similar to: Residuals from GLMMs in the lme4 package

I am creating habitat selection models for caribou and other species with data collected from GPS collars. In my current situation the radio-collars recorded the locations of 30 caribou every 6 hours. I am then comparing resources used at caribou locations to random locations using logistic regression (standard habitat analysis). The data is therefore highly autocorrelated and this causes Type

Hi r-help forum, I have been collecting contact data (with proximity logger collars) between a few different species of animal. All animals wear the collars, and any contact between the animals should be detected and recorded by both collars. However, this isn't always the case and more contacts may be recorded on one collar of the two. This is fine, it depends on battery life and other

Hi R help forum, I have a simple data frame of four columns - one of numbers (really a categorical variable), one of dates and one of data. I have over 500,000 data points to work with, spread over 40 files, each named after a different animal. These are contact data recorded by proximity loggers over two years between the animals of the file name and collars being worn by other animals. The

Dear Listers, Apologize to pile up on the 'tz' issue in POSIX objects. I have a 'simple' thing on which I must make up my mind but cannot do it from the existing R-help threads. I am currently working on dog telemetry in China, and download time information from GPS collars. I would like to set up the corresponding POSIXxx variables in R to a given time zone. Eg Pekin

I need you help with this problem, I have a data-frame like this: BHID=c(43,43,43,43,44,44,44,44,44) FROM=c(50.9,46.7,44.2,43.1,52.3,51.9,49.3,46.2,42.38) TO=c(46.7,44.2,43.1,40.9,51.9,49.3,46.2,42.38,36.3) AR=c(45,46,0.0,38.45,50.05,22.9,0,25,9) DF<-data.frame(BHID,FROM,TO,VALUE) #add the length DF$LENGTH=DF$FROM-DF$TO where: + BHID: is the borehole

Hi all, I have multiple datasets of time series data taken from GPS collars. The collars are supposed to take a fix every hour on the half hour, i.e., 0:30, 1:30, 2:30...23:30, (because it sometimes takes longer for the collars to acquire a location the minute of these locations vary from 30-34) but because of a software glitch in the collars, at random times the collars start taking multiple

Both of these bugs are not a real harm, however, they have been annoying me for too long ... ;-) 1) print(2^30, digits = 12) #- exponential form; unnecessarily! formatC(2^30, digits = 12) #- shows you what you'd want above ## S-plus is okay here; note that the problem also affects ## paste(.) & format(.) : options(digits=10) paste(2^(4*1:8)) S-plus gives [1] "16"

Here is a summary of responses to my original email (see my query at the bottom). Thank you to Achim Zeileis , Anders Nielsen, Pierre Kleiber and Dave Fournier who all helped out with advice. I hope that their responses will help some of you too. ***************************************** Check out glm.nb() from package MASS fits negative binomial GLMs.

Dear R-ers, I am just a simple 'end-user' of R and am trying to analyse data with a binary response variable (dead or alive) in relation to weight and sex (of young birds). As some of the birds have the same biological mother, I am using mixed models with the identity of the mother as a random factor. (please, Mick Crawley, when are you going to write a chapter on mixed models with binary

Sort of a warning before I start: This post may be considered to describe a rather amateurish approach to distributing software which may annoy some people, but I sincerely hope it doesn't. I've been working for some years with David Clayton on a project which started life as an S package but has now turned into an R library. It is (now) called GLMMGibbs and estimates the parameters of

Hi, I have a couple of questions related to glmm (glmmPQL in MASS and GLMM in lme4). 1) is there some way do obtain the fitted values by group, similar to: > predict(dbd.glmmPQL, dbd.cytdens, + type="response", level=0) where dbd.glmmPQL is the fitted model and dbd.cytdens is a data frame with a subset of the factors? 2) when I double-click on a saved workspace

I am trying to find a way to analyze a "simple" mixed model with two levels of a treatment, a random blocking factor, and (wait for it) negative binomial count distributions as the response variable. As far as I can tell, the currently available R offerings (glmmGibbs, glmmPQL in MASS, and Jim Lindsey's glmm code) aren't quite up to this. From what I have read (e.g.

Dear R-ers, I am just a simple 'end-user' of R and am trying to analyse data with a binary response variable (dead or alive) in relation to weight and sex (of young birds). As some of the birds have the same biological mother, I am using mixed models with the identity of the mother as a random factor. (please, Mick Crawley, when are you going to write a chapter on mixed models with binary

Hi there, I have a question about the GLMM that I'm doing, that a statistician friend suggested I should have for my analysis. I would like to know if there's any way of obtaining a p value and R square for the full model (and not each variable separately) as to asses whether this model is somewhat appropriate or not. Can one do this for a GLMM in the lme4 package? The other thing I

Hi everyone, I'm trying to fit a generalized linear mixed effects model (logistic) in R and am having some trouble specifying the covariance structure for the random effects. I'm using glmer, which by default assumes an unstructured relationship between the random effects, but I want the structure to be a multiple of an identity. Here is my code: glmer(y ~ 1 + (x1 + x2 + x3 + x4

In a GLMM, one compares the conditional model including covariates with the unconditional model to see whether the conditional model fits the data better. (1) For my unconditional model, a different random effects term fits better (independent random effects) than for my conditional model (correlated random effects). Is this very uncommon, and how can this be explained? Can I compare these models

I'm fitting generalized linear mixed models to using several fixed effects (main effects and a couple of interactions) and a grouping factor (site) to explain the variation in a dichotomous response variable (family=binomial). I wanted to compare the output I obtained using PROC GLIMMIX in SAS with that obtained using lmer in R (version 2.6.1 in Windows). When using lmer I'm specifying

Dear R-listers, I am working with generalized linear mixed models to quantify the variance due to two nested random factors, but have hit a snag in the interpretation of variance components. Despite my best efforts with Venables & Ripley 2002, Fahrmeir & Tutz 2001, R-help archives, Google, and other eminent sources (i.e. local R gurus), I have not been able to find a definitive answer

Three related questions on LMEs and GLMMs in R: (1) Is there a way to fix the dispersion parameter (at 1) in either glmmPQL (MASS) or GLMM (lme4)? Note: lme does not let you fix any variances in advance (presumably because it wants to "profile out" an overall sigma^2 parameter) and glmmPQL repeatedly calls lme, so I couldn't see how glmmPQL would be able to fix the dispersion

Dear All, I am analysing a dataset on levels of herbivory in seedlings in an experimental setup in a rainforest. I have seven classes/categories of seedling damage/herbivory that I want to analyse, modelling each separately. There are twenty maternal trees, with eight groups of seedlings around each. Each tree has a TreeID, which I use as the random effect (blocking factor). There are two