# Variable selection with ordinal model

**URL:** <https://discourse.mc-stan.org/t/variable-selection-with-ordinal-model/17242>\
**Category:** Modeling\
**Tags:** projpred\
**Created:** [August 5, 2020, 10:36am UTC](https://discourse.mc-stan.org/t/variable-selection-with-ordinal-model/17242 "2020-08-05T10:36:09Z")\
**Posts on this page:** 1\
**Showing post:** 12

<div class="post-metadata">

**Author:** ![fabio](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.mc-stan.org/fabio/32/935_2.png) [@fabio](https://discourse.mc-stan.org/u/fabio)\
**Post date:** [August 5, 2020, 4:33pm UTC](https://discourse.mc-stan.org/t/variable-selection-with-ordinal-model/17242/12 "2020-08-05T16:33:19Z")

</div>

`brms` generated. I am working on this model -more or less successfully - for more than a year. see one of my previous posts [on setting priors](https://discourse.mc-stan.org/t/brms-with-cmdstanr-as-backend-horseshoe-problem/16873)  
I think the problem is not the slow computation: the model as it is struggles to distill the signal that is in the response variable. To improve I need to test various models and various combinations of variables. And this is time-consuming …

---

_[View the full topic](https://discourse.mc-stan.org/t/variable-selection-with-ordinal-model/17242)._