Re: [R] How to convert c:\a\b to c:/a/b

On Wed, 29 Jun 2005, David Duffy wrote: I couldn't resist adding a more literal answer This can only work for escapes which are preserved. The parser maps \n to a character (LF) and the deparser maps it back to \n. This happens to be true of \a \b \f \n \r \t \v \\ but no others. For example,

Re: [R] where can i download the metrics package?

There are several packages within rmetrics such as fSeries, fBasics, fExtremes, and so on. You can download those in the usual way. From: Spencer Graves [EMAIL PROTECTED] To: ronggui [EMAIL PROTECTED] CC: R [EMAIL PROTECTED] Subject: Re: [R] where can i download the metrics package? Date: Tue,

Re: [R] quick way to construct formula

Here is a way: it uses 'paste' but I dont think it is a problem anyway to use it. Nevertheless, it is surely a bad idea to fit any model with more than 25 terms... main_effects = paste(nam,collapse=+) inter - outer(nam,nam,paste,sep=:) inter -

Re: [R] enhanced MDS

Try also ?sphpca (library(psy) -- new version 0.7) Best Bruno Bruno Falissard INSERM U669, PSIGIAM Paris Sud Innovation Group in Adolescent Mental Health Maison de Solenn 97 Boulevard de Port Royal 75679 Paris cedex 14,

Re: [R] quick way to construct formula

On Tue, 28 Jun 2005, Luke wrote: Dear R users, I have a data with 1000 variables named x1, x2, ..., x1000, and I want to construct a formula like this format: ~x1+x2+...+x1000+x1:x2+x1:x3+x999:x1000+log(x1)+...+log(x1000) That is: the base variables followed by all interaction terms and

Re: [R] enhanced multidimensional scaling?

Karen == Karen Kotschy [EMAIL PROTECTED] on Tue, 28 Jun 2005 13:13:31 +0200 writes: Karen Dear R list Would anyone be able to tell me whether Karen it is possible to do enhanced multidimensional Karen scaling (enhanced MDS) in R? In other words, Karen something that goes

[R] comparison of packages for Unit Root test

Dear R Users, Could somebody please compare the packages of unit root test ( Uroot, Ucra, tseries and fseries ) regarding the type of test ( without constant and trend, with constant , and with constant and trend ) ? Regards, Amir Safari

[R] Running SVM {e1071}

Dear David, Dear Friends, After any running svm I receive different results of Error estimation of 'svm' using 10-fold cross validation. What is the reason ? It is caused by the algorithm, libsvm , e1071 or something els? Which value can be optimal one ? How much run can reach to the

Re: [R] comparison of packages for Unit Root test

On Wed, 29 Jun 2005 03:08:23 -0700 (PDT) Amir Safari wrote: Dear R Users, Could somebody please compare the packages of unit root test ( Uroot, Ucra, tseries and fseries ) regarding the type of test ( without constant and trend, with constant , and with constant and trend ) ? IMHO,

Re: [R] Running SVM {e1071}

Amir Safari wrote: Dear David, Dear Friends, After any running svm I receive different results of Error estimation of 'svm' using 10-fold cross validation. What is the reason ? It is caused by the algorithm, libsvm , e1071 or something els? Which value can be optimal one ? How much

Re: [R] svm and scaling input

[EMAIL PROTECTED] wrote: Dear All, I've a question about scaling the input variables for an analysis with svm (package e1071). Most of my variables are factors with 4 to 6 levels but there are also some numeric variables. I'm not familiar with the math behind svms, so my assumtions maybe

Re: [R] Running SVM {e1071}

Dear David, Dear Friends, After any running svm I receive different results of Error estimation of 'svm' using 10-fold cross validation. using tune.svm(), or the `cross' parameter of svm()? What is the reason ? It is caused by the algorithm, libsvm , e1071 or something els? The

