[R] ROCR - confidence interval for Sens and Spec

Dear List,   I am new to ROC analysis and the package ROCR. I want to compute the confidence intervals of sensitivity and specificity for a given cutoff value. I have used the following to calculate sensitivity and specificity:   data(ROCR.simple) pred <- prediction(ROCR.simple$predictions, ROCR.

[R] xyplot

Hi   I am using following code to produce a xyplot for some longitudinal data. There are 2 panels. It produced all longitudinal trajectories with mean profile. But since the dataset it very large plot looks very messy. I want to show, say 10 randomly selected individual longitudinal trajectories

[R] ROCR for combination of markers

Dear list   I have 5 markers that can be used to detect an infection in combination. Could you please advise me how to use functions in ROCR/ other package to produce the ROC curve for a combination of markers?   I have used the following to get ROC statistics for each marker. pred <- prediction(

Re: [R] ROCR for combination of markers

Subject: Re: [R] ROCR for combination of markers To: "Rasanga Ruwanthi" Cc: r-help@r-project.org Date: Thursday, 28 April, 2011, 13:11 ... and additionally, 'ROC' from the Epi package does the second step all in one. Am 28.04.2011 13:01, schrieb Eik Vettorazzi: > Hi Ra

Re: [R] ROCR for combination of markers

Thanks Eik. As you said both packages give the same result, except labelling of the x axis. --- On Thu, 28/4/11, Eik Vettorazzi wrote: From: Eik Vettorazzi Subject: Re: [R] ROCR for combination of markers To: "Rasanga Ruwanthi" Cc: "R Help" Date: Thursday, 28 Apr

[R] Longitudinal categorical response data

Dear List,   I have some longitudinal data, each patient was followed at times 0, 12, 16, 24 weeks and measure severity of a illness (0-worse, 1-same, 2-better). So, longitudinal response is categorical.  I was wondering whether lmer in R can fit a model for this type of data. If so, how we code

[R] coxme - bug / error

Hello everyone, Many thanks to Terry Therneau for giving me a solution for my previous problem re coxme function. Now, I am using a bigger dataset to fit the same model; random treatment effect nested within centre. I used the command coxme(Surv(time, status) ~ factor(treat), data=data1, r

[R] Help load a package into R

Dear R List, I want to download kinship_1.2_S.tar.gz in http://mayoresearch.mayo.edu/mayo/research/biostat/splusfunctions.cfm to R. Once save this file to C:\, how I could load into R? I am working in Windows XP. Usually what I do is, I go to "packages" and then "install packages from local zip

Re: [R] Help load a package into R

t;[EMAIL PROTECTED]> To: Rasanga Ruwanthi <[EMAIL PROTECTED]> Cc: r-help@r-project.org Sent: Friday, April 11, 2008 10:46:14 AM Subject: Re: [R] Help load a package into R Rasanga Ruwanthi wrote: > Dear R List, > > I want to download kinship_1.2_S.tar.gz in > http:/

[R] 95% CI for difference in median survival time

Dear R users,   I want to compute the 95% CI for difference in median survival times of two treatment groups. survfit function in R gives median and the corresponding CIs for each group. Could you please help me to get a CI for the difference in median times?   Thanks Ruwanthi

[R] coxme - fitting random treatment effect nested within centre

Dear all, I am using "coxme" function in Kinship library to fit random treatment effect nested within centre. I got 3 treatments (0,1,2) and 3 centres. I used following commands, but got an error. > ugroup=paste(rep(1:3,each=3),rep(0:2,3),sep='/') > mat1=bdsmatrix(rep(c(1,1,1,1,1,1,1,1,1),3),b