I have a simple partial pooled model that fits a normal distribution to observed data. In my actual data, I have hundreds of groups with anywhere between 1 and hundreds of observations per group. I tried fitting to the entire dataset and found that I was getting major divergences and sampling issues…

Out of sample/model predictions in hierarchical model with new observed data

ricardoV94 October 1, 2024, 6:05am 4

pm.Flat is currently a good way to ensure the draws are being used. There was an idea to add a specific FromTrace object for this behavior, as Flat is a bit hacky.

2 Likes

Topic		Replies	Views
How to properly do out-of-sample prediction for hierarchical model v5 modeling , hierarchical , prediction	24	1489	January 25, 2024
How do we predict on new unseen groups in a hierarchical model in PyMC3? Questions	10	5432	September 12, 2022
Predict on unseen group in hierarchical model Questions	6	1590	November 9, 2020
How to predict new values on hold-out data Questions	24	13494	July 22, 2020
Prediction using sample_ppc in Hierarchical model Questions from_github	6	5004	December 14, 2017

Out of sample/model predictions in hierarchical model with new observed data

Related topics