[R] Memory Management under Linux: Problems to allocate large amounts of data

Dear Group I'm still trying to bring many data into R (see older postings). After solving some troubles with the database I do most of the work in MySQL. But still I could be nice to work on some data using R. Therefore I can use a dedicated Server with Gentoo Linux as OS hosting only R. This

[R] coxph, survfit and Brier score

Hello and apologies for a very long question. I thought it better to be verbose and clear than short and imprecise. I am trying to compute the brier score comparing true surv object of test data to predictions from train data (using sbrier in ipred package). I am having trouble getting the right

Re: [R] Producing character given i.e. | with plotmath

Hello! Does someone know how to produce L(y|mu) with plotmath? Some code with unsuccessfull results: plot(dnorm(x = seq(from = -4, to = 4, by = 0.1)), type = l) ## Not what I want legend(legend = c(expression(L(y:mu))), x = topright) ## Strange, is this a bug? legend(legend

[R] x*x*x*... vs x^n

Hi I have been wondering if there one can speed up calculating small powers of numbers such as x^8 using multiplication. In addition, one can be a bit clever and calculate x^8 using only 3 multiplies. look at this: f1 - function(x){x*x*x*x*x*x*x*x} f2 - function(x){x^8} f3 -

[R] x*x*x*... vs x^n

Something like this is exploited very nicely in the mtx.exp for matrix powers in the Malmig package, actually. Hi I have been wondering if there one can speed up calculating small powers of numbers such as x^8 using multiplication. In addition, one can be a bit

Re: [R] x*x*x*... vs x^n

I tried your code and got different results: system.time(ignore - f1(a)) [1] 0.83 0.09 1.08 NA NA system.time(ignore - f2(a)) [1] 0.38 0.01 0.41 NA NA system.time(ignore - f3(a)) [1] 0.32 0.04 0.43 NA NA So I tried it again but with a

Re: [R] x*x*x*... vs x^n

On 6/29/2005 7:32 AM, Robin Hankin wrote: Hi I have been wondering if there one can speed up calculating small powers of numbers such as x^8 using multiplication. In addition, one can be a bit clever and calculate x^8 using only 3 multiplies. look at this: f1 -

[R] range of input data

Hi, I've written this function: g = function(test,p1,p2) { test=sort(test) merke=0 for (z in 1:length(test)) { F1=((2*z-1)/length(test)) F21=log(plnorm(test[z],p1,p2)) F22=log(1-plnorm(test[length(test)+1-z],p1,p2)) F2= F21+F22 merke=merke+F1*F2 } return(-length(test)*-merke) }

Re: [R] Memory Management under Linux: Problems to allocate large amounts of data

Let's assume this is a 32-bit Xeon and a 32-bit OS (there are 64-bit-capable Xeons). Then a user process like R gets a 4GB address space, 1GB of which is reserved for the kernel. So R has a 3GB address space, and it is trying to allocate a 2GB contigous chunk. Because of memory

Re: [R] x*x*x*... vs x^n

Hi Duncan On Jun 29, 2005, at 02:04 pm, Duncan Murdoch wrote: On 6/29/2005 7:32 AM, Robin Hankin wrote: Hi I have been wondering if there one can speed up calculating small powers of numbers such as x^8 using multiplication. In addition, one can be a bit clever and calculate x^8 using

Re: [R] x*x*x*... vs x^n

On Wed, 29 Jun 2005, Duncan Murdoch wrote: On 6/29/2005 7:32 AM, Robin Hankin wrote: I have been wondering if there one can speed up calculating small powers of numbers such as x^8 using multiplication. In addition, one can be a bit clever and calculate x^8 using only 3 multiplies. look

Re: [R] x*x*x*... vs x^n

On 6/29/2005 9:31 AM, Robin Hankin wrote: Hi Duncan On Jun 29, 2005, at 02:04 pm, Duncan Murdoch wrote: On 6/29/2005 7:32 AM, Robin Hankin wrote: Hi I have been wondering if there one can speed up calculating small powers of numbers such as x^8 using multiplication. In addition,

