[R-sig-ME] hurdle negative binomial models with MCMCglmm

Zelda Van der Waal z.van-der-waal at newcastle.ac.uk
Mon Dec 12 10:25:31 CET 2011


thanks again Dave, i will give a go to the glmmADMB package as it seems to fit the distributions i am after i.e. both Poisson and negative binomial.

.zelda.

________________________________________
From: David Atkins [datkins at u.washington.edu]
Sent: 11 December 2011 22:02
To: Zelda Van der Waal
Cc: r-sig-mixed-models at r-project.org
Subject: Re: [R-sig-ME] hurdle negative binomial models with MCMCglmm

On 12/11/11 1:25 AM, Zelda Van der Waal wrote:
> Many thanks Dave for this link, this is very useful!
>
> However I can only see zero-altered models using Poisson distribution.
> Is there a way to use negative binomial distribution in zero-altered models (zero-inflated and hurdle) with mixed effects in MCMCglmm?

No, MCMCglmm does not fit a negative binomial model (with or without
zero component).

However, it does fit an "over-dispersed" Poisson, which includes an
additional, per-observation random-effect.  Although this is not
identical to a negative binomial, they are often functionally quite
similar, and the OD Poisson model is almost always a far superior fit a
straight Poisson.  In fact, MCMCglmm automatically fits this model (the
"units" term in the output is the over-dispersion random-effect).

If you are truly committed to a zero-inflated negative binomial, the
glmmADMB package has some facility for fitting these models; however, I
believe their are some restrictions on how covariates enter the logit
vs. count portions of the model.  At least, it seemed that way when I
perused them a while back.  Ben Bolker could speak more to what is (or
is not) possible via glmmADMB.

Hope that helps.

cheers, Dave

Dave Atkins, PhD
Research Associate Professor
Department of Psychiatry and Behavioral Science
University of Washington
datkins at u.washington.edu

Center for the Study of Health and Risk Behaviors (CSHRB)
1100 NE 45th Street, Suite 300
Seattle, WA  98105
206-616-3879
http://depts.washington.edu/cshrb/
(Mon-Wed)

Center for Healthcare Improvement, for Addictions, Mental Illness,
   Medically Vulnerable Populations (CHAMMP)
325 9th Avenue, 2HH-15
Box 359911
Seattle, WA 98104
http://www.chammp.org
(Thurs)


>
> thanks again to everyone
>
> .zelda.
>
> ________________________________________
> From: r-sig-mixed-models-bounces at r-project.org [r-sig-mixed-models-bounces at r-project.org] On Behalf Of David Atkins [datkins at u.washington.edu]
> Sent: 09 December 2011 18:57
> To: r-sig-mixed-models at r-project.org
> Subject: Re: [R-sig-ME] hurdle negative binomial models with MCMCglmm
>
> Zelda--
>
> You might take a look at a tutorial paper we have written on mixed model
> count regression; it also includes R code and two datasets:
>
> http://depts.washington.edu/cshrb/newweb/statstutorials.html
>
> [last ms on the page]
>
> The R code provides some details on using MCMCglmm for zero-altered
> models (including zero-inflated and hurdle mixed models).
>
> Hope it helps.
>
> cheers, Dave
>
>
> Dear all,
>
> I am very new at using MCMCglmm, and would like to fit a hurdle negative
> binomial distribution model with this package. Does anyone know whether
> this is possible? as this family is not amongst the distribution
> families described in the package vignette.
>
> thanks a lot
>
> .zelda.
>
> --
> Dave Atkins, PhD
> Research Associate Professor
> Department of Psychiatry and Behavioral Science
> University of Washington
> datkins at u.washington.edu
>
> Center for the Study of Health and Risk Behaviors (CSHRB)
> 1100 NE 45th Street, Suite 300
> Seattle, WA  98105
> 206-616-3879
> http://depts.washington.edu/cshrb/
> (Mon-Wed)
>
> Center for Healthcare Improvement, for Addictions, Mental Illness,
>     Medically Vulnerable Populations (CHAMMP)
> 325 9th Avenue, 2HH-15
> Box 359911
> Seattle, WA 98104
> http://www.chammp.org
> (Thurs)
>
> _______________________________________________
> R-sig-mixed-models at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models




More information about the R-sig-mixed-models mailing list