similar to: GLM: Classification problem. Help!

[This email is either empty or too large to be displayed at this time]

If my aim is to select a good subset of parameters for my final logit model built using glm(). What is the best way to cross-validate the results so that they are reliable? Let's say that I have a large dataset of 1000's of observations. I split this data into two groups, one that I use for training and another for validation. First I use the training set to build a model, and the the

Posted about this earlier. Didn't receive any response But, some further research leads me to believe that MAYBE a GLMM or a GEE function will do what I need. Hello, I have a bit of a tricky puzzle with trying to implement a logit model as described in a paper. The particular paper is on horseracing and they explain a model that is a logit trained "per race", yet somehow the

Hello, Are there any packages/functions available for testing the assumptions underlying assumptions for a good GLM model? Like linktest in STATA and smilar. If not, could somebody please describe their work process when they check the validity of a logit/probit model? Regards, Jay

Dear R people, I generated a glm logit model using a sample of a bigger set, and now I want to test the model with the bigger set. How can I do this? predict makes predictions only for a number of rows equal to the sample used. The question is, how can I use the coefficients of a glm with other sets than the one used to generate those coefficients? Thank you in advance. -- View this message in

Hello all, I've come across an online posting http://www.biostat.wustl.edu/archives/html/s-news/2001-10/msg00119.html that described how to get confidence intervals for predicted values from predict.glm. These instructions were meant for S-Plus. Yet, it generally seems to work with R too, but I am encountering some problems. I am explaining my procedure in the following and would be most

Dear R-list. I have done a logistic glm using Age as explanatory variable for some allergic event. #the model model2d<-glm(formula=AEorSAEInfecBac~Age,family=binomial("logit"),data=emrisk) #predictions for age 30 and 60 preds<-predict(model2d,data.frame(Age=c(30,60)),se.fit=TRUE) # prediction interval

Hello, I have a bit of a tricky puzzle with trying to implement a logit model as described in a paper. The particular paper is on horseracing and they explain a model that is a logit trained "per race", yet somehow the coefficients are combined across all the training races to come up with a final set of coefficients. My understanding is that they maximize log likelihood across the

Dear List, With regard to the question I previously raised, here is the result I obtained right now, brglm() does help, but there are two situations: 1) Classifiers with extremely high AIC (over 200), no perfect separation, coefficients converge. in this case, using brglm() does help! It stabilize the AIC, and the classification power is better. Code and output: (need to install package:

Dear All, I know this may be a trivial question. In the past I have used glm to make logistic regressions on data. The output creates an object with the results of the logistic regression. This object can then be used to make predictions. Great. I have a different problem. I need to make predictions from a logistic regression taken from a paper. Thus I need to (by hand) enter the reported odds

Hi All, When modeling with glm and family = binomial (link = logit) and response values of 0 and 1, I get the predicted probabilities of assigning to my class one, then I would like to compare it with my vector y which does have the original labels. How should I change the probabilities into values of zero and 1 and then compare it with my vector y to find out about the accuracy of my

Dear R-list. I'm doing af logistic analyses using gml. The model explaines variations in Adverse events infections (0 og 1) using age as explanatory variable. model2d<-glm(formula=AEorSAEInfecBac~Age,family=binomial("logit"),data=emrisk) I want to get predictions with 95% confidence limits for age 30 and age 60. I've been reading the "google" and "search

I am trying to use predict.glm to validate a logistic model. Using predictions <- predict.glm(logit.model, type="response", dataframe="validate") I get the predictions from the original dataframe, not the validation data frame. Am I missing an input to the method or is this what is supposed to happen?

Dear R users, I'm new of the R, I really don't know much. I want classification some data (two class, many features and huge size of data) by using R. At this case, I want using Support Vector Machine, Bayes theory based classifier, Discriminant Analysis, Regression based at least. Which package should I using, and can I compare each classifier result by predictions? Thank you.

Hi! I was trying to implement a probit model on a dichotomous outcome variable and found that the predictions were outside the (0,1) interval that one should get. I later tried it with some simulated data with a similar result. Here is a toy program I wrote and I cant figure why I should be getting such odd predictions. x1<-rnorm(1000) x2<-rnorm(1000) x3<-rnorm(1000)

Hi, I'm running gam (mgcv version 1.3-29) and glm (logit) (stats R 2.61) on the same models/data, and I got error messages for the gam() model and warnings for the glm() model. R-help suggested that the glm() warning messages are due to the model perfectly predicting binary output. Perhaps the model overfits the data? I inspected my data and it was not immediately obvious to me (though I

Dear R users, I'm trying to understand how to derive the actual predictions (in terms of class) using predict.glm. Consider this example: mydf=data.frame(A=sample(rnorm(1000), size=1000, replace=T), B=sample(rnorm(5), size=1000, replace=T), C=sample(rnorm(10), size=1000, replace=T), class=sample(c("a", "b"), size=1000, replace=T)) mydf.glm=glm(class ~ .^2, data=mydf,

Hi all, I have a dataset with a response variable with three categories (1, 2, 3) and a lot of continuous variables. I'd like to make a MLR with these variables. I've been watching the libraries nnet and zelig for this purpose but I don't understand them well. I use a training sample data to make the MLR. train.set <- sample(1:1000,1000*0.7) I have done this: library(nnet) net

Hello, I was trying a glm fitting (as shown below) and I got a warning and a fitted residual deviance larger than the null deviance. Is this the expected behavor of glm? I would expect that even though the warning might be warranted I should not get worse fitting with an additional covariate in the model. Could anyone tell me what I'm missing? I get the same results in both R2.5.1 on windows

Hi all, Could anybody tell me what happened to my logistic regression in R? mylog=glm(mytraindata$V1 ~ ., data=mytraindata, family=binomial("logit")) It generated the following error message: Error in model.frame.default(Terms, newdata, na.action = na.action, xlev = object$xlevels) : factor 'state1' has new level(s) AP Thank you!