor(rep(c(g1,g2,g3),each=3),levels=c(g1,g2,g3)) df - data.frame(val=c(4,3,2,5,4,3,6,5,4),

[R] Substring and strsplit

Dear R People: I am trying to split a character vector into a set of individual letters: Ideal: x3 - c(dog) d o g I tried the following: strsplit(x3) Error in strsplit(x3) : argument split is missing, with no default strsplit(x3,1) [[1]] [1] dog I know that this is incredibly simple, but

Re: [R] Substring and strsplit

On Tue, 29 Aug 2006, Erin Hodgess wrote: Dear R People: I am trying to split a character vector into a set of individual letters: Ideal: x3 - c(dog) d o g I tried the following: strsplit(x3) Error in strsplit(x3) : argument split is missing, with no default strsplit(x3,1) [[1]] [1]

Re: [R] Substring and strsplit

Use '' as parameter to strsplit x3 - 'dog' strsplit(x3, '') [[1]] [1] d o g On 8/29/06, Erin Hodgess [EMAIL PROTECTED] wrote: Dear R People: I am trying to split a character vector into a set of individual letters: Ideal: x3 - c(dog) d o g I tried the following: strsplit(x3)

Re: [R] lattice/xyplot: plotting 4 variables in two panels - can this be done?

On 8/29/06, Søren Højsgaard [EMAIL PROTECTED] wrote: Hi, I would like to create a plot of y1,y2,y3,y4 against x for several subjects such that y1 and y2 are plotted against x in one panel and y3 and y4 against x in another panel. Thus if there are 3 subjects I should end up with 6 panels.

[R] Handling realisations in geoRglm

Dear R users: I want to model mosquito count data based on landcover attributes and meteorological variables using a Poisson GLSM in the geoRglm package. I have monthly mosquito counts over more than 20 years with repeated observations from individual trap sites over time. I have used

[R] Help on apply() function

Respected Sir/Madam, I have a problem with apply function. I have to two matrices of dimension of one column but n rows. I have to check whether one matrix is greater than other by going thru each row (ie) using if condition to check one matrix with another matrix. I like to use apply()

Re: [R] lattice and several groups

Try this: xyplot(val ~ x, data = df, type = p, col = as.numeric(df$f1), pch = as.numeric(df$f2)) key1 - list(border = TRUE, colums = 2, text = list(levels(df$f1)), points = list(pch = 1:nlevels(df$f1)) ) key2 - list(border = TRUE, colums = 2, text = list(levels(df$f2)),

Re: [R] Producing R demos

I have not used this but wink is a free demo-maker for Windows available at: http://www.debugmode.com/wink/ Click the red on green arrow on that page to a (very short) demo. On 8/29/06, Gregor Gorjanc [EMAIL PROTECTED] wrote: Hello! I have found terrific demo or R package functionality at

Re: [R] Producing R demos

Gabor Grothendieck wrote: I have not used this but wink is a free demo-maker for Windows available at: http://www.debugmode.com/wink/ Click the red on green arrow on that page to a (very short) demo. Thanks! Do you perhaps also know equivalent of ghostwriter (link is bellow) for

Re: [R] C compile problem on Ubuntu linux

On 20 August 2006 at 15:29, Frank E Harrell Jr wrote: | Manuel Castejón Limas wrote: | Hello, | I've just compiled Hmisc ok under dapper. | I think you need to further install some packages. | Have you installed libc6-dev? | I would start installing the build-essential package. | Best

Re: [R] Producing R demos

Don't know. I would check whether the functionality is included in wink. On 8/29/06, Gregor Gorjanc [EMAIL PROTECTED] wrote: Gabor Grothendieck wrote: I have not used this but wink is a free demo-maker for Windows available at: http://www.debugmode.com/wink/ Click the red on green

Re: [R] problem in install on ubuntu

On 24 August 2006 at 11:35, Ryan Austin wrote: | Hi Bruno, | | Your missing the Basic Linear Algebra Subroutines 3.0 package. | | apt-get install refblas3 | | should fix the problem. (At least in Debian, should be the same for Ubuntu) The 'empty' package r-base-dev depends on 'refblas3-dev |

Re: [R] lattice/xyplot: plotting 4 variables in two panels - can this be done?

Try xyplot.zoo in the zoo package (be sure you have the latest zoo version). One caveat is that xyplot.zoo is under development and could change. Here we use the builtin data set anscombe as an example: # display the anscombe data set anscombe library(lattice) library(zoo) # create zoo object

Re: [R] lattice and several groups

Note that before entering this you need: library(lattice) library(grid) # to access the viewport function On 8/29/06, Gabor Grothendieck [EMAIL PROTECTED] wrote: Try this: xyplot(val ~ x, data = df, type = p, col = as.numeric(df$f1), pch = as.numeric(df$f2)) key1 - list(border =

[R] Problem plotting with xyplot

This is in regard to Dan Norlund's post from December 2003 (available at https://stat.ethz.ch/pipermail/r-help/attachments/20031225/1bce02b8/attachment.pl ) While I agree with Prof. Ripley's warning against fitting so few observations per panel, this is not actually what causes the error.

Re: [R] Help on apply() function

Anusha anu1978 at hotmail.com writes: Respected Sir/Madam, I have a problem with apply function. I have to two matrices of dimension of one column but n rows. I have to check whether one matrix is greater than other by going thru each row (ie) using if condition to check one matrix with

[R] Need help to estimate the Coef matrices in mAr

Dear R users, I am using mAr package to fit a Vector autoregressive model to my data. But here I want to put some predetermined values for some elements in coefficient matrix that mAr.est going to estimate. For example if p=3 then I want to put A3[1,3] = 0 and keep rest of the elements of

[R] Cross-correlation between two time series data

Hi all, I have two time series data (say x and y). I am interested to calculate the correlation between them and its confidence interval (or to test no correlation). Function cor.test(x,y) does the test of no correlation. But this test probably is wrong because of