brianstock / MixSIAR

A framework for Bayesian mixing models in R:
http://brianstock.github.io/MixSIAR/
94 stars 75 forks source link

I only know the prior for 1 source. Can I run a model with unknown priors? #296

Closed AdrianaVelasquezVacca closed 3 years ago

AdrianaVelasquezVacca commented 3 years ago

Hi! I have 4 sources, 3 isotopes. I only know that one of the sources is 20% of the diet. I have no info for the rest of my sources (since the rest of stomach content contained species I didn't find in my sampling), but we know the turtle eats them. My approach was to put priors as: kw.alpha <- c(0.8,1.06,1.06,1.06), giving the rest of the sources and equal proportion of the diet seemed to me like the best way...is there anything else I could do? Or am I missing something here? Thanks a lot!

Originally posted by @AdrianaVelasquezVacca in https://github.com/brianstock/MixSIAR/issues/156#issuecomment-957038373

AdrianaVelasquezVacca commented 3 years ago

Closed this one because Brian answered on my original comment. : )