When modeling, for example, random intercepts in a regression, I follow the standard of indexing a vector the length of the number of groups in the variable: data { int<lower = 0> N; int<lower = 0> N_grps; int<lower = 1, upper = N_grps> grp [N]; } parameters { vector [N_grps] mu_grp; } S…

[image] walkerharrison: if I should avoid including unused parameters for other reasons. It’s OK if you have a proper prior (ideally with two finite moments) on the otherwised unused parameters.

Computational cost of unused parameters?

Modeling

mike-lawrence October 16, 2020, 12:23pm 3

Note that a related thread is here, though you’ve asked the question more succinctly!

Topic		Replies	Views
Adding unused variable changes model behaviour (Answered: no bug) Modeling specification	4	849	April 19, 2019
Faster sampling with unused parameters included in model Modeling	3	682	October 28, 2021
Computational Efficiency: advanced techniques? Modeling	1	461	October 4, 2022
Flexibility of opt-in sampling variables Modeling	4	433	November 12, 2019
Number of observations for every parameters Modeling	8	1363	January 27, 2019

Computational cost of unused parameters?

Related topics