similar to: glm-poisson fitting 400.000 records

Dear userRs, when applied the summary function to a glm fit (e.g Poisson) the parameter table provides the categorical variables assuming that the first level estimate (in alphabetical order) is 0. What is the standard error for that variable then? Are the standard errors calculated assuming a normal distribution? Many thanks, -- View this message in context:

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

Hi there, I need to do the same thing as cumsum but with the variance and skewness. I have tried to do a loop for like this: var.value <- vector(mode = "numeric", length = length(daily)) for (i in (1:length(daily))) { var.value[i] <- var(daily[1:i]) } But because my dataset is so huge, I run out of memory..... Any ideas?!?! Much appreciate

Good evening. I have this following table and I would like to turn it into a matrix in which my rows would be filled with de "Sellers", my columns with my "Articles" and my data would be the mean unitary price used by each seller in each produt. Seller Art. Unit Price 1 v1 p1 9.148352 2 v2 p1 2.858073 3 v3 p1 3.775315 4 v4

Hola: Soy nuevo en esto de R, llevo toda la mañana perdida con esto, a ver si alguien me puede ayudar, Cuando genero el gráfico con el siguiente archivo: library(gplots) data <- read.table("data.dat",h=T) postscript(file = "join10kb.ps", horizontal = FALSE, onefile = FALSE,family = "Helvetica", width = 5, height = 4) par(mar=c(5.1, 4.1, 0.1, 0.1)) d <-

Dear Adrian Dusa, others, I've recently started to learn R in order to use the QCA package because i think it might offer what other QCA packages don't: possibilities for quite a few conditions and large n. However, can someone tell me approx. how much RAM i need to run QCA on set of +/- 400.000 cases and +/- 15 conditions? (or differently: how much time will it take with RAM of a

Dear List, I'm using glmulti for model averaging in R. There are ~10 variables in my model, making exhaustive screening impractical - I therefore need to use the genetic algorithm (GA) (call: method = "g"). I need to include random effects so I'm using glmulti as a wrapper for lme4. Methods for doing this are available here

Hi all, First of all, I have spent a lot of time reading up on it. Anyway, I live in a shared accomodation with 2 roommates and a landlord and we share a cable internet connection. It is 2Mbit/400Kbit connection. Sometimes when one of us is downloading a song through Kazaa or a new Linux or FreeBSD iso, the bandwidth gets hogged and other users can't get through. I was trying to configure

Hello, I'm using the "glmulti" package to run models of all the possible combinations of my variables. However, I am only interested in a few interactions between my variables. I have tried the equivalent of: mod1<-lm(y~a+b+c+a:b) glmulti(mod1, level=1) mod2<-lm(y~a+b+c+a:b) glmulti(mod2, level=2) and glmulti("y", c("a", "b", "c"),

Dear R, The glmulti package no longer loads through the library() command, apparently because of a problem with rJava. I have today reinstalled R from scratch (updated to v2.14.0) and reinstalled all packages from scratch and updated them all too. The problem is the same as I found on v2.13.2. See session below for the error. I tried install.packages(rJava) as advised by the error report but it

Dear all, I have a question about the glmulti package. I want to include some variables in all models. To that end I applied the wrapper function as shown in the examples (http://www.inside-r.org/packages/cran/glmulti/docs/glmulti). To include the variable "Geslacht" in all models: > glm.redefined = function(formula, data, always="", ...)

Dear All, wonder if you have some thoughts on running the with() function (and perhaps including the pool() function to get the results?) in glmulti? In other words, how to run glmulti with a data set that is produced by mice()? publicly available code: data <- airquality data[4:10,3] <- rep(NA,7) data[1:5,4] <- NA data <- data[-c(5,6)] library(mice) library(glmulti) the following

Dear all, I had a R segmentation fault, and then invoked debug mode and ran step by step. When I reached "terms(Y~X1*X2*...*X16)", I would then have "segmentation" fault. However, if I just ran this under regular "R interactive" mode, it would be fine though taking long time. My questions are: 1. Is there a known limit of terms for a formula? 2. Why does the

Dear all, I had a R segmentation fault, and then invoked debug mode and ran step by step. When I reached "terms(Y~X1*X2*...*X16)", I would then have "segmentation" fault. However, if I just ran this under regular "R interactive" mode, it would be fine though taking long time. My questions are: 1. Is there a known limit of terms for a formula? 2. Why does the

Dear list, I am trying to do an automated model selection of a glmm (function glmer; package: lme4) containing a large number of predictors. As far as i understand, glmulti is able to devide the process into chuncks and proceed by parallel processing on on multiple cores. Unfortunately this does not seem to work and i could not really fid any advice on the matter on other forums. Specifically i

Hello, I'm using the "glmulti" package to run models of all the possible combinations of my variables. However, I am only interested in a few interactions between them. I have tried the equivalent of: 1) mod1<-lm(y~a+b+c+a:b) glmulti(mod1, level=1) 2) mod2<-lm(y~a+b+c+a:b) glmulti(mod2, level=2) 3) glmulti("y", c("a",

All, I am working on a multiple-regression meta-analysis and have too many alternative models to fit by hand. I am using the "metafor" package in R, which generates AIC scores among other metrics. I'm using a simple formula to define these models. For example, rma(Effect_size,variance, mods=~Myco_type + N.type +total, method="ML")->mod where Effect_size is the

Dear List, I am using both the clm() and clmm() functions from the R package 'ordinal'. I am fitting an ordinal dependent variable with 5 categories to 9 continuous predictors, all of which have been normalised (mean subtracted then divided by standard deviation), using a probit link function. From this global model I am generating a confidence set of 200 models using clm() and the

I'm running r 2. on a mac running 10.6.4 and a dual-core macbook pro. I'm having a funny time with multicore. When I run it with 2 cores, mclapply, R borks with the following error. The process has forked and you cannot use this CoreFoundation functionality safely. You MUST exec(). Break on __THE_PROCESS_HAS_FORKED_AND_YOU_CANNOT_USE_THIS_COREFOUNDATION_FUNCTIONALITY___YOU_MUST_EXEC__()

Dear all, I tried to use nls, but I got the following error Error in numericDeriv(form[[3L]], names(ind), env) : Missing value or an infinity produced when evaluating the model Any suggestion? Thanks, Paola. The code I wrote is Data_pp2_mrna <- data.frame( p1 = protein_1, p6 = protein_6, pp2_mrna