similar to: dfbetas vs dfbeta

Hi there, I have the problem, that I'm not able to reproduce the SPSS residual statistics (dfbeta and cook's distance) with a simple binary logistic regression model obtained in R via the glm-function. I tried the following: fit <- glm(y ~ x1 + x2 + x3, data, family=binomial) cooks.distance(fit) dfbetas(fit) When i compare the returned values with the values that I get in SPSS,

Hello. I want to get the proper influence function for the glm coefficients in R. This is supposed to be inv(information)*(y-yhat)*x. So I am wondering what is the exact mathematical formula for the output that the functions: dfbeta() OR lm.influence()$coefficients return for a glm model. I am confused because: 1. Their columns don't sum to zero as influences should. 2. They

I am using the Unix version of R (version 1.7.0), installed via fink on a G4 Macintosh. I recently upgraded from version 1.6.0 and found that the "car" library now has a problem: ---Begin transcript--- >library(car) Attaching package 'car': The following object(s) are masked from package:base : dfbeta dfbeta.lm dfbetas dfbetas.lm hatvalues hatvalues.lm

Hello I am running a regression without the intercept, and want to compute dfbetas. How do I do this? The dfbetas function only works when the intercept is included in the model. Regards K [[alternative HTML version deleted]]

I've prepared preliminary versions of two packages that I plan eventually to contribute to CRAN: car (for "Companion to Applied Regression") is a package that provides a variety of functions in support of linear and generalized linear models, including regression diagnostics (e.g., studentized residuals, hat-values, Cook's distances, dfbeta, dfbetas, added-variable plots,

I've prepared preliminary versions of two packages that I plan eventually to contribute to CRAN: car (for "Companion to Applied Regression") is a package that provides a variety of functions in support of linear and generalized linear models, including regression diagnostics (e.g., studentized residuals, hat-values, Cook's distances, dfbeta, dfbetas, added-variable plots,

I've prepared preliminary versions of two packages that I plan eventually to contribute to CRAN: car (for "Companion to Applied Regression") is a package that provides a variety of functions in support of linear and generalized linear models, including regression diagnostics (e.g., studentized residuals, hat-values, Cook's distances, dfbeta, dfbetas, added-variable plots,

Greetings to r-help land. I've run into some program crashes and I've traced them back to methods() behavior after the package gdata is loaded. I provide now a minimal re-producible example. This seems bugish to me. How about you? dat <- data.frame(x = rnorm(100), y = rnorm(100)) lm1 <- lm(y ~ x, data = dat) methods(class = "lm") ## OK so far library(gdata)

Hi Everyone, I recently have started using R again on a Linux box after spending several years on a Mac. Last I checked, the best way to use R was through EMACS using something like ESS. I remember that being serviceable but not always the most convenient. Is there anything comparable to the mac version of R with its built in console, editor, etc?? thanks! -- View this message in context:

influence.measures gives several measures of influence for each observation (Cook's Distance, etc) and actually flags observations that it determines are influential by any of the measures. Looks good! But how does it discriminate between the influential and non- influential observations by each of the measures? Like does it do a Bonferroni-corrected t on the residuals identified by

Hi, I am using coxph with weights to represent sampling fraction of subjects. Our simulation results show that the robust SE of beta systematically under-estimate the empirical SD of beta. Does anyone know how the robust SE are estimated in coxph using weights? Is there any analytical formula for the “weighted” robust SE? Any help is appreciated! Thanks so much in advance Willy

I have sort of an emergency question for the list. One of my professors for an S-Plus intensive class distributed a function to produce partial regression plots. I need to run it under R, because I'm doing the homework on my home computer with a modem; hence I don't have the speed required to emulate X-Windows and run S Plus off one of the campus servers. Bottom line: I'm using R.

I had a look at some influence measures, and it seems to me that currently several methods handle multiple lm (mlm) objects wrongly in R. In some cases there are separate "mlm" methods, but usually "mlm" objects are handled by the same methods as univariate "lm" methods, and in some cases this fails. There are two general patterns of problems in influence measures:

Hi there I have created a multivariate logistic regression model looking at the presence/absence of disease on farms. I would like to plot the diagnostic plots recommended by Hosmer & Lemeshow to look particularly for any points of high influence. In order to do this I need to extract values for delta-beta. The function dfbeta gives a value for change in each coefficient but I am looking

hello all I am using the R package Zelig for some tobit regression with robust standard errors. I have got R version 2.9.2 (2009-08-24) and Zelig Version: 3.4-5 when i do demo(robust) It ends like this way data(coalition) > # Fit the model with robust standard error > user.prompt() Press <return> to continue: > z.out3 <- zelig(Surv(duration, ciep12) ~ polar + numst2 +

I'm trying to write some functions extending influence measures to multivariate linear models and also allow subsets of size m>=1 to be considered for deletion diagnostics. I'd like these to work roughly parallel to those functions for the univariate lm where only single case deletion (m=1) diagnostics are considered. Corresponding to stats::hatvalues.lm, the S3 method for class

Dear R experts: I just tried some simple test that told me that hand computing the OLS coefficients is about 3-10 times as fast as using the built-in lm() function. (code included below.) Most of the time, I do not care, because I like the convenience, and I presume some of the time goes into saving a lot of stuff that I may or may not need. But when I do want to learn the properties of an

Hi Folks, Hopefully this question has enough R and not too much stats to be appropriate for this list. Based on,* Hosmer et al. 2013. Logistic regression for matched case-control studies. Applied Logistic Regression *(eqtn. 7.8)*, *I am assessing GOF of conditional (or matched) logistic regression models with the *standardized Pearson residuals*. The authors define ?large? as delta chi-squared

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 =

Hi, I found that using different contrasts (e.g. contr.helmert vs. contr.treatment) will generate different fitted probabilities from multinomial logistic regression using multinom(); while the fitted probabilities from binary logistic regression seem to be the same. Why is that? and for multinomial logisitc regression, what contrast should be used? I guess it's helmert? here is an example