Quasi-likelihood is a function similar to but not likelihood, and it was introduced by Wedderburn (1974) and mainly used in generalized linear models.

learn more… | top users | synonyms

1
vote
0answers
11 views

Composite-likelihood ratio test

I am interested in a number of articles (such as Kim and Stephan 2002 and follow-up articles) that use composite likelihood ratio tests to infer selection pressure on linked (phased) genetic data. I ...
0
votes
0answers
20 views

Gaussian QMLE in estimating GARCH model

I am having some troubles understanding the estimation of a CCC-GARCH model (where the univariate GARCH models are GJR-GARCH(1,1)) by the means of Gaussian QMLE with the likelihood function of ...
3
votes
0answers
11 views

Quasi-likelihood increases or decreases when mu_i and y_i are closer?

I have a question about quasi-likelihood. I think the following formula says something opposite to what likelihood means. Could someone clarify what I'm misunderstanding. I'm looking at the formula ...
1
vote
0answers
14 views

How to decide between quasi-poisson and negative binomial?

I tried quasi-poisson and negative binomial glms on my counted data in R. The estimates are pretty much the same but p-value are different. Quasi-poisson gives insignificant result. NB give ...
0
votes
0answers
27 views

Central limit theorem for maximum likelihood estimators when modelling assumptions are violated

Lehman's Element's of Statistical Learning Theory gives in Theorem 7.5.2 a central limit theorem for multiparamter maximum likelihood estimators. (Many other sources provide similar theorems.) The ...
0
votes
1answer
17 views

Frequency Data, Model Choice (Poisson with Offset, Fractional Regression)

I have text data and am interested in estimating the effect of some covariate on word frequency. All the frequencies are very small. The unit of observation is a single document. I'm trying to think ...
4
votes
0answers
59 views

Idea and intuition behind quasi maximum likelihood estimation (QMLE)

Question(s): What is the idea and intuition behind quasi maximum likelihood estimation (QMLE)? What makes the estimator work when the actual error distribution does not match the assumed error ...
1
vote
1answer
68 views

Diagnostics for quasipoisson glm for continuous data

I'm a little confused about how to use the quasipoisson family in the glm function. It was recommended by someone that I use it for my analysis, even though the data are continuous - and as such, I ...
2
votes
1answer
67 views

Scaling vs Offsetting in Quasi-Poisson GLM

I recently modeled insurance claim frequency assuming a Quasi-Poisson distribution in R. My frequency dependent variable was calculated, in advance of modeling, as the number of claims per underlying ...
0
votes
0answers
9 views

Number of parameters for a GEE

How can I determine the number of parameters I have for each of 2 Generalized Estimating Equations, as well as the log-quasi-likelihood for each equation, using R? I am using the geepack library, R ...
0
votes
0answers
73 views

How can compare a Poisson model against a Quasipoisson model in GAM?

I have count data of species and I would like to fit a GAM model in mgcv with poisson distribution. The poisson model has overdispersion so I have read that is better to fit a quasipoisson ...
0
votes
0answers
24 views

Why does GEE produce the same parameter estimates as OLS?

The quasi-likelihood function optimized under GEE is: $S_k(\beta)=\sum_{i=1}^{K}\frac{\partial\mu_i}{\partial\beta_k}\nu_i^{-1}(y_i-\mu_i)=0,$ where $\mu_i=h(\textbf{x}_i,\beta)$ is the conditional ...
1
vote
1answer
127 views

GLM Model checking Plots - Quasi Poisson - Poisson

I wonder whether accounting for overdispersion in a GLM (Quasi - Poisson instead of Poisson family) has an effect on the model checking plots (plot of residuals against fitted values, a scale–location ...
1
vote
0answers
54 views

Generalized linear model using quasi-likelihood

I am going to fit a model using quasi likelihood, (because the dispersion parameter > 1, y is a binary data). But when I ...
2
votes
1answer
567 views

compare quasi poisson models

I have two models: ...
2
votes
0answers
110 views

What properties of a likelihood function are required for quasi-likelihood estimation?

Quasi-likelihood seems like a great way to use Iteratively Weighted Least Squares to fit linear linear models with a very general class of likelihoods. But what is that class? Obviously the ...
5
votes
1answer
313 views

GLM analogue of weighted least squares

The short version: I can fit a model using Weighted Least Squares, given a diagonal matrix of weights $W$, by solving $(X^TWX)\hat{\beta}=X^TWy$ for $\hat{\beta}$. Is there a GLM analogue? if so, ...
3
votes
1answer
1k views

How to handle underdispersion in GLMM (binomial outcome variable)

I'm working on the following model in R: ...
2
votes
1answer
92 views

Estimating the asymptotic distribution of a quasi maximum likelihood estimator

We consider the following GARCH(1, 1) model: $y_t = h_t \epsilon_t$ where $(\epsilon_t)_{t \in \{1, \dots, n\}}$ are i.i.d. random variables with mean 0 and standard deviation 1. $h_t = \omega + ...
1
vote
1answer
173 views

Difference between quasi-likelihood estimating equations, IEE and GEE?

What is the difference between quasi-likelihood estimating equations, and GEE? From a note Quasi-score function is for independent, over-dispersed data (Poisson or binomial), while GEE1 is for ...
1
vote
1answer
935 views

GEE, quasi-likelihood and what it generalizes

Wikipedia formulates Generalized Estimating Equations (GEE) as Given a mean model, $\mu_{ij}$, and variance structure, $V_{i}$, the estimating equation is formed via: $$ U(\beta) = ...
5
votes
1answer
330 views

Models for Generalized Estimating Equation?

From Wikipedia, Generalized Estimating Equation (GEE) is a method to estimate the parameters of a generalized linear model (with an exponential family distribution for the response). By reading other ...
0
votes
0answers
217 views

Weird behavior of Poisson, negative binomial, and quasipoisson GLM

I have some overdispersed count data (mean=8.6, var=263.5) that I am hoping to model using either a negative binomial (NB) or quasipoisson GLM. A rootogram suggests that the Poisson distribution is a ...
3
votes
1answer
5k views

Definition of dispersion parameter for quasipoisson family

I try to model quasi-poisson family in bugs language, to handle overdispersion. According to Introduction to WinBUGS for ecologists, this is done by: $log(\lambda_i) = f(x_i) + \epsilon_i$ $N_i \sim ...
0
votes
0answers
283 views

GLM quasi family with log transformation?

I am working on my thesis analysis, and I have some error data that's right-skewed. I log-transformed it and ran glm on it (gaussian, identity in R) weighted by sample size, and my data is still ...
0
votes
0answers
370 views

Using GLM with germination percentages

I have germination data in percentages (with a few zeros) and wish to fit a GLM on them to explore how different seed origins and levels of treatment affect them. My results are not exactly 'counts', ...
2
votes
0answers
123 views

Fitting a complex model of variance-vs-mean for quasi likelihood models? (in R)

I wish to deal with over dispersion of a Poisson model. Negative binomial (glm.nb), and quasi likelihood models (family=quasi in glm) do not offer a flexible enough structure of the variance-vs-mean ...