To Do

[wzmli]

Highest Priority

• Make sure glmmTMB lmm work
  -- cannot find residual summary.
  -- tmb cannot handle 500 species by 200 sites (300 sp works)

Error in nlminb(start = par, objective = fn, gradient = gr) : 
  gradient function must return a numeric vector of length 6
In addition: Warning messages:
1: In nlminb(start = par, objective = fn, gradient = gr) :
  NA/NaN function evaluation
2: In he(par) : restarting interrupted promise evaluation

obj$gr() does not work and returns NaN

• Implement phylo_glmm (other glmm families/distributions)
  -- It is really slow

• Clean up and document code/repo

• Set up a more structured simulation test (more or less done for single site)

• Not as important, think about using same tree but different data (seeds)

• Create simple test to show pez/phyr and lme4/glmmtmb gives similar results

• Run all cases with lme4/glmmtmb (because they are fast)

• Finish the draft

• Run pez/phyr

• add glmmTMB and BRMS back in