[R] all connections are in use error during lazyload stage of packa ge installation

Hi, I suddenly started getting strange errors while working on my caTools package: RCMD install C:/programs/R/rw2011/src/library/caTools .. preparing package caTools for lazy loading Error in file(file, r, encoding = encoding) : all connections are

Re: [R] all connections are in use error during lazyload stage of packa ge installation

On 6/29/05, Tuszynski, Jaroslaw W. [EMAIL PROTECTED] wrote: Hi, I suddenly started getting strange errors while working on my caTools package: RCMD install C:/programs/R/rw2011/src/library/caTools .. preparing package caTools for lazy loading Error in

Re: [R] x*x*x*... vs x^n

On Jun 29, 2005, at 02:47 pm, Duncan Murdoch wrote: On 6/29/2005 9:31 AM, Robin Hankin wrote: Hi Duncan library(gsl) system.time(ignore - pow_int(a,8)) [1] 1.07 1.11 3.08 0.00 0.00 why the slow execution time? Shouldn't you ask the gsl maintainer that? :-) well I did ask myself,

[R] moving correlation coef ?

Hello, R gives us the correlation functions cor(). (Many thanks ;-)) Does it also exist a moving correlation coefficient ? (like the moving average). If not, could someone give me some infos or link on how to practically implement such a function in R. (I did search for moving correlation on the

Re: [R] moving correlation coef ?

vincent wrote: Hello, R gives us the correlation functions cor(). (Many thanks ;-)) Does it also exist a moving correlation coefficient ? (like the moving average). If not, could someone give me some infos or link on how to practically implement such a function in R. (I did search for

Re: [R] all connections are in use error during lazyload stage of packa ge installation

I found the problem, by doing comparison of directories and files of working and not working versions, and applying changes one by one until one caused install to fail. It was a case of having a call to a source function somewhere in my code, that I forgot about. I was definitely doing

Re: [R] x*x*x*... vs x^n

I ran 100 repetitions of the 3 multiplications that Robin had compared. Here are the summaries of system times (I only took the first component of system.time) that I obtained. It is clear that f1() is nearly twice as slow as f2() which is slightly slower (not 3 times slower as claimed by Robin)

Re: [R] x*x*x*... vs x^n

In general, the Russian peasant algorithm, which requires only O(log n) multiplications, is very good. Section 4.6.3 of Knuth's The Art of Computer Programming. Volume 2: Seminumerical Algorithms has an in depth discussion. I have had to use this in the past, when computers were slower and

[R] Selecting rows regarding the frequency of a factor variable.

Hi and sorry to disturb, I'll try to be as clear as possible: I want to select rows of a data frame called Data2.Iso regarding the frequency of a factor variable called Variete that I want =4. I used function table to have the frequency: FRAMEVARIETE-as.data.frame(table(Data2.Iso$Variete))

Re: [R] moving correlation coef ?

or ?rapply in package zoo. spencer graves Sundar Dorai-Raj wrote: vincent wrote: Hello, R gives us the correlation functions cor(). (Many thanks ;-)) Does it also exist a moving correlation coefficient ? (like the moving average). If not, could someone give me some infos or link

Re: [R] Selecting rows regarding the frequency of a factor variab le.

See if this does what you want: dat - data.frame(f=factor(sample(letters[1:10], 100, replace=TRUE)), x=runif(100)) str(dat) `data.frame': 100 obs. of 2 variables: $ f: Factor w/ 10 levels a,b,c,d,..: 2 5 10 9 10 3 9 8 3 1 ... $ x: num 0.9162 0.0481 0.3048 0.0938 0.8599 ... g -

[R] MLE with optim

Hello, I tried to fit a lognormal distribution by using optim. But sadly the output seems to be incorrect. Who can tell me where the bug is? test = rlnorm(100,5,3) logL= function(parm, x,...) -sum(log(dlnorm(x,parm,...))) start= list(meanlog=5, sdlog=3)

