Statistical Analysis Stack Exchange
Statistical Analysis Stack Exchange

Questions tagged [quasi-binomial]

Please use [quasi-likelihood] instead.

A quasi-binomial model is a binomial model estimated with quasi-likelihood (an inference function which is not a true likelihood function, but is used as a replacement for the binomial likelihood when some assumption underlying the binomial model is note verified, typically overdispersion).

Wikipedia has an article https://en.wikipedia.org/wiki/Quasi-likelihood with further information and references.

10 questions
6
votes
1 answer

Accounting for overdispersion in binomial glm using proportions, without quasibinomial

I am doing binomial GLM using relative abundance, for example: model<-glm(cbind(number_pres,number_abs)~Var1+Var2+Var3+Var4..., family=binomial, data=Data). My sample size is about 700, and I have about 15 explanatory variables. I can't use Poisson…
snowtosurf
  • 81
  • 1
  • 4
3
votes
0 answers

glmnet with quasibinomial in R

I have a fractional response regression model, which is estimated with R's glm with family parameter equal to quasibinomial. Now, I want to perform model selection via lasso on the model. Is there any way to tweak R's glmnet to perform lasso on…
DavidH
  • 178
  • 5
2
votes
0 answers

Binomial GLM with unknown totals?

Essentially, I have some covariate data X, and a dependent variable Y consisting of proportions of a sample that shown a certain response (i.e. between 0 and 1). I suspect I want to proceed via a GLM approach, but the thing is, I don't know the…
Fhnuzoag
  • 21
  • 1
2
votes
2 answers

What happen when model selection ranks null model as the best one and there's another model that is competitive?

I'm analyzing the proportion of marked chicks vs. the number of chicks that were recaptured at one moth of age (not possible to use conventional capture-recapture analysis because we don't have a second recapture event). The idea is to find if there…
MSS
  • 267
  • 2
  • 9
2
votes
1 answer

Is it appropriate to account for overdispersion in a glm by using a quasi-binomial distribution?

I have several sets of count data (as below) that are overdispersed. The overdispersion likely comes as a result of the number of zeros in the data which I understand means the paramater estimates in my model are okay, but the standard error may be…
hamilthj
  • 253
  • 1
  • 4
  • 14
1
vote
0 answers

P values from quasi-binomial generalised linear models in R

I am sorry if this has been asked elsewhere. I could find it when looking. I am running a quasi-binomial generalised linear model (to correct for overdispersion) weighted by a count of sample size. I have simplified the model using F tests. model2…
LuCapstick
  • 11
  • 2
1
vote
0 answers

GLM on Proportion Response and Categorical Predictor gives strange standard errors

I am looking at the effects of seawater salinity levels on fertilization rates. Salinity levels are set so they are treated as factors. Call: glm(formula = cbind(fertilized, unfertilized) ~ salinity, family = "quasibinomial", data =…
CFC
  • 11
  • 2
1
vote
0 answers

c-bind on proportion data, quasi-binomial GLM: how to remove effect of sample size

I'm studying a colonial organism, and my hope is to compare differences in percent survival between three treatment groups. The results are clear, there is a 55% difference in survival between control and treatment groups and very little variance…
Disproportionately confused
  • 21
  • 4
0
votes
1 answer

Calculating QAICc and Averaging GLMM models with various overdispersion

I am having difficulty figuring out how to calculate a dispersion parameter to calculate QAICc for a GLMM with a binomial fit. I have tested for overdispersion using this code: overdisp_fun <- function(model) { ## number of variance parameters…
birdnerd_j
  • 11
  • 3
0
votes
0 answers

Can I run a multivariate quasi-binomial analysis of proportion data?

I am trying to best analyse a set of foraging ecology data with >10 behaviour categories (DVs) and 3 levels of IV (season, sex, age). The time which an animal spent engaged in a behaviour was recorded and then divided by the total time spent in…
Mand
  • 1
  • 1