similar to: PLS component selection for GPLS question

Hello, I am using the gpls package for modelling vegetation classes. My problem is that I now want to know which input variables are significant for the modelling of the classes to recalculate the equation again with just the selected variables. I think I can analyse the significance of the variables via their weights. I used the "gpls1a" term for two group classification. Here my

Hello, I have the following function that receives a "function pointer" formal parameter name "fnc": loocv <- function(data, fnc) { n <- length(data.x) score <- 0 for (i in 1:n) { x_i <- data.x[-i] y_i <- data.y[-i] yhat <- fnc(x=x_i,y=y_i) score <- score + (y_i - yhat)^2 } score <- score/n

Hy, I got the following problem when trying to build a rpart model and using everything but LOOCV. Originally, I wanted to used k-fold partitioning, but every partitioning except LOOCV throws the following warning: ---- Warning message: In nominalTrainWorkflow(dat = trainData, info = trainInfo, method = method, : There were missing values in resampled performance measures. ----- Below are some

I am trying to write a wrapper for the last example in help(cv.glm) that deals with leave-one-out-cross-validation (LOOCV) for a logistic model. This wrapper will be used as part of a bigger program. Here is my wrapper funtion : logistic.LOOCV.err <- function( formu=NULL, data=NULL ){ cost.fn <- function(cl, pred) mean( abs(cl-pred) > 0.5 ) glmfit <- glm(

Dear all, not really a R question but: If I want to check for the classification accuracy of a LDA with previous PCA for dimensionality reduction by means of the LOOCV method: Is it ok to do the PCA on the WHOLE dataset ONCE and then run the LDA with the CV option set to TRUE (runs LOOCV) -- OR-- do I need - to compute for each 'test-bag' (the n-1 observations) a PCA

Good afternoon. I would like to know if there is any function in R to do LOOCV with these classifiers: 1)SVM 2)Neural Networks 3)C4.5 ( J48) 4)KNN Thanks a lot! [[alternative HTML version deleted]]

Can someone please help with the error message below? thanks! Start: AIC=-Inf value ~ 1 + Core_CPI__ + GDP_change + Unemployment + housing + interest + S_P + d1 + d2 + d3 Error in if (any(ch)) { : missing value where TRUE/FALSE needed In addition: Warning message: attempting model selection on an essentially perfect fit is nonsense

Hi, I was trying to do cross-validation using the crossval function (bootstrap package), with the following code: --------------------------------------------------------------------------------------------------------- theta.fit <- function(x,y){ model <- svm(x,y,kernel = "linear") } theta.predict <- function(fit,x){ prediction <- predict(fit,x)

stimpak wrote: > idont forget to run it with a -opengl flag Thank you so very much!!!! That let me play warcraft 3 on my laptop with linux and Intel 945gm graphik card on ubuntu 8.04, quite well! Thank you! I searched a while, but can't find anything, that helps, now only the -opengl flag was missing.. [Rolling Eyes] great. Maybe that should be added in the APPDB warcraft 3 entry...

Ran a bunch of variables in R and the final result of StepAIC is as below: Why are the first 5 variables kept in the stepwise result?? Are the last 4 variables finally chosen after Stepwise? Thanks Coefficients: Estimate Std. Error t value Pr(>|t|) (Intercept) 1.315e-01 2.687e-01 0.490 0.63611 Core_CPI__ 1.290e-02 7.496e-03 1.721 0.11927 GDP_change -3.482e-03 2.075e-03 -1.678 0.12767

I have data set up like the following: control1 <- sample(1:75, 3947398, replace=TRUE) control2 <- sample(1:75, 28793, replace=TRUE) control3 <- sample(1:100, 392733, replace=TRUE) control4 <- sample(1:75, 858383, replace=TRUE) patient1 <- sample(1:100, 28048, replace=TRUE) patient2 <- sample(1:50, 80400, replace=TRUE) patient3 <- sample(1:100, 48239, replace=TRUE) control

New major versions of the caret packages (caret 3.37, caretLSF 1.23 and caretNWS 0.23) have been uploaded to CRAN. caret is a package for building and evaluating a wide variety of predictive models. There are functions for pre-processing, tuning models using resampling, visualizing the results, calculating performance and estimating variable importance. caretNWS and caretLSF are two parallel

New major versions of the caret packages (caret 3.37, caretLSF 1.23 and caretNWS 0.23) have been uploaded to CRAN. caret is a package for building and evaluating a wide variety of predictive models. There are functions for pre-processing, tuning models using resampling, visualizing the results, calculating performance and estimating variable importance. caretNWS and caretLSF are two parallel

Check out the gpls package on CRAN. HTH, Andy > From: Min-Han Tan > > Good morning, > > Thank you all for your help so far. I really appreciate it. > > The crux of my problem is that I am generating a generalized linear > model with 1 dependent variable, approximately 50 training samples and > 100 parameters (gene levels). > > Essentially, if I have 100

You need to do some extra work if you want to do classification with a regression method. One simple way to do classification with PLS is to code the classes as 0s and 1s (assuming there are only two classes) or -1s and 1s, fit the model, then threshold the prediction; e.g., those with predicted values < 0.5 (in the 0/1 coding) get labeled as 0s. There's a predict() method for mvr

Greetings! The Bioconductor core group would like to announce the 5th release of Bioconductor, version 1.4. There are many new packages as well as several major upgrades and fixes in older packages, and users are encouraged to upgrade existing tools and check out the new packages. Release 1.4 is intended to be operated with R version 1.9.x, which can be obtained at CRAN

Dear R Users I am maximizing a user defined log likelihood function. It includes variance parameter (sigma). I used R function optim with BFGS maximization method. However, it stops before the solution saying ?sqrt(sigma): NaNs produced? Could anybody know a proper transformation for sigma which can be passed in the function? For the correlation parameter I used Fishers? transformation so it

Hello, How can I do a cross validation in R? Thank You!

Hello all. I have this code: myLOOCV <- function(myformula, data) { Y <- all.vars(myformula)[1] Scores<- numeric(length(data[,1])) for (i in 1:length(data[,1])) { train <- data[-i,] test <- data[i,] myModel <- lrm(myformula, train) Scores[i] <- predict(myModel, test,type="mean") }

Can someone help me with performing leave-out-one cross validation using R (model built is a Cox model)? Thanks. --------------------------------------------- David Verbel, MPH Senior Biostatistician Aureon Biosciences 28 Wells Avenue Yonkers, NY 10701 Phone: (914) 377-4021 Fax: (914) 377-4001 --------------------------------------------- [[alternative HTML version deleted]]