# Good link to suggest for non-centering parametrization?

**URL:** <https://discourse.mc-stan.org/t/good-link-to-suggest-for-non-centering-parametrization/21377>\
**Category:** General\
**Tags:** reparametrization\
**Created:** [March 19, 2021, 12:22pm UTC](https://discourse.mc-stan.org/t/good-link-to-suggest-for-non-centering-parametrization/21377 "2021-03-19T12:22:50Z")\
**Posts on this page:** 1\
**Showing post:** 6

<div class="post-metadata">

**Author:** ![jsocolar](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.mc-stan.org/jsocolar/32/2486_2.png) [@jsocolar](https://discourse.mc-stan.org/u/jsocolar)\
**Post date:** [March 20, 2021, 2:39am UTC](https://discourse.mc-stan.org/t/good-link-to-suggest-for-non-centering-parametrization/21377/6 "2021-03-20T02:39:46Z")

</div>

@Funko_Unko yep!

FWIW, I think it would be really useful to put together some kind of simple treatment of hierarchical funnels and non-centering, but crucially it would be great if this treatment could give an intuitive explanation for when and why centering can be preferable (imo it’s intrinsically subtler to grasp the [funnel-shaped likelihood](https://twitter.com/betanalpha/status/1309208265805443072/photo/1) than the funnel-shaped prior).

Also, maybe I’m the only one who’s ever run into the [sticky boundary issue](https://discourse.mc-stan.org/t/offset-multiplier-initialization/20712/4) in an applied setting, but I’d be reluctant to recommend offset/multiplier to people who are first encountering non-centering until it’s solved.

---

_[View the full topic](https://discourse.mc-stan.org/t/good-link-to-suggest-for-non-centering-parametrization/21377)._