Hi Gustaf, just on your question of interpreting zapoisson in MCMCglmm - my recent paper uses zero-altered poisson models (for calling effort in male crickets), which might (hopefully?) help with interpretation: http://onlinelibrary.wiley.com/doi/10.1111/1365-2435.12766/full I also found David Atkins' paper (and associated tutorial) on zero-altered count models helpful - paper and code at his website here: https://depts.washington.edu/cshrb/statistics-resources-tutorials-tutorial-on-count-regression/ Cheers, and good luck! Tom ________________________________ Message: 1 Date: Fri, 25 Nov 2016 14:16:30 +0100 From: Gustaf Granath <gustaf.granath at gmail.com> To: r-sig-mixed-models at r-project.org Subject: [R-sig-ME] zero-inflated models in MCMCglmm Message-ID: <d4a6fd3a-151a-32e0-1fea-12ff7fe48466 at gmail.com> Content-Type: text/plain; charset=utf-8; format=flowed Hi, A few questions regarding zero-inflated models using MCMCglmm. 1. Odd contrasts are created when using, e.g. : y ~ trait-1 + at.level(trait, 1):(X1+X2), family = "zipoisson" #X1 and X2 are factors with 2 levels COEF TABLE traity traitzi_y at.level(trait, 1):X1lev1 at.level(trait, 1):X1lev2 at.level(trait, 1):X2lev2 It doesnt look like this in the course notes (what I can see). Is at.level(trait, 1):X1lev1 the reference level for everything below? I also get very high (>1000) estimates for traity, at.level(trait, 1):X1lev1 and at.level(trait, 1):X1lev2. 2. I made four models a) y ~ X1*X2, family = "poisson" Large overdispersion (units ~ 5) but everything looks fine (traceplots, random effects (including units) ). Predictive checks show that the models predict too few zeros though. And alarming is that predictions are really bad, e.g. a treatment mean of 40 is predicted to have 300 counts. b) y ~ trait-1 + at.level(trait, 1):(X1+X2), family = "zipoisson" Model looks OK, but again, predictions are way too high for the higher tretament means. c:d) y ~ trait-1 + at.level(trait, 1):(X1+X2), family = "zapoisson" or "hupoisson" Predicted values are much better. But is it the same way get predictions here? Possible to get predictions from the separate models (poisson/binomial) in the hurdle case? (code available?) #get e.g. treatment predictions? predict.MCMCglmm(model, marginal = ~ random_factor, type="response", posterior = "mean") The "zapoisson" model performs best but I dont understand why the "zipoisson" is so bad. Any typical things to look for when it looks like this? Interpreting "zapoisson" isnt easy, any good literature/tutorials on this model? Cheers Gustaf -- Gustaf Granath Post doc Swedish University of Agricultural Sciences
zero-inflated models in MCMCglmm
1 message · Houslay, Tom