Skip to content

ggplot of Hurdle model

3 messages · Mollie Brooks, andreu blanco

Original
andreu blanco
# 
According to the information in the Zuur's book "Begginers guide to
Zero-inflated models with R", I see they suggest a graph to add to the
research paper. However I don't know how to sketch the model fit to my
results.

My data structure is:
'data.frame': 80 obs. of  6 variables:
 $ Location  : Factor w/ 8 levels "C1","C2","O",..: 1 1 1 1 1 5 5 5 5 5 ...
 $ Protection: Factor w/ 2 levels "C","P": 1 1 1 1 1 2 2 2 2 2 ...
 $ Exposure  : Factor w/ 2 levels "E","S": 1 1 1 1 1 1 1 1 1 1 ...
 $ replicates: int  1 2 3 4 5 1 2 3 4 5 ...
 $ Biomass   : num  124.8 104.8 139.2 102.6 62.9 ...

Any suggestion would be highly appreciated.

Andreu
Mollie Brooks
# 
Hi Andreu,

We don?t really have enough information to answer your question. I don?t have access to that book and I imagine many people on this list don't either. 

If you are using glmmTMB and trying to plot predictions, there is an example on pages 8-9 of this appendix
https://www.biorxiv.org/content/biorxiv/suppl/2017/05/01/132753.DC1/132753-2.pdf <https://www.biorxiv.org/content/biorxiv/suppl/2017/05/01/132753.DC1/132753-2.pdf>

cheers,
Mollie

  
  


  


      

    

    

      
      

        


  

        

      andreu blanco
    

    

      
      #
    

  


  

      
Thank you Mollie, I understand what you mean but this is the reference I
have and that's why I am referring to it. Of course I understand every data
will need its own graph and that why I am asking for help. I will check the
info you sent and try to figure out if it is useful for my data.

Yes, I am trying to fil the model predictions, I used a glmer for the
Hurdle model and it perform smoothly. However I want to understand how to
graph the predicted values of the model to get a fancy figure for my paper.
Unfortunately I am quite new to R and doing betiful graphs I think is quite
difficult, at least as far as I tried. I hope to get some help on how to do
a good graph for my predicted values.

        
On 2 November 2017 at 15:11, Mollie Brooks <mollieebrooks at gmail.com> wrote: