similar to: Correlated count data technique advice

Dear R-helpers, this mail is intended to mention a rather trange result and generate potential useful comments on it. I am not aware of another posts on this issue ( RSiteSearch("quasipoisson lmer version dispersion")). MUsing the exemple in the reference of the lmer function (in lme4 library) and turning it into a quasi-poisson or quasi-binomial analysis, we get different results,

Hi Greg, For quasi families I've used extended quasi-likelihood (see Mccullagh and Nelder, Generalized Linear Models 2nd ed, section 9.6) in place of the likelihood/quasi-likelihood in the expression for the (RE)ML score. I hadn't realised that this was possible before the paper was published. best, Simon ps. sorry for slow reply, the original message slipped through my filter for

Hey Buddy, Hope you have been doing well since last contact. If you have the answer to the following question, please let me know. If you have chance to travel up north. let me know. best, -Sean ---------- Forwarded message ---------- From: Sean Zhang <seanecon@gmail.com> Date: Sat, Apr 11, 2009 at 12:12 PM Subject: question related to fitting overdispersion count data using lmer

Dear R-helpers: I have a question related to fitting overdispersed count data using lmer. Basically, I simulate an overdispsed data set by adding an observation-level normal random shock into exp(....+rnorm()). Then I fit a lmer quasipoisson model. The estimation results are very off (see model output of fit.lmer.over.quasi below). Can someone kindly explain to me what went wrong? Many thanks in

Dear all, Using the quasibinomial and quasipoisson families results in no AIC being calculated. However, a quasi AIC has actually been defined by Lebreton et al (1992). In the (in my opinon, at least) very interesting book by Burnham and Anderson (1998,2002) this QAIC (and also QAICc) is covered. Maybe this is something that could be implemented in R. Take a look at page 23 in this pdf:

Hello R-help, According to a research article that covers the topic I'm analyzing, in Stata, a Poisson pseudo-maximum-likelihood (PPML) estimation can be obtained with the command poisson depvar_ij ln(indepvar1_ij) ln(indepvar2_ij) ... ln(indepvarN_ij), robust I looked up Stata help for the command, to understand syntax and such: www.stata.com/help.cgi?poisson Which simply says

Hi everyone, I'm trying to perform the following regressions in order to compare linear vs. sigmoidal fit of the relationship between my dependent variable (y) and one explaining parameter (x2), both including the confounding effects of a third variable (x1): quasi-pois-lin <- glm(y ~ x1 + x2, family = quasipoisson(link="identity"), data=fit) quasi-pois-sig <- gnm(y ~ x1 +

Dear all, I am analyzing counts of seabirds made from line transects at sea. I have been fitting Poisson and negative binomial distributions to the data using the goodfit function from the vcd library. I would also like to evaluate how well a quasi-poisson distribution fits the data. However, none of the potentially suitable functions I have identified (goodfit(vcd), fitdistr(MASS),

Hi list, can anybody point me to the trick how glm is computing the dispersion parameter in quasi-poisson regression, eg. glm(...,family="quasipoisson")? Thanks &regards, Sven

Hello, I'm looking for a dataset for Quasipoisson regression. The result must be significantly different from the classic poisson regression. You can help me? Please It is for my last university exam Thanks a lot -- View this message in context: http://r.789695.n4.nabble.com/Dataset-Quasi-Poisson-tp3533060p3533060.html Sent from the R help mailing list archive at Nabble.com.

Dear R users, I have now tried out several options of obtaining p-values for (quasi)poisson lmer models, including Markov-chain Monte Carlo sampling and single-term deletions with subsequent chi-square tests (although I am aware that the latter may be problematic). However, I encountered several problems that can be classified as (1) the quasipoisson lmer model does not give p-values when

Hello list, I am not sure if the terminology that I am using here is widely used, however, I provide an example in the hopes that my problem will become clear. My basic problem is that I am unsure of how to 'constrain' my model estimates to reproduce the aggregate (by factor levels) observed dependent variable for a negative.binomial model. I realize this sounds rather vague, so I provide

I am attempting to model data with the following variables: timepoint - n=48, monthly over 4 years hospital - n=3 opsn1 - no of outcomes total.patients skillmixpc - skill mix percentage nurse.hours.per.day Aims To determine if skillmix affects rate (i.e. no.of.outcomes/total.patients). To determine if nurse.hours.per.day affects rate. To determine if rates vary between

Hello, I have a question about the add1() function and quasilikelihoods for GLMs. I am fitting quasi-Poisson models using glm(, family = quasipoisson). Technically, with the quasilikelihood approach the deviance does not have the interpretation as a likelihood-based measure of sample information. Functions such as stepAIC() cannot be used. The function add1() returns the change in the scaled

Dear fellows, I'm trying to extract the AIC statistic from a GLM model with quasipoisson link. The formula I'm referring to is AIC = -2(maximum loglik) + 2df * phi with phi the overdispersion parameter, as reported in: Peng et al., Model choice in time series studies os air pollution and mortality. J R Stat Soc A, 2006; 162: pag 190. Unfortunately, the function logLik

> Hello, > > I have a question about a discrepancy between the > reported F statistics using anova() and add1() from > adding an additional term to form nested models. > > I found and old posting related to anova() and > drop1() regarding a glm with a dispersion parameter. > > The posting is very old (May 2000, R 1.1.0). > The old posting is located here. >

Hello, I am interested in estimating this type of random effects panel: y_it = x'_it * beta + u_it + e_it u_it = rho * u_it-1 + d_it rho belongs to (-1, 1) where: u and e are independently normally zero-mean distributed. d is also independently normally zero-mean distributed. So, I want random effects for group i to be correlated in t, following an AR(1) process. Any idea of how

Hello all: I frequently have glm models in which the residual variance is much lower than the residual degrees of freedom (e.g. Res.Dev=30.5, Res.DF = 82). Is it appropriate for me to use a quasipoisson error distribution and test it with an F distribution? It seems to me that I could stand to gain a much-reduced standard error if I let the procedure estimate my dispersion factor (which

Dear R users I have been looking for functions that can deal with overdispersed poisson models. Some (one) of the observations are negative. According to actuarial literature (England & Verall, Stochastic Claims Reserving in General Insurance , Institute of Actiuaries 2002) this can be handled through the use of quasi likelihoods instead of normal likelihoods. The presence of negatives is not

Sorry about re-posting this, it never went out to the mailing list when I posted this to r-help forum on Nabble and was pending for a few days, now that I am subscribe to the mailing list I hope that this goes out: I've been a viewer of this forum for a while and it has helped out a lot, but this is my first time posting something. I am running glm models for richness and abundances. For