# Modeling many zeros and low values in a multinomial outcome

**URL:** <https://discourse.mc-stan.org/t/modeling-many-zeros-and-low-values-in-a-multinomial-outcome/29716>\
**Category:** brms\
**Tags:** specification, brms, techniques\
**Created:** [December 6, 2022, 5:50pm UTC](https://discourse.mc-stan.org/t/modeling-many-zeros-and-low-values-in-a-multinomial-outcome/29716 "2022-12-06T17:50:23Z")\
**Posts on this page:** 1\
**Showing post:** 2

<div class="post-metadata">

**Author:** ![jaredv](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.mc-stan.org/jaredv/32/19979_2.png) [@jaredv](https://discourse.mc-stan.org/u/jaredv)\
**Post date:** [December 8, 2022, 5:05pm UTC](https://discourse.mc-stan.org/t/modeling-many-zeros-and-low-values-in-a-multinomial-outcome/29716/2 "2022-12-08T17:05:52Z")

</div>

Update: With hopefully clearer terminology, I think that what I am asking about is how to implement a dirichlet-multinomial model via brms via custom\_family. The same question is asked in [Dirichlet-multinomial custom family in brms](https://discourse.mc-stan.org/t/dirichlet-multinomial-custom-family-in-brms/27590).

---

_[View the full topic](https://discourse.mc-stan.org/t/modeling-many-zeros-and-low-values-in-a-multinomial-outcome/29716)._