similar to: glm

I came to R from GLIM and its glm. My data sets (ecological community data) are severely over-dispersed, and so I was delighted to find out that the MASS library has glm.nb which is an advancement from the GLIM macros I had used (N.E.Breslow, Applied Statistics 33, 38--44; 1984). However, I need to use offset, but that failed. I am not (yet --- hopefully) fluent enough in R to be able to

Hi all, In my continuous transition of GLIM to R I try to make a glm with binomial errors. The data file have 3 vectors: h -> the factor that is ajusted (have 3 levels) d -> number of animais alive (the response) n -> total number of animals To test proportion of alive, make d/n. In GLIM: $yvar d$ $error binomial n$ $fit +h$ scale deviance = 25.730 (change = -9.138) at cycle 4

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

I am new to R so may well have missed the point somewhere. I would like to use an exponential error in my generalized linear model. It seems natural to restrict the Gamma family to do this ( and as one might in GLIM) by specifying the scale. This does not seem possible in R . Have I missed something? Sorry to raise such a trivial point but I am keen to specify the scale G.Janacek

Dear Experts, In glim() of S Plus, one of the returned values is "var", the estimated variance matrix of coefficients. However, in glm() of R (there is no glim() in R), "var" is not one of the returned values. Anyone know what could I get the varience matrix of coefficients in glm() in R? As a novice in R and S+, I'd appreciate your help Sincerely, Charlie Liu

Hi all I have another GLIM question. I have been using R as well as Genstat (version 6) in order to fit GLIM models to the data (displayed below). The same models are fitted but the answers supplied by the two packages are not the same. Why? Can anyone help? A discription of the data and the type of model/s fitted can be found below. Regards Allan The

Dear list, I am looking for a way to fix the scale parameter when fitting a generalized linear model with gamma errors and log link. Is there something like "SCALE" such as in GLIM? As always thanks a lot. Peter

I'm writing functions that need to behave differently for GLMs like binomial and Poisson with fixed deviance, and those like normal or gamma or quasi where the deviance is estimated from the data. Given a glm object, is there a simple way to tell this directly, or do I have to look at the name of the family? Duncan Murdoch

I'm confused as to the trustworthiness of the dispersion parameters reported by glm. Any help or advice would be greatly appreciated. Context: I'm interested in using a fitted GLM to make some predictions. Along with the predicted values, I'd also like to have estimates of variance for each of those predictions. For a Gamma-family model, I believe this can be done as Var[y] =

Hi All, could someone shed some light on what the difference between the estimated dispersion parameter that is supplied with the GLM function and the one that the 'gamma.dispersion( )' function in the MASS library gives? And is there consensus for which estimated value to use? It seems that the dispersion parameter that comes with the summary command for a GLM with a Gamma dist. is

In glm() you can use the summary() function to recover the shape parameter (the reciprocal of the dispersion parameter). How do you recover the scale parameter? Also, in the given example, how I estimate and save the geometric mean of the predicted values? For a simple model you can use fitted() or predicted() functions. I will appreciate any help. ? ? ? #Call required R packages require(plyr)?

Hi userRs! I am trying to fit some GLM-poisson and neg.binomial. The neg. Binomial model is to account for over-dispersion. When I fit the poisson model i get: (Dispersion parameter for poisson family taken to be 1) However, if I estimate the dispersion coefficient by means of: sum(residuals(fit,type="pearson")^2)/fit$df.res I obtained 2.4. This is theory means over-dispersion since

Dear R users, Which test is most appropriate in glm when the family is Gamma? In the help page of anova.glm, I found the following ?For models with known dispersion (e.g., binomial and Poisson fits) the chi-squared test is most appropriate, and for those with dispersion estimated by moments (e.g., gaussian, quasibinomial and quasipoisson fits) the F test is most appropriate.? My questions :

Greetings, everybody. Can I ask some glm questions? 1. How do you find out -2*lnL(saturated model)? In the output from glm, I find: Null deviance: which I think is -2[lnL(null) - lnL(saturated)] Residual deviance: -2[lnL(fitted) - lnL(saturated)] The Null model is the one that includes the constant only (plus offset if specified). Right? I can use the Null and Residual deviance to

Hello all, I was wondering if someone can enlighten me as to the difference between the logLik in R vis-a-vis Stata for a GLM model with the gamma family. Stata calculates the loglikelihood of the model as (in R notation) some equivalent function of -1/scale * sum(Y/mu+log(mu)+(scale-1)*log(Y)+log(scale)+scale*lgamma(1/scale)) where scale (or dispersion) = 1, Y = the response variable, and mu

Hi all, How is dispersion calculated within the glm function in R ? Cheers _________________________________________________________________ -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.- r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html Send "info", "help", or "[un]subscribe" (in the "body",

After some futile searches, I decided to ask the list to see if any of the sages out there would have an answer: I have a function I wrote a few years ago in S, which calls glim numerous times. I'd like to port it to R, but glm works differently from glim, which takes as part of its input an X design matrix. I probably could write a function to convert glim to glm, but hope this

Hi all I try to make a weibull survival analysis on R. I know make this on GLIM, and now I try to make the GLIM exercice GLEX8 on R to learning and compare the test. The variables are: time censor group bodymass In GLIM I make: $calc %s=1 $ to fit weibull rather than exponential $input %pcl weibull $ $macro model group*bodymass $endmac$ $use weibull t w %s $ Then, GLIM estimate an alpha for the

Following p.206 of "Statistical Models in S", I wish to change the code for summary.glm() so that it estimates the dispersion for binomial & poisson models when the parameter dispersion is set to zero. The following changes [insertion of ||dispersion==0 at one point; and !is.null(dispersion) at another] will do the trick: "summary.glm" <- function(object, dispersion =

Dear list, This is a question about overdispersion and the ML estimates of the parameters returned by the glm.poisson.disp (L. Scrucca) and glm.nb (Venables and Ripley) functions. Both appear to assume a negative binomial distribution for the response variable. Paul and Banerjee (1998) developed C(alpha) tests for "interaction and main effects, in an unbalanced two-way layout of counts