# Inverse gamma prior brms

**URL:** <https://discourse.mc-stan.org/t/inverse-gamma-prior-brms/31136>\
**Category:** brms\
**Tags:** priors, specification, brms\
**Created:** [April 20, 2023, 8:14am UTC](https://discourse.mc-stan.org/t/inverse-gamma-prior-brms/31136 "2023-04-20T08:14:30Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Alice1](https://avatars.discourse-cdn.com/v4/letter/a/ecc23a/32.png) [@Alice1](https://discourse.mc-stan.org/u/Alice1)\
**Post date:** [April 20, 2023, 8:14am UTC](https://discourse.mc-stan.org/t/inverse-gamma-prior-brms/31136/1 "2023-04-20T08:14:30Z")

</div>

I would like to use an inverse gamma prior (my data has a lot of zeros so I want to avoid negative variances) but I am not sure how to specify it. This is what I have come up with, and it runs without any errors, does it look correct to any of you?

prior ← set\_prior(“igamma(2, 0.5)”, class = “sigma”)

- Operating System: Ventura 13.3.1
- brms Version: ‘2.19.0’

---

<div class="post-metadata">

**Author:** ![Solomon](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.mc-stan.org/solomon/32/2495_2.png) [@Solomon](https://discourse.mc-stan.org/u/Solomon)\
**Post date:** [April 22, 2023, 5:09am UTC](https://discourse.mc-stan.org/t/inverse-gamma-prior-brms/31136/2 "2023-04-22T05:09:52Z")

</div>

Say you fit the model and name it `my_fit`. You should be able to confirm your priors by executing `my_fit$prior`.