Re: [R] x*x*x*... vs x^n

Looking at the code for gsl_pow_int, I see they do use that method. David L. Reiner -Original Message- From: [EMAIL PROTECTED] [mailto:r-help- [EMAIL PROTECTED] On Behalf Of David Reiner [EMAIL PROTECTED] Sent: Wednesday, June 29, 2005 9:50 AM To: r-help Subject: Re: [R]

Re: [R] MLE with optim

Carsten Steinhoff wrote: Hello, I tried to fit a lognormal distribution by using optim. But sadly the output seems to be incorrect. Who can tell me where the bug is? test = rlnorm(100,5,3) logL= function(parm, x,...) -sum(log(dlnorm(x,parm,...))) start=

Re: [R] MLE with optim

the following work for me: x - rlnorm(1000, 5, 3) fn - function(parms, dat) -sum(dlnorm(dat, parms[1], parms[2], log = TRUE)) optim(c(5, 3), fn, dat = x) library(MASS) fitdistr(x, log-normal, list(meanlog = 5, sdlog = 3)) I hope it helps. Best, Dimitris Dimitris Rizopoulos Ph.D.

Re: [R] moving correlation coef ?

Thank you for your answers. In fact, i believe my question wasn't precise enough. I don't want to have a moving/sliding windows over the data to correlate (i am already doing that). If I have 2 vectors X = (x1, x2, x3, ..., xt) Y = (y1, y2, x3, ..., yt) I want the most recent elements (t) to

[R] poly() in lm() leads to wrong coefficients (but correct residuals)

Dear all, I am using poly() in lm() in the following form. 1 DelsDPWOS.lm3 - lm(DelsPDWOS[,1] ~ poly(DelsPDWOS[,4],3)) 2 DelsDPWOS.I.lm3 - lm(DelsPDWOS[,1] ~ poly(I(DelsPDWOS[,4]),3)) 3 DelsDPWOS.2.lm3 - lm(DelsPDWOS[,1]~DelsPDWOS[,4]+I(DelsPDWOS[,4]^2)+I(DelsPDWOS[,4]^3)) 1 and 2 lead to

Re: [R] poly() in lm() leads to wrong coefficients (but correct residuals)

On Wed, 2005-06-29 at 18:19 +0200, Andreas Neumann wrote: Dear all, I am using poly() in lm() in the following form. 1 DelsDPWOS.lm3 - lm(DelsPDWOS[,1] ~ poly(DelsPDWOS[,4],3)) 2 DelsDPWOS.I.lm3 - lm(DelsPDWOS[,1] ~ poly(I(DelsPDWOS[,4]),3)) 3 DelsDPWOS.2.lm3 -

Re: [R] moving correlation coef ?

vincent wrote: Thank you for your answers. In fact, i believe my question wasn't precise enough. I don't want to have a moving/sliding windows over the data to correlate (i am already doing that). If I have 2 vectors X = (x1, x2, x3, ..., xt) Y = (y1, y2, x3, ..., yt) I want the most

Re: [R] moving correlation coef ?

One common weighting scheme is exponentially weighted, i.e., wt = L^(0:m) , where 0 L = 1 . David L. Reiner p.s. If your question is coming from a financial application, you might be interested in the R-sig-finance list, as well as reading the RiskMetrics (r) document Return to RiskMetrics:

[R] Help with regression modeling

Hello all, I'm using R version 2.0.1. I have been having trouble with my linear modeling. I have a table that looks something like this: T RSS DSS LSPFCOLS PS R RTT Actual Max COMM char 5 MSS 2

Re: [R] x*x*x*... vs x^n

I was surprised to find that I was wrong about powers of complexes: seq.pow1 - function(x,n) { + y - rep(x,n) + for(i in 2:n) y[i] - y[i-1] * x + y + } seq.pow2 - function(x,n) x^(1:n) x - 1.001 + 1i * 0.999 # several reps of the following system.time(ignore -

