4
$\begingroup$

I have a set of count data that seems to fit "Poisson" = not overdispersed, alpha = 0.

The problem is, I get different results using gamlss vs glmer. Any help explaining the difference would be appreciated:

Treatment is a factor with 6 levels. Trial is a random intercept factor with 3 levels.

Glmer.POI <- glmer( Y ~ Treatment + offset(log(Total)) + (1|Trial),      family=poisson))
Gamlss.PO <- gamlss(Y ~ Treatment + offset(log(Total)), random=~1|Trial, family=PO)

# Glmer result:  AIC = 284. deviance = 270
# Gamlss result: AIC = 388. deviance = 376

I get different coefficients and different p-values with the 2 models. When I look at the diagnostic plots, I see residuals that increase with fitted values in the gamlss model "heteroscedasticity", but not with the glmer.

My intuition tells me this is related to how random effects are handled, but how?

I think I had similar problems with another dataset using negative binomial. I pulled the question from this site to concentrate on this one: If gamlss and glmer behaviour with random effects explains both problems, Great! But I'd like to know how a biologist (non statistician) "poor soul" like me can understand how to use these tools and choose the right one! ;-)

$\endgroup$
  • $\begingroup$ Welcome to the site, @VincentPhilion. Your comment still makes it seem like the same answer could address both questions. Here you state that you'd like to "understand how to use these tools and choose the right one", there you ask, "What makes these models so different, and how can I choose between them?". These seem awfully similar to me. If you are asking something substantially different b/t these two Q's, can you edit them to make the difference clearer? $\endgroup$ – gung Feb 18 '13 at 16:10
  • 2
    $\begingroup$ What you hint at I suspect as well, in that it is likely the random effects estimation that is causing differences between the two procedures (as opposed to the link function). The fact that it is different sets of data is immaterial (since you don't provide the data for people to examine and estimate the models themselves anyway). I would suggest you stick with one question, and when that is answered if it doesn't apply here, or doesn't satisfactorily answer this question, then ask a second one. $\endgroup$ – Andy W Feb 18 '13 at 16:10
  • $\begingroup$ OK, I will scrap the negative binomial question for now. Hopefully, someone who knows about gamlss and glmer will answer! $\endgroup$ – Vincent Philion Feb 18 '13 at 17:39
2
$\begingroup$

It may be that it has changed since this question was written, but it looks as though the random effect is not coded correctly for gamlss. You have it written as "random=~1|Trial," but when I try to run that through gamlss it states that the "|" is not valid for factors. More details on how to code random effects for gamlss is in the manual: http://www.gamlss.org/wp-content/uploads/2013/01/gamlss-manual.pdf

The benefit of gamlss is that you can model different aspects (I use a zero-inflated beta distribution and can model both the distribution of non-zero values and the probability of zeroes). It could be that, as coded, the random effect is not influencing the same part of the model as it is in glmer. When I use a ~ for the random effect in my gamlss models, it doesn't contribute to the distribution of non-zero values anymore; it is transferred to the probability of zero.

Unfortunately I have not figured out how to properly code mixed models for gamlss, but hopefully this at least clears up why you're getting different results.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.