-
-
Notifications
You must be signed in to change notification settings - Fork 393
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Improve loo functionality #496
Comments
I'm in progress of adding more explanations to loo package about interpreting loo output: approx SE of elpd_diff, p_loo, k stan-dev/loo#81. I'll comment here when ready with those. |
Because of some confusing questions in discourse.mc-stan.org I found out that
The year should be 2017 (http://link.springer.com/article/10.1007/s11222-016-9696-4), but more importantly in that paper log score is used. However the code computes
that is, log score multiplied by -2. As the lppd has a specific definition in Vehtari et al (2017) which doesn't include -2, I recommend to remove that -2. If you want to print out a value multiplied by .2, call it something else and make it clear that it's lppd multiplied by -2. This will make it much easier to answer questions whether one model is better than the other. |
I also noticed that |
Hmm, where does that -2 come from? pymc-devs/pymc@90c7286#diff-e41ef58a3a4077bc00fca799f90d12a4 And this pymc-devs/pymc@5d8a8c5#diff-e41ef58a3a4077bc00fca799f90d12a4 |
So it is the deviance scale. I think we could let user to decide the scale or return all scales (deviance, log, neglog?) |
R |
There is additional documentation now in loo package. See the pull request stan-dev/loo#98 (review). The glossary will appear in loo web pages also after the next release in spring. |
loo
functionality should be more verbose and return more informative data. (see Model Selection lecture in StanCon Helsinki by @avehtari)Also docstrings needs extensive examples for loo-usage.
The text was updated successfully, but these errors were encountered: