I’m trying to implement a polytomous latent class model: (x[i, j] | Theta[i] = c, Pi[j] ~ Categorical(Pi[c,j]) for i = 1, 2, . . ., n and j = 1, 2, …, J Theta[i] | Gamma ~ Categorical(Gamma) for i = 1, 2, . . ., n Gamma ~ Dirichlet(Alpha[Gamma]) Pi[c,j] ~ Dirichlet(Alpha[Pi[c]]) for c = 1, 2, …,…

Thank you very much for the reply.

Latent Class Analysis Model (Dirichlet / Categorical Implementation Question)

junpenglao February 2, 2019, 11:02pm 2

You might find this post helpful: Naive Bayes model with PyMC3

Topic		Replies	Views
Dirichlet and Categorical Questions	2	624	October 26, 2020
Multivariate categorical with different probabilities Questions	5	1905	April 9, 2019
Dynamic number of Dirichlet distributions? Questions	3	629	February 25, 2018
Multivariate categorical with observed data	9	1505	April 26, 2023
Shape issues when creating Dirichlet mixtures Questions	0	440	August 19, 2021