I am trying to define a mixture of bounded random variables e.g. with pm.Model() as model: w = w = pm.Dirichlet("w", a=np.ones(3)) upper_sig = pm.HalfNormal("upper_sig", sigma=0.2) lower_sig = pm.HalfNormal("lower_sig", sigma=0.2) efficiencies = pm.Mixture( "efficiencies",…

I would suggest you use pm.Truncated instead. That way you can also perform prior and posterior predictive sampling with the Mixture model.

Using Bound RV in a Mixture

Questions v5

jahall April 7, 2023, 3:16pm 4

Perfect, I could see Bound was broken for the prior and posterior sampling, but that Censored was broken for sampling! Truncated works as you suggest.

Topic		Replies	Views
Using a bounded variable within a Mixture Questions	8	1862	January 24, 2018
Using a mixture of multivariate normal distributions as a prior Questions	16	1826	March 12, 2019
Add bounds to gaussian unmixture model v5	4	328	December 12, 2023
Mixture of bounded normals as a prior Questions	4	1363	April 27, 2018
Truncated Distributions in Mixture Models? Questions	3	1355	September 20, 2017

Using Bound RV in a Mixture

Related topics