[R-sig-ME] Interpreting Zero altered models in MCMCglmm

[Hodsoll, John]

Hi David

Thanks for your note. Really useful paper and code which I've used quite extensively. One point of interest, I understand from your code how estimated means are generated for observations with events. But how would you recommend combining this with the estimates for zero inflation to get an overall mean? In general when we present this to clinicians they would want to get an overall estimate of reduction of violent incidents. 

Thanks and again, great paper.

John

-----Original Message-----
From: r-sig-mixed-models-bounces at r-project.org [mailto:r-sig-mixed-models-bounces at r-project.org] On Behalf Of David Atkins
Sent: 08 November 2013 14:58
To: r-sig-mixed-models at r-project.org
Subject: Re: [R-sig-ME] Interpreting Zero altered models in MCMCglmm


John--

In addition to Jarrod's specific suggestions, you might give a look at an article we wrote describing GLMM for count data (including zero-inflated / hurdle models), which also has accompanying R code, focused in large part on MCMCglmm:

Atkins, D. C., Baldwin, S., Zheng, C., Gallop, R. J., & Neighbors, C. 
(2013). A tutorial on count regression and zero-altered count models for longitudinal substance use data.  Psychology of Addictive Behaviors, 27, 166-177. doi: 10.1037/a0029508 PMCID: PMC3513584.

MS, data, code can be found from link at:

http://depts.washington.edu/cshrb/statistical-resources-tutorial-link/

Hope that helps and best wishes with your analyses.

cheers, Dave

--
Dave Atkins, PhD

Research Professor
Department of Psychiatry and Behavioral Science University of Washington datkins at u.washington.edu
http://depts.washington.edu/cshrb/david-atkins/#more-48

"The combination of some data and an aching desire for an answer does not ensure that a reasonable answer can be extracted from a given body of data." -- John Tukey

_______________________________________________
R-sig-mixed-models at r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models