I am trying to fit a model of the form: for(i in 1:N) X[i] ~ multinomial(theta); theta ~ dirichlet(exp(alpha)); alpha ~ normal(0,1); where alpha is a univariate parameter. Unsurprisingly, this model – being non-centred – suffers from divergent iterations. These do not go away if I increase adap…

Non-centred parameterisation for Dirichlet distribution

aaronjg June 14, 2018, 2:41am 10

Check out this thread - it’s on sum to zero constraints, but may be relevant for the sum to 1 constraint.

Topic		Replies	Views
Non-centered parametrisation for hierarchical log_mix (mixed) distribution Modeling rstan , techniques	4	946	February 21, 2022
Trying to generalise the dirichlet-multinomial (non-analytical) framework (replacing Dirichlet with other distributions) Modeling techniques , bioinformatics , dirichlet-multinomial	23	2599	November 5, 2018
Centred vs. non-centred parametrisation with lognormal likelihood Modeling fitting-issues	15	1979	April 4, 2020
Poisson Hierarchical Model Centered/Non-centered Parameterization Modeling	7	1273	January 6, 2022
Poisson Hierarchical Model Non-centered Parametrization Modeling	3	735	January 12, 2022