similar to: net classification improvement?

Hi, I am trying to calculate net reclassification improvement (NRI) and Inegrated Discrimination Improvement (IDI) for a survival dataset to compare 2 risk models. It seems that the improveProb() in Hmisc package does this only for binary outcome, while rcorrp.cens() does take survival object, but doesn't output NRI or IDI. Can anyone suggest any other packages that can calculate NRI and IDI

Dear all I am trying to compare the performances of several methods using the AUC0.1 and not the whole AUC. (meaning I wanted to compare to AUC's whose x axis only goes to 0.1 not 1) I came to know about the Mcneil Hanley test from Bernardo Rangel Tura and I referred to the original paper for the calculation of "r" which is an argument of the function cROC. I can only find the

Hi, I would like to compare differences in AUC from 2 different models, glm and gam for predicting presence / absence. I know that in theory the model with a higher AUC is better, but what I am interested in is if statistically the increase in AUC from the glm model to the gam model is significant. I also read quite extensive discussions on the list about ROC and AUC but I still didn't find

Dear Sirs. I am working with the R packages Hmisc and PredictABEL to make NRI estimates from my Cox models with and without a specific biomarker. According to Pencina et al (Statistics in Medicine 2010, DOI: 0.1002/sim.4085 ), a continuous/non-categorical NRI (NRI>0) is to be used when there are no obvious reason to categorize risk, such as the risk of future cardiovascular events in patients

Hello Thanks to Frank Harrell for the great Design package. I noted from Pencina's Article (Statistics in Medicine Vol 27, pp157-172) that the result obtained for the Net Reclassification Index depends upon categorical cut-offs for risk (eg in the paper <6%, 6-20% and >20%). I wondered how the improveprob function arrives at its cut-offs, and whether there was any function to change the

Dear list, I am trying to work out how the improveProb() function works and how to interpret the results, and I have a few questions. I would be grateful if anyone could shed some light on these. in the Net Reclassification Improvement section of the output, is the 2P column the two-sided p-value for the differences in classification? So if a limit is set at 0.05, then lower values indicate

Dear all, I am interested to evaluate reclassification using net reclassification improvement and Integrated Discrimination Index IDI after survival analysis (Cox proportional hazards using stcox). I search a R package or a R code that specifically addresses the categorical NRI for time-to-event data in the presence of censored observation and, if possible, at different follow-up time points. I

As describe in the Hmisc package's improveProb function, that function is for binary Y. And it's best to use category-free methods. Frank Petergodsk wrote > Hi > > I'm new to R. > > Is it possible to use the improveProb function to generate categorybased > NRI using a Cox model? > I believe I saw someone mentioning the possibility, but I can't find the

So I recognize that: 1. many people hate forward stepwise regression (i've read the archives)--but I need it 2. step() or stepAIC are two ways to get a stepwise regression in R But here's the thing: I can't seem to figure out how to specify that I want the criteria to be Mallow's Cp (and then to subsequently tell me what the Cp stat is). I know it has something to do with

I have been using the mlogit package but can't seem to figure out how to make constraints on the beta coefficients. For example, I would like to force that two of my beta's are equal to each other. Thanks in advance. Jonah

Dear all I have used the lda and predict functions to classify a set of objects of unknown origin. I would like to use a jackknife reclassification to assess the degree to which the outcomes deviate from that expected by chance. However, I can't find any function that allows me to do this. Any suggestions of how to generate the jackknife reclassification to assess classification accuracy?

Hi, Does anyone know if the D'agostino test is available with R ? Alex

Dear all, here is a example of my problem: /#data# g<-c(1,1,1,2,2,2) A<-runif(6,min=1,max=5) B<-runif(6,min=100,max=1000) C<-runif(6,min=30,max=31) D<-runif(6,min=67,max=98765) var<-cbind(A,B,C,D) label<-colnames(var) store<-data.frame(matrix(ncol=2)) colnames(store)=c("usedVar","prediction") library(MASS)#get lda for (i in c(1:4)) { for (k in

I have a question about the D'Agostino skewness test and the Anscombe-Glynn kurtosis test. agostino.test(x, alternative = c("two.sided", "less", "greater")) anscombe.test(x, alternative = c("two.sided", "less", "greater")) The option "alternative" in those two functions seems to be the null hypothesis. In the output, the

Hola Carlos. Muchas gracias. No es exactamente lo que estoy buscando (sería genial ver que alguien tiene un paquete con la prueba de Nam-D'Agostino) pero puedo aprovechar algo de código. Encontré alguna referencia al test de Gronnesby&Borgan en el paquete stcoxgof de Stata, pero estoy torpe para encontrar algo hecho en R (y me extraña que no haya nada) Un saludo, Miguel. De: Carlos

Hi! I replace some elements of a matrix a > a [,1] [,2] [,3] [1,] 1 2 3 [2,] 4 5 6 [3,] 7 8 9 [4,] 10 11 12 according to a reclassification matrix such > pares [,1] [,2] [1,] 1 2 [2,] 5 6 [3,] 8 7 to get > b [,1] [,2] [,3] [1,] 1 2 3 [2,] 4 5 6 [3,] 7 8 9 [4,] 10 11 12 As both a and

Hola. Una duda.... Alguien sabe si hay algo hecho en R para comprobar si un modelo de supervivencia está bien calibrado? (usando las pruebas de Nam-D'Agostino o de Gronnesby & Borgan). Thnks. Un Saludo, _____________________________ Miguel Ángel Rodríguez Muíños Dirección Xeral de Innovación e Xestión da Saúde Pública Consellería de Sanidade Xunta de Galicia http://dxsp.sergas.es

Dear All, I am using a specific approach for my master thesis. In essence, a supervised reclassification is used as an intermediate step to find chemical parameters which are able to reclassify defined groups. These variables will be used in a next step where location and scale estimators of the groups are important. Traditionally linear discriminant analysis is used for reclassification which

hi. I know this is a big topic on the list, please forgive me. rsync -avv --include "/film/jonah/**/sourceimages/*.tif" --exclude "*" /film /tmp i'm trying to copy all *.tif 's that are in a */sourceimages/ directory and that are only under /film/jonah. i would like to copy the directory tree and tif files to /tmp i was able to copy ever tif with: rsync -a

Hello, I'd appreciate any ideas on how to compare the skewness of two samples. In my case, one sample is likely to be roughly normal and the other one skewed. I could run two D'Agostino tests, but then I'll have to correct for the family-wise error. What if both samples are skewed? If there are no general tests (or they can't exist), I'd like to know. Thanks, Skirmantas