Re: [R] help on ROC analysis

Thanks. library(ROCR) was used finally. It also automatically generate a plot beside the value of AUC. On Dec 31, 2007 11:38 PM, Frank E Harrell Jr [EMAIL PROTECTED] wrote: zhijie zhang wrote: Dear all, Some functions like 'ROC(Epi)' can be used to perform ROC analyssi, but it needs us

[R] access data inside package

Dear all, Happy new year! I posted a very similar question a few days ago, but probably too cluttered. Here is a tidy, minimal version: I want to make a package, with a data.frame d and a function f given below. Now, the function f needs to use the data.frame d. I could (and that's what

[R] proximity on prediction in cforest

Hello there, How to get the proximity matrix of new data in party package? Thanks. Joseph [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide

[R] Alignment and Labeling of a color key in a xyplot?

Happy New Year to all R users! I have two short questions concerning a xyplot with a color key: 1) How do I properly place (align) the color key beside the xyplot? As you can see from the code listed below, the placement of the color key is not correct. I would like the upper and lower end

[R] Variable scope R 2.6.1

I have the following procedure which worked just fine for in R 2.2.0. Recently I upgraded to 2.6.1 and now get an error: ScatterOutlier(pass_500_506[1:1000,6:12], marginal_500_506[,6:12]) Error in eval(expr, envir, enclos) : object out not found Note that I use the same workspace (and

[R] passing args from the command line

Happy New Year to all! I want to run a script from a directory on a central server on different machines, linux and windows. To determine which machine is calling the script I want to pass an argument with the call (e.g. for choosing the display device, for writing path names etc.) I tried the

Re: [R] Bootstrap Confidence Intervals

Hi again. Watching this example that appears in the help page ratio - function(d, w) sum(d$x * w)/sum(d$u * w) city.boot - boot(city, ratio, R = 999, stype = w,sim = ordinary) boot.ci(city.boot, conf = c(0.90,0.95),type = c(norm,basic,perc,bca)) I have tried to do the following (calling boot()

[R] Non-Linear Quantile Regression

Please, I have a problem with nonlinear quantile regression. My data shows a large variability and the quantile regression seemed perfect to relate two given variables. I got to run the linear quantile regression analysis and to build the graph in the R (with quantreg package). However, the up

Re: [R] Bootstrap Confidence Intervals

Thank you very much for your help, Chuck. But I don't understand the function statistic nor that his arguments make. Those arguments do not take value at any moment, according to I understand (I have not given values to d nor ind). It is not thus? Can you explain me, please? Thanks. _Fede_

[R] Specify a correct formula in R for Piecewise Linear Functions?

Dear all, I have two variables, y and x. It seems that the relationship between them is Piecewise Linear Functions. The cutpoint is 20. That is, when x20, there is a linear relationship between y and x; while x=20, there is another different linear relationship between them. How can i specify

Re: [R] access data inside package

baptiste Auguié wrote: Dear all, Happy new year! I posted a very similar question a few days ago, but probably too cluttered. Here is a tidy, minimal version: I want to make a package, with a data.frame d and a function f given below. Now, the function f needs to use the

Re: [R] passing args from the command line

Richard Müller wrote: Happy New Year to all! I want to run a script from a directory on a central server on different machines, linux and windows. To determine which machine is calling the script I want to pass an argument with the call (e.g. for choosing the display device, for

Re: [R] Alignment and Labeling of a color key in a xyplot?

Is this what you want (same as your except the draw.key and reference to grid is removed key=... is added in the xyplot call: library(lattice) x - 1:3 colorseq c(0.2, 0.5, 0.8) mycolors - gray(colorseq) xyplot(x ~ x, col = mycolors, aspect = 1, key = list(rect = list(col = mycolors), text =

Re: [R] Trying to install rjags on Mac OS X 10.5

Dear Lindsay, If you pkgconfig installed by MacPorts. Maybe it likely to be caused by JAGS install. You'll better to do sudo make uninstall ./configure --prefix=/usr/local --mandir=/usr/local/share/man make sudo make install sudo R CMD INSTALL -l

[R] predicted proximity in cforest

Hello there, Happy new year. As I know, we can get proximity of new data in randomForest package. How to get the proximity matrix of new data in party package then? Thanks. Joseph [[alternative HTML version deleted]] __ R-help@r-project.org

Re: [R] Specify a correct formula in R for Piecewise Linear Functions?

On Tue, 1 Jan 2008, zhijie zhang wrote: Dear all, I have two variables, y and x. It seems that the relationship between them is Piecewise Linear Functions. The cutpoint is 20. That is, when x20, there is a linear relationship between y and x; while x=20, there is another different linear

[R] How to convert day-month-year to Julian data number?

