similar to: drop1() seems to give unexpected results compare to anova()

the data is : >table.8.3<-data.frame(expand.grid( marijuana=factor(c("Yes","No"),levels=c("No","Yes")), cigarette=factor(c("Yes","No"),levels=c("No","Yes")), alcohol=factor(c("Yes","No"),levels=c("No","Yes"))), count=c(911,538,44,456,3,43,2,279))

Hi, I was wondering why anova() and drop1() give different tail probabilities for F tests. I guess overdispersion is calculated differently in the following example, but why? Thanks for any advice, Tom For example: > x<-c(2,3,4,5,6) > y<-c(0,1,0,0,1) > b1<-glm(y~x,binomial) > b2<-glm(y~1,binomial) > drop1(b1,test="F") Single term deletions Model: y ~

I would like to do a SS type III analysis on a proportional odds logistic regression model. I use drop1(), but dropterm() shows the same behaviour. It works as expected for regular main effects models, however when the model includes an interaction effect it seems to have problems with matching the parameters to the predictor terms. An example: library("MASS"); options(contrasts =

A recent question in r-help made me realize that I should add a drop1 method for coxph and survreg. The default does not handle strata() or cluster() properly. However, for coxph the right options for the "test" argument would be likelihood-ratio, score, and Wald; not chisq and F. All of them reference a chi-square distribution. My thought is use these arguments, and add an

Dear List, recently tried to reproduce the results of some custom model selection function after updating R, which unfortunately failed. However, I ultimately found the issue to be that testing with pchisq() in drop1() seems to have changed. In the below example, earlier versions (e.g. R 2.4.1) produce a missing P-value for the variable x, while newer versions (e.g. R 2.7.1) produce 0 (2.2e-16).

By changing three lines in drop1 from access based on $ to access based on standard accessor methods (terms() and residuals()), it becomes *much* easier to extend drop1 to work with other model types. The use of $ rather than accessors in this context seems to be an oversight rather than a design decision, but maybe someone knows better ... In particular, if one makes these changes (which I am

This is probably simple, but I just can't see it... I want to calculate the R^2s for a series of linear models where each term is dropped in turn. I can get the RSS from drop1(), and the r.squared from summary() for a given model, but don't know how to use the result of drop1() to get the r.squared for each model with one term dropped. Working example: library(vcd) # for

Hi, If I used drop1 in a weighted lm fit, it seems to ignore the weights in the AIC calculation of the dropped terms, see the example below. Can this be right? Yan -------------------- library(car) > unweighted.model <- lm(trSex ~ (river+length +depth)^2- length:depth, dno2) > Anova(unweighted.model) Anova Table (Type II tests) Response: trSex Sum Sq Df F value

Hello All, Am having some trouble computing Type III SS in a Cox Regression using either drop1 or Anova from the car package. Am hoping that people will take a look to see if they can tell what's going on. Here is my R code: cox3grp <- subset(survData, Treatment %in% c("DC", "DA", "DO"), c("PTNO", "Treatment", "PFS_CENSORED",

Yes, it's homework . . . delete now if desired . . . but I think it is an interesting problem. Running R 2.11.1, LaTeX on WinXP, via Sweave. A drop1() object from a glm() produces, as part of its output, a string that looks like this: <none> The trouble I run into is that running latex() on a drop1() object from glm() produces a string that looks like this in the generated .tex

Dear R Core Team I've a proposal to improve drop1(). The function should change the contrast from the default ("treatment") to "sum". If you fit a model with an interaction (which ist not signifikant) and you display the main effect with drop1( , scope = .~., test = "F") If you remove the interaction, then everything's okay. There is no way to fit a

Hi all, I've spent quite a lot of time searching through the help lists and reading about how best to run perform a 2-way ANOVA with unbalanced data. I realize this has been covered a great deal so I was trying to avoid adding yet another entry to the long list considering the use of different SS, etc. Unfortunately, I have come to the point where I feel I have to wade in and see if someone

Dear experts, I just noticed that I get different results conducting type III anova using drop1 or the Anova command from the car package. I suppose I made a mistake and hope you can offer me some help. I have no idea where I got wrong and would be very grateful for explaination as R is new terrain for me. If I run the commands in line, they produce the same results. But if I run them in

Dear R Help, I have noticed some inconsistent behaviour of add1 and drop1 with a weighted linear model, which affects the interpretation of the results. I have these data to fit with a linear model, I want to weight them by the relative size of the geographical areas they represent. _________________________________________________________________________________________ > example

I've been experimenting with drop1 for my biostatistics class, to obtain the so-called Type III sums of squares. I am fully aware of the deficiencies of this method, however I feel that the students should be familiar with it. What I find baffling is that when applied to a fully balanced design, you obtain different sums of squares. I've used this for several years in Splus and R and never

My apologies to the list for sending this without adequate research. I have found my answer; please ignore! Thanks. I've been experimenting with drop1 for my biostatistics class, to obtain the so-called Type III sums of squares. I am fully aware of the deficiencies of this method, however I feel that the students should be familiar with it. What I find baffling is that when applied to a fully

I'd like to fit and explore a collection of hierarchical loglinear models that might range from the independence model, ~ 1 + 2 + 3 + 4 to the saturated model, ~ 1 * 2 * 3 * 4 I can use add1 starting with a baseline model or drop1 starting with the saturated model, but I can't see how to get the model formulas or terms in each model as a *list* that I can work with further. Consider

I am using R to teach, and here are a couple of things that I thought would work didn't work. 1. I noticed the utility data(***,package=***) recently and like it very much, but unless I type in the whole word "package" I'll get an error in 1.4.0. For example, data(cats,package=MASS) works fine but data(cats,pac=MASS) doesn't. 2. drop1 doesn't seem to be as smart as

Does anybody knows what this error message means: Error in object$terms : $ operator not defined for this S4 class I have peformed the following steps: > library(lattice) > library(Matrix) > library(lme4) > inkm inkm$Gamie glm.incm drop1(glm.incm,test="Ch") Error in object$terms : $ operator not defined for this S4 class Your suggestin would be of a greatl help to

I've been poking around with GLMs (on which I am *not* an expert) on behalf of a student, particularly binomial (standard logit link) nested models with overdispersion. I have one possible bug to report (but I'm not confident enough to be *sure* it's a bug); one comment on the general inconsistency that seems to afflict the various functions for dealing with overdispersion in GLMs