[R] Generalized Linear Mixed Models

Hello! I am trying to fit a Generalized Linear Mixed Model, ordinally I use GLIMMIX macros in SAS System, but I would like to fit this kind of models in R. Could anyone help me on what package I should use to? Thanks in advance Francisco [[alternative HTML version deleted]]

Re: [R] Generalized Linear Mixed Models

submit the following in R: RSiteSearch('glmm',restr='functions') -- 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

Re: [R] Generalized Linear Mixed Models

-Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] Behalf Of [EMAIL PROTECTED] Sent: 29 June 2005 18:05 To: r-help@stat.math.ethz.ch Subject: [R] Generalized Linear Mixed Models Hello! I am trying to fit a Generalized Linear Mixed Model, ordinally I use

[R] return NA

A-c(1,2,NA,7,5) B-c(3,4,1,4,1) C-c(6,5,6,NA,9) D-c(8,7,4,6,2) df1-cbind(A,B,C,D) for(i in seq(1,ncol(df1)-1, by=2)) { ifelse(df1[,i]==NA,df1[,i+1]==NA,df1[,] ) } Tried several variations but none worked. I wish to find any NA's in column's 1 or 3 and change the numerical value to the

Re: [R] return NA

You need to use is.na(df1[,i]) to test for NA. Andy From: [EMAIL PROTECTED] A-c(1,2,NA,7,5) B-c(3,4,1,4,1) C-c(6,5,6,NA,9) D-c(8,7,4,6,2) df1-cbind(A,B,C,D) for(i in seq(1,ncol(df1)-1, by=2)) { ifelse(df1[,i]==NA,df1[,i+1]==NA,df1[,] ) } Tried several variations but

Re: [R] return NA

[EMAIL PROTECTED] wrote: A-c(1,2,NA,7,5) B-c(3,4,1,4,1) C-c(6,5,6,NA,9) D-c(8,7,4,6,2) df1-cbind(A,B,C,D) for(i in seq(1,ncol(df1)-1, by=2)) { ifelse(df1[,i]==NA,df1[,i+1]==NA,df1[,] ) } Tried several variations but none worked. I wish to find any NA's in column's 1 or 3

[R] predicted survival curve from a cox model

Hi there, I have a predictor varible class which is a categorical variable and a ' coxph' is used to find the coeffients. How can I plot the predicted survival proportion based on this model? Thanks Lisa Wang Princess Margaret Hospital Toronto tel 416 946 4501

[R] plot (log scale on y-axis)

I am planning to plot my data on log scale (y-axis). There is a parameter in plot function, which is plot( ..., log=y, ...) While, the problem is that it is with base of e. Is there a way to let me change it to 10 instead of e? Thanks __

Re: [R] return NA

Here is a way to do it without a loop that could save some time for a big dataset. df1 A B C D [1,] 1 3 6 8 [2,] 2 4 5 7 [3,] NA 1 6 4 [4,] 7 4 NA 6 [5,] 5 1 9 2 df2-cbind(0,ifelse(is.na(df1),NA,0))[,-ncol(df1)-1] df2 A B C [1,] 0 0 0 0 [2,] 0 0 0 0 [3,] 0 NA 0 0

[R] sbrier (Brier score) and coxph

Hello I've decided to try and distill an earlier rather ill focused question to try and elicit a response. Any help is greatly appreciated. Why does mod.cox not work with sbrier whilst mod.km does? Can I make it work? data(DLBCL) DLBCL.surv-Surv(DLBCL$time,DLBCL$cens)

Re: [R] sbrier (Brier score) and coxph

Is this sbrier from package ipred? The short answer is that it contains ptype - class(pred) and assumes that is of length one. For a survfit.coxph fit it is of class c(survfit.cox, survfit). I suspect from the help page that this is not supported, but you need to contact the authors (as

Re: [R] How to convert c:\a\b to c:/a/b

Thank You, Prof. Ripley! Both test1.R and test2.R worked for me just now, as did the following minor modification: (x - readLines(stdin(), n=1)) D:\spencerg\dataPOWER\stats\Tukey\Boxplot_missing_Tukey2.txt Thanks again. spencer graves Prof Brian Ripley wrote:

Re: [R] How to convert c:\a\b to c:/a/b?