Hi, Is there a package for converting day-month-year type date to julian day number (JDN)? I looked around and I couldn't find any (I am pretty new to R...) Thanks and happy New Year to everybody! H. Nüzhet Dalfes Professor, Istanbul Technical University Eurasia Institute of Earth

[R] if statement problem

Hi All, I have a small dataset named das (43 cases) in which I am trying to create a binary outcome (1/0) based on the following code: if (das$age65 das$bmi30) {das$danger-1} else das$danger-0 I am setting a flag called 'danger' to 1 of the subject is over 65 and has a BMI 30. I find that

Re: [R] How to convert day-month-year to Julian data number?

Is this what you want? x - c('5/5/2007', '12/31/2007') # convert to day of year (Julian date) -- use POSIXlt strptime(x, %m/%d/%Y)$yday+1 [1] 125 365 On Jan 1, 2008 4:59 PM, Nüzhet Dalfes [EMAIL PROTECTED] wrote: Hi, Is there a package for converting day-month-year type date to julian

Re: [R] if statement problem

You need to use '' instead of '': A shorter version of your code using ifelse: das$danger - with(das, ifelse(age65 bmi30, 1, 0)) HTH -Christos -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Gerard Smits Sent: Tuesday, January 01, 2008 5:04 PM

Re: [R] if statement problem

Thanks, but I tried the single ampersand, but got a warning msg with the same lack of correct assignment: if (das$age65 das$bmi30) {das$danger-1} else das$danger-0 Warning message: In if (das$age 65 das$bmi 30) { : the condition has length 1 and only the first element will be used

Re: [R] if statement problem

You should look for your answer using the help for the if statement (?if). The cond argument should be a scalar (otherwise only the first element is used). ?if . cond: A length-one logical vector that is not 'NA'. Conditions of length greater than one are accepted with a warning,

Re: [R] if statement problem

you could try the following: das$danger - 0 das$danger[das$bmi 30 das$age 65] - 1 On Jan 2, 2008 9:16 AM, Gerard Smits [EMAIL PROTECTED] wrote: Thanks, but I tried the single ampersand, but got a warning msg with the same lack of correct assignment: if (das$age65 das$bmi30)

Re: [R] if statement problem

Hi Domenico, I was incorrectly assuming it would use a vector of equal length to my data. frame. Thanks for the clarification. Also, thanks for the many alternate programming approaches provided by others. Gerard At 02:25 PM 1/1/2008, Domenico Vistocco wrote: You should look for your answer

Re: [R] Symbolic substitution in parallel; use infinity symbol?

Actually this works beautifully as it stands: breaks - c(-Inf, -1, 1, Inf) zz - lapply(breaks, function(x) if(x==-Inf) quote(-infinity) else if (x==Inf) quote(infinity) else format(x)) lbl - mapply(function(x,y) bquote(( * .(x) * , * .(y) * ]),

[R] Subsetting data frame problem....

Dear R users, I'm new but already fascinated R user so please forgive for my ignorance. I have the problem, I read most of help pages but couldn't find the solution. The problem follows I have large data set 10,000 rows and more than 100 columns... Say something like

Re: [R] Subsetting data frame problem....

You could try complete.case.df - na.omit(df) Ross Darnell -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Marko Milicic Sent: Wednesday, 2 January 2008 11:50 AM To: r-help@r-project.org Subject: [R] Subsetting data frame problem Dear R users,

Re: [R] COMPAR.GEE error with logistic model

My guess is that this combination of variables produces separation in the data: Too many (all?) of the response 1's are in at level of VAR3, and the 0's are at the other level (or vice versa). HTH, Simon. On Sat, 2007-12-29 at 18:39 -0500, Charles Willis wrote: Hello, I am trying to run the

Re: [R] Subsetting data frame problem....

Or use complete.cases df.complete - df[complete.cases(df),] Simon. On Wed, 2008-01-02 at 13:21 +1000, Ross Darnell wrote: You could try complete.case.df - na.omit(df) Ross Darnell -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Marko

[R] How to select a reasonable shrinkage coefficient in stepplr?

Dear R-users, I am using stepplr for L2 regularized logistic regression. Since number of attribute is too large i discarded interaction terms. Everything is fine but only problem i have faced that i cannot choose a good shrinkage coefficient (lambda). If CV is the best way to estimate, can you

[R] USA map with all states

Hi R Gurus! There was a function in S called usa() which would plot the US. I found map('usa') in R for the lower 48 states. Is there a way to include Alaska and Hawaii as well, please? Thanks, Edna Bell __ R-help@r-project.org mailing list

[R] Find missing days

Hi, I have a data.frame like this: y - rnorm(60) lev - gl(3,20, labels=paste(lev, 1:3, sep=)) date1 - as.Date(seq(ISOdate(2007,9,1), ISOdate(2007,11,5), by=60*60*24)) date1 - date1[-c(3,4,15,34,38,40)] df - data.frame(lev=lev, date1=date1, y=y) I would like to produce a new data.frame with

Re: [R] Find missing days

Try this. It creates a sequence of dates from the range of df$date1 and then does a setdiff between that and the original dates. The result is numeric so we create a Date structure out of it. structure(setdiff(do.call(seq, as.list(range(df$date1))), df$date1), class = Date) On Jan 2, 2008