similar to: Pearson residuals (PR#1123)

R version 1.3.0 OS: SunOS 5.7, but I think the same problem occurs with Windows An incorrect formula seems to be used to calculate the pearson residuals for a generalized linear model with a binomial response. Here is a simple program which gives (a) the pearson residuals calculated directly, (b) the pearson residuals from glm, and (c) the deviance residuals from glm. The first and last

Hi all, This is a very silly question or something escapes me: Let obj a simple gam poisson model. Let >obj<-gam(....,family=poisson) >obj1<-update(obj, family=quasi(link="log", var="mu")) >From summary.glm(obj1) the dispersion parameter is estimated 1.165; In fact it is: > (predict(obj1, se.fit=T)$se.fit[1:5]/predict(obj, se.fit=T)$se.fit[1:5])^2 4

Dear Sirs What is the best aproximation to the standardized normal distribution: necessidade = c("sem necessidade","com necessidade") tipo =c("CE-1", "CE-2", "CE-3") dados=c(20,34,44,69,9,3) Tabela =cbind(expand.grid(list(Necessidade=necessidade, Tipo=tipo)), count=dados) Tabela.array=tapply(Tabela$count, Tabela[,1:2], sum) ni =

Greetings, I have been using lm to perform weighted linear regressions and resid to extract the residuals. I happened upon some class notes on the internet that described how one can specify type="pearson" in resid to extract the weighted residuals. Where is this option documented? And if you know that, what is the best way to find such documentation if you don't know that the

Is there any reason that rstandard.glm doesn't have a "pearson" option? And if not, can it be added? Background: I'm currently teaching an undergrad/grad-service course from Agresti's "Introduction to Categorical Data Analysis (2nd edn)" and deviance residuals are not used in the text. For now I'll just provide the students with a simple function to use, but I

Hi Peter and others, If it helps, I wrote a small function glm.scoretest() for the statmod package on CRAN to compute score tests from glm fits. The score test for adding a covariate, or any set of covariates, can be extracted very neatly from the standard glm output, although you probably already know that. Regards Gordon --------------------------------------------- Professor Gordon K

Hi, is there a possibility to calculate the different "types" of residuals directly using the multinom function from MASS as it is possible for the functions gam, glm using type="deviance" or "working" or "pearson" or "response"? I tried it but got always the "response" type, I guess. thanx Matthias

Full_Name: Bin Nan Version: 1.3.0 OS: Win32 Submission from: (NULL) (141.211.15.110) The function resid(fit, "pearson") seems not giving the same Pearson's residuals for logistic regression as what Splus does. I found the problem when I fitted glm with family = binomial using Crowder's seed data.

Dear all, I am running a logistic regression and this is the output: glm(formula = educationUniv ~ brncntr, family = binomial) Deviance Residuals: Min 1Q Median 3Q Max # ???? ????? ?? ???????? -0.8825 -0.7684 -0.7684 1.5044 1.6516 Coefficients: Estimate Std. Error z value Pr(>|z|) (Intercept) -1.06869 0.01155 -92.487 <2e-16 *** brncntrNo

Hi to all I would to determinate whether bits is a binary code and I would to find out the which bit is set to 1 bits <-"00110110" I found to detect whether there are only numbers all.digits(bits) but is there any function to detect whether there are only 0 and 1 in the string And how could I get the f.e the third "bit" from the right hand side With regards Carmen

Hi to all I did not found the right hints for functions with the dot-dot-dot argument. Is it possible to write own functions with the tree dots and if yes what's wrong with the following example? test <- function(x, ...) { print (x) if (exists("y"))print(y) if (exists("z"))print(z) } test(4,y=2) With regards Carmen

Hi to all, I found in the R-help archive how to calculate the p-value for a gee result: http://finzi.psych.upenn.edu/R/Rhelp02a/archive/74150.html but there are two questions (I am afraid they are basic questions ...) 1. why is the result multiplicated with 2 2. how could I decide between lower.tail =TRUE and FALSE: example:

Hi to all, I have some problems to get the times-scale to the x-axis the times are coming from an excel sheet f. e [1] "0:01:00" "0:02:00" "0:03:00" "0:04:00" "0:05:00" "0:06:00" "0:07:00" [8] "0:08:00" "0:09:00" "0:10:00" "0:11:00" "0:12:00" "0:13:00"

what is the cleanest way to do something for every request of a particular type (Verb, and Content-Type header)? i''m trying to figure out if shipping a custom camping.rb is avoidable, and if, how i should structure a patch my app http://whats-your.name/yard/ uses exclusively JSON based messaging between server and client. this means POST bodies are JSON, and not querystring.. camping

My application runs a backgrond process and after running for a while I get this error in my logs: #<Errno::EMFILE: Too many open files Lasty, the ONLY code I have that does anything with files is: File.open(image_path, "wb") do |file| file.puts file_content end Any idea what this means? -- Posted via http://www.ruby-forum.com/.

i was wondering how a blog db has grown by about 15 mb in a week or two. it turns out its the sessions table.. so ive tried this: class ApplicationController.. session :off end class AccountController session :only, :login end and now, its impossible to login, and nothing ever appears in the session table. is this the right approach? i dont want to weed out the sessions with cron, i just

In running the following example of a loglinear model for the Titanic data, I was surprised to see NaN reported for the Pearson chisq > loglin(Titanic, margin=list(1:3, 4)) 2 iterations: deviation 2.273737e-13 $lrt [1] 671.9622 $pearson [1] NaN $df [1] 15 $margin $margin[[1]] [1] "Class" "Sex" "Age" $margin[[2]] [1] "Survived" Tracing it back,

Can anyone show me how to add a log Pearson type III plot using the evdistq() command to an extreme value plot using the lmom package? Attached sample code below... Thanks in advance, Dave library(lmom) # annual maximum daily streamflows Mackenzie River mackenzieRiver = c(26600, 30300, 34000, 32000, 29200, 28300, 28600, 26400, 28300, 28800, 29000, 22100, 32900, 31800, 21600, 32100, 27000,

Thank you for your reply. I am aware of the good reasons not to use the deviance estimate in binomial, Poisson, and gamma families. However, for the inverse Gaussian, the choice seems to me less clear cut. So I just wanted to compare two different options. I have used the dispersion parameter to compute the standardized deviance residuals: summary(model.gamma)$deviance.resid

I have used the correlation analysis (pearson) in the agricolae package to analyse my data and got unexpectedly low p-values (therefore making many more highly significant correlations in my data than I had expected). I am wondering if the p-values given should be subtracted from 1 to give the real p-value, because for each variable compared against itself has a p-value of 1 and I thought it