I have a model in PyMC v5.18, fit to some observations. I simulated posterior values in a somewhat different model (with much overlap to the original model of course), using pm.sample_posterior_predictive(), predicting distributions as traces for several RVs. Now I would like to measure the log like…

Estimate log likelihood of ground truth values using trace from sample_posterior_predictive

bridgeland December 6, 2024, 7:55pm 2

Wups! I asked the same question four years ago.

2 Likes

Topic		Replies	Views
Is it getting better or do you feel the same?: How to evaluate a model by estimating log probability of ground truth in posterior trace? Questions	4	614	January 7, 2021
How to retrieve (log) posterior/prior/likelihood from trace? Questions	4	4251	May 23, 2020
Are samples from the trace equivalent to samples from pm.sample_posterior_predictive? Questions	6	629	October 16, 2020
Log-likelihood not found in InferenceData when model as pm.Potential in PYMC v5	3	363	March 27, 2024
Trace from Pymc3 being used in Pymc 4.0 v5	11	906	June 10, 2022