guiblanchet / HMSC

Hierarchical modelling of species community
40 stars 13 forks source link

species association and random variables #18

Open ghost opened 6 years ago

ghost commented 6 years ago

Hello,

I am not sure if I am making an error somewhere. But from what I understand, HMSCdata can accept both 'Random' and 'Auto' arguments (I have both in my dataset. Auto= spatial coordinates and Random= effort for each sampling plot). The model runs with both arguments specified but I have troubles in the corRandomEff function which creates two different arrays, one each for Random and Auto.

  1. How do I use/interpret these separate correlation matrices for my study site to generate a single one?
  2. Am I not supposed to use both arguments in a single model?