Hi there, I wrote a walkthrough on how to use integrated LOO. This was mainly to describe the process I used in a package, but I tried to generalize it to an extent so hopefully others will find it helpful: https://andrewghazi.github.io/posts/int_loo/integrated_loo.html Please let me know if you spot any mistakes!
5 Likes
Nice walkthrough! I wrote about some related issues for multivariate ordinal models that might complement your post: Adventures in ordinal model likelihoods.
2 Likes
Looks great! One of the references is missing the journal information. Here’s the bib entry for it
@article{JMLR:v17:14-540,
author = {Aki Vehtari and Tommi Mononen and Ville Tolvanen and Tuomas Sivula and Ole Winther},
title = {Bayesian Leave-One-Out Cross-Validation Approximations for Gaussian Latent Variable Models},
journal = {Journal of Machine Learning Research},
year = {2016},
volume = {17},
number = {103},
pages = {1–38},
url = {http://jmlr.org/papers/v17/14-540.html}
}
1 Like
Thanks, your help on one of my earlier threads is what enabled me to get to the point of being able to write this post. I fixed the reference you mentioned.
Thanks. I’m still going through your post but it has a lot of good information. I’ve been trying loo with ordered probit models recently (pre-specified cut points thankfully), so I’ve been looking for resources like this.
2 Likes