# Convert Output from categorical model to Odds ratio

**URL:** <https://discourse.mc-stan.org/t/convert-output-from-categorical-model-to-odds-ratio/22896>\
**Category:** General\
**Tags:** interpret-results, techniques, specification, brms\
**Created:** [June 7, 2021, 5:13pm UTC](https://discourse.mc-stan.org/t/convert-output-from-categorical-model-to-odds-ratio/22896 "2021-06-07T17:13:19Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![GabriellaS-K](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.mc-stan.org/gabriellas-k/32/11510_2.png) [@GabriellaS-K](https://discourse.mc-stan.org/u/GabriellaS-K)\
**Post date:** [June 7, 2021, 5:13pm UTC](https://discourse.mc-stan.org/t/convert-output-from-categorical-model-to-odds-ratio/22896/1 "2021-06-07T17:13:19Z")

</div>

Hi,

I have the output of a model, which is categorical (Family: acat model, Links: mu = cloglog)

Is there a way to convert this to odds ratios to report it?  
Thank you so much

---

<div class="post-metadata">

**Author:** ![andrjohns](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.mc-stan.org/andrjohns/32/15297_2.png) [@andrjohns](https://discourse.mc-stan.org/u/andrjohns)\
**Post date:** [June 8, 2021, 4:46am UTC](https://discourse.mc-stan.org/t/convert-output-from-categorical-model-to-odds-ratio/22896/2 "2021-06-08T04:46:57Z")

</div>

Hi Gabriella,

Odds ratios are transformations of logits, so you would need to re-estimate your model with the `logit` link. Then you can exponentiate the coefficients to give odds ratios