One other comment. Ninotech Path Copy, which can be found at: http://home.worldonline.dk/ninotech/ is a free Windows utility that appears in the Windows Explorer context menu (i.e. it appears as the Copy Path menu entry when you right click any file in Windows Explorer). I had forgotten

Re: [R] How to convert c:\a\b to c:/a/b

Note that if you want to source it rather than than run it as a batch job from the command line you will something like this. The way it works is that one puts the file name into comments that are marked with tags and the script rereads itself as data picking out the tagged lines and removing

[R] Extract fixed effects SE from lmer

Hi, Does anyone know how to extract fixed effects SE values from generalized linear mixed models estimated using the lmer function in the lme4 library? I searched attributes and structure with no luck. Thanks Frank A. La Sorte, Ph.D. Department of Fisheries and Wildlife Sciences

[R] Fwd: Extract fixed effects SE from lmer

I forgot to cc: the list on this reply. -- Forwarded message -- From: Douglas Bates [EMAIL PROTECTED] Date: Jun 29, 2005 6:28 PM Subject: Re: [R] Extract fixed effects SE from lmer To: La Sorte, Frank A. [EMAIL PROTECTED] On 6/29/05, La Sorte, Frank A. [EMAIL PROTECTED] wrote:

[R] deal package

Hi, I am wondering if anyone here used deal package in R to do the bayesian network. I am curious about its scalability: how many variables and how many observations can it handle in a reasonable time. If you have some good experience, please share your data configurations. thanks, -- Weiwei

[R] Finding out collinearity in regression

Hi, I am trying to find out a collinearity in explanatory variables with alias(). I creat a dataframe: dat - ds[,sapply(ds,nlevels)=2] dat$Y - Response Explanatory variables are factor and response is continuous random variable. When I run a regression, I have the following error: fit - aov(

Re: [R] Finding out collinearity in regression

Hi, Young Cho wrote: fit - aov( Y ~ . , data = dat) Error in contrasts-(`*tmp*`, value = contr.treatment) : contrasts can be applied only to factors with 2 or more levels I think there is a dependency in explanatory variables. So, I wanted to use alias to find out a dependency

Re: [R] Finding out collinearity in regression

At 01:45 PM 30/06/2005, Young Cho wrote: Hi, I am trying to find out a collinearity in explanatory variables with alias(). I creat a dataframe: dat - ds[,sapply(ds,nlevels)=2] dat$Y - Response Explanatory variables are factor and response is continuous random variable. When I run a regression,

[R] how to call egarch of sas in R

I use R to generate data and I need to estimate the data by egarch (that doesn't have in R). So how I can call egarch from SAS in R. Regards, luck __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the

Re: [R] moving correlation coef ?

Sundar Dorai-Raj a écrit : Perhaps ?cov.wt will work for you? Your example would be identical to: set.seed(1) X - rnorm(100); Y - rnorm(100) # using cov.wt rho1 - cov.wt(cbind(X, Y), 1:100, cor = TRUE)$cor[1, 2] # your weighting scheme rho2 - cor(X[rep(1:100, 1:100)], Y[rep(1:100,

[R] Dispersion parameter in Neg Bin GLM

Hi, Can someone tell me if it is possible to set the dispersion parameter constant when fitting a negative binomial glm in R? I've looked at the documentation and can't find the appropriate argument to pass. In STATA I can type: nbreg depvar [indepvar...], offset(offset) dispersion(constant).