Hi, I am developing a model with a pm.HurdleGamma likelihood. I have priors on the alpha and beta parameters of the HurdleGamma, but not on the psi parameter. When I sample with a small subset of my data (2500 observations), it samples well and the results look good to me. However, it takes about 2…

Sampling options with many observations and a HurdleGamma likelihood

zweli April 21, 2025, 6:16pm 15

@eklim0407 you mind sharing the pymc code?

Topic		Replies	Views
HurdleGamma diverges, where as a Mixture samples perfectly well v5 modeling	5	219	December 27, 2024
Improving speed with large dimensional problem Questions	12	4080	September 27, 2017
Gaining intuitions for why sampling fails Questions	2	826	December 5, 2019
Sampler occasionally gets static in pymc3.1, but not in pymc3.0 Questions development	19	2271	July 5, 2018
Hierarchical Logistic Regression sampling problems Questions	4	1828	January 18, 2018