Assessing model fit for multi-season models (the remix)

questions concerning analysis/theory using program PRESENCE

Assessing model fit for multi-season models (the remix)

Postby kbrunk » Wed Aug 26, 2020 1:06 pm

Hey all,

I realize there are several elderly posts here asking about this topic, but it's been a while and I'm curious if any progress has been made in finding appropriate ways to assess model fit for multi-season occupancy models. I've been combing the literature and haven't found much.

I attempted to conduct an analysis of deviance (see Tempel et al. 2016 [Condor], and Jones et al. 2017 [Diversity and Distributions]) to at least see how much variation my covariates were explaining, but unfortunately I can't fit a fully-time-varying ("global") model with my limited data because the model becomes overfit. At least I suspect that's why the deviance of the larger, more complex model is higher than more simple models.

I've also seen a paper where they used the function 'parboot' in the Unmarked package to assess model fit with a parametric bootstrap, but I'm uncertain how appropriate that strategy is. Anyway, open to any and all thoughts on this topic! Thanks in advance!

Posts: 12
Joined: Fri Oct 12, 2018 11:51 am

Return to analysis help

Who is online

Users browsing this forum: Google [Bot] and 1 guest