similar to: generalized linear model (glm) and "stepAIC"

Problem: I am sorting through model selection process for first time and want to make sure that I have used glm, stepAIC, and update correctly. Something is strange because I get a different result between: 1) a glm of 12 predictor variables followed by a stepAIC where all interactions are considered and then an update to remove one specific interaction. vs. 2) entering all the terms

This is a question at the border between stats and r. When I do a glm with many potential effects, and select a model using stepAIC, many independent variables are selected even if there are no relationship between dependent variable and the effects (all are random numbers). Do someone has a solution to prevent this effect ? Is it related to Bonferoni correction ? Is there is a ratio of

I would like test AICc as a criteria for model selection for a glm using stepAIC() from MASS package. Based on various information available in WEB, stepAIC() use extractAIC() to get the criteria used for model selection. I have created a new extractAIC() function (and extractAIC.glm() and extractAIC.lm() ones) that use a new parameter criteria that can be AIC, BIC or AICc. It works as

Based on the stepAIC help, I have assumed that it only was for lm, aov, and glm models. I gather from the following correspondence that it also works with lme models. Thomas Lumley 07:40 a.m. 28/04/03 -0700 4 Re: [R] stepAIC/lme problem (1.7.0 only) Prof Brian Ripley 04:19 p.m. 28/04/03 +0100 6 Re: [R] stepAIC/lme problem (1.7.0 only) Prof Brian Ripley 06:09 p.m. 29/04/03 +0100 6 Re: [R]

Hello, I'm trying to figure out how to run the stepAIC function starting with the NULL model. I can call the null model (e.g., lm(y ~ NULL)), but using this object in stepAIC doesn't seem to work. The objective is to calculate AICc. This can be done if stepAIC can be run starting with the NULL model; the (2p(p-1)/(n-p-1))to get AICc would be added to the final step AIC value. Can

Hi, First of all, thanks for the great work on R in general, and MASS in particular. It's been a life saver for me many times. However, I think I've discovered a bug. It seems that, when I use weights during an initial least-squares regression fit, and later try to add terms using stepAIC(), it uses the weights when looking to remove terms, but not when looking to add them:

Hi - I use stepAIC to automatically select the model. The stepAIC was applied on polr as follow:objPolr <- polr(formula=myformula, data=dat, method=METHOD);objPolr.step <- stepAIC(objPolr, trace=T);Then R complaints that it doesn't know about 'dat' when it executes the second line. Below is the exact error that I got when executing the stepAIC line above:Error in eval(expr,

Hi, I am experiencing a baffling behaviour of stepAIC(), and I hope to get any advice/help on this. Greatly appreciate any kind advice given. I am using stepAIC() to, say, select a model via stepwise selection method. R Version : 1.7.1 Windows ME Many thanks! ***Issue : When stepAIC() is placed within a function, it seems that stepAIC() cannot detect the data matrix, and the program is

I have a question about stepAIC and extractAIC and why they can produce different answers. Here's a stepAIC result (slightly edited - I removed the warning about noninteger #successes): stepAIC(glm(formula = (Morbid_70_79/Present_70_79) ~ 1 + Cohort + Cohort2, family = binomial, data = ghs_70_79, subset = ghs_70_full),direction = c("backward")) Start: AIC=3151.41

Hello, I am using the function stepAIC (library MASS) to run a backward elimination on my linear regression. The new model stepAIC calculates contains coefficients that have a Pr(>|t|) value below 0.1, but I'd like to have only coefficients with 0.001 or below. How can I change the stop criterion for stepAIC, so that it is more strict? There is a parameter "steps", but it is

Hi List, Being new to R, I am trying to apply boot.stepAIC() for Model selection by bootstrapping the stepAIC() procedure. I had gone through the discussion in various thread on the variable selection methods. Understood the pros and cons of various method, also going through the regression modelling strategies in rms. I want to read Final model or Formula or list of variables automatically

dear R users, I have fit the lm() on a mtrix of responses. i.e M1 = lm(cbind(R1,R2)~ X+Y+0). When i use summary(M1), it shows details for R1 and R2 separately. Now i want to use stepAIC on these models. But when i use stepAIC(M1) an error message comes saying that dropterm.mlm is not implemented. What is the way out to use stepAIC in such cases. regards,

I can use stepAIC on an lme object in 1.6.2, but I get the following error if I try to do the same in 1.7.0: Error in lme(fixed = resp ~ cov1 + cov2, data = a, random = structure(list( : unused argument(s) (formula ...) Does anybody know why? Here's an example: library(nlme) library(MASS) a <- data.frame( resp=rnorm(250), cov1=rnorm(250), cov2=rnorm(250),

Hi, i'm trying to apply StepAIC with coxph...but i have the same error: stepAIC(fitBMT) Start: AIC=327.77 Surv(TEMPO,morto==1) ˜ VOD + SESSO + ETA + ........ Error in dropterm.default(fit,scope$drop, scale=scale,trace=max(0, : number of rows in use has changed: remove missing values? anybody know this error?? Thanks. Michele [[alternative HTML version deleted]]

Dear All, I am trying to use stepAIC for an lmer object but it doesn't work. Here is an example: x1 <- gl(4,100) x2 <- gl(2,200) time <- rep(1:4,100) ID <- rep(1:100, each=4) Y <- runif(400) <=.5 levels(Y) <- c(1,0) dfr <- as.data.frame(cbind(ID,Y,time,x1,x2)) fm0.lmer <- lmer(Y ~ time+x1+x2 + (1|ID), data = dfr, family = binomial)

I'm attempting to use stepAIC to select a model through a forward procedure. I want to consider up to all 3-way interactions. I've attempted to use the following code: m2.Fwd3way <- stepAIC(m1.Ionly, direction="forward", scope=list(upper=~(var1 + var2 + var3 + var4)^3, lower=~1)) When I submit this the trace indicates that only 2-way

Hello, My question concerns model selection, stepAIC(), add1(), and coxph(). In Venables and Ripley (3rd Ed) pp389-390 there is an example of using stepAIC() for the automated selection of a coxph model for VA lung cancer data. A statistics question: Can partial likelihoods be interpreted in the same manner as likelihoods with respect to information based criterion and likelihood ratio tests?

Hello R-Users,   I have one binary dependent variable and a set of independent variables (glm(formula,…,family=”binomial”) ) and I am using the function stepAIC (“MASS”) for choosing an optimal model. However I am not sure if stepAIC considers significance properties like Likelihood ratio test and Wald test (see example below).     > y <- rbinom(30,1,0.4) > x1 <- rnorm(30) > x2

Hi, I am experiencing a baffling behaviour of stepAIC(), and I hope to get any advice/help on what went wrong or I'd missed. I greatly appreciate any advice given. I am using stepAIC() to, say, select a model via stepwise selection method. R Version : 1.7.1 Windows ME Many thanks and best regards, Siew-Leng ***Issue : When stepAIC() is placed within a function, it seems

Hi, stepAIC generic plot function creates useful graphics for the diagnosis of multiple regressions. To create predicted versus observed plots, I use to look for the coefficients, copy them by hand, calculate R?, then plot. Is there a more automated way to plot predicted versus observed with its associated R? output using stepAIC, or another function? Kind regards, S.-?. Parent Universit?