search

coreytcallaghan / bird_diversity_MoB

working draft of analysis for a paper currently under review
1 stars 0 forks source link

n_perm? #11

Closed coreytcallaghan closed 3 years ago

coreytcallaghan commented 3 years ago

Hey @dmcglinn what exactly does n_perm do in this line of code stats <- get_mob_stats(bird_mob, group_var = 'grid_id', n_perm = 1)?

Do we need to up this? We aren't testing for 'treatment effects' per se right, as highlighted in the documentation? Just checking.

Thanks, Corey!

dmcglinn commented 3 years ago

Hey @coreytcallaghan so n_perm = 1 means that it will do just one permutation of a null model that randomly swaps each checklist's group. I set it to 1 so that it wouldn't slow down the analysis at this stage. Jon and Shane have told me that they don't like the null model but it is probably the simplest non-parametric randomization test you can do.

coreytcallaghan commented 3 years ago

Awesome, thanks. I won't worry about this for now then since we have a whole other set of complexity to drill down on (i.e., grid size and sample cutoff). Can circle back to this down the road if need be.