# Prior based on sample

**URL:** <https://discourse.pymc.io/t/prior-based-on-sample/8438>\
**Category:** Questions\
**Tags:** prior\
**Created:** [December 11, 2021, 3:47am UTC](https://discourse.pymc.io/t/prior-based-on-sample/8438 "2021-12-11T03:47:17Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![Antonis\_Mav](https://yyz2.discourse-cdn.com/flex036/user_avatar/discourse.pymc.io/antonis_mav/32/3344_2.png) [@Antonis\_Mav](https://discourse.pymc.io/u/Antonis_Mav)\
**Post date:** [December 11, 2021, 3:47am UTC](https://discourse.pymc.io/t/prior-based-on-sample/8438/1 "2021-12-11T03:47:17Z")

</div>

Dear all

In my Bayesian model, I would like to use a prior that is based on a sample.

Could you please explain how to do that in PyMC3?

Thank you in advance.

---

<div class="post-metadata">

**Author:** ![cluhmann](https://yyz2.discourse-cdn.com/flex036/user_avatar/discourse.pymc.io/cluhmann/32/3083_2.png) [@cluhmann](https://discourse.pymc.io/u/cluhmann)\
**Post date:** [December 11, 2021, 4:44am UTC](https://discourse.pymc.io/t/prior-based-on-sample/8438/2 "2021-12-11T04:44:16Z")

</div>

Take a look at [this notebook](https://docs.pymc.io/en/v3/pymc-examples/examples/pymc3_howto/updating_priors.html) and see if that gets you what you want. People smarter than me [have suggested](https://twitter.com/betanalpha/status/1425938076644347904) avoiding intermediate posteriors when possible, so you might consider doing all your updating in a single go.

---

<div class="post-metadata">

**Author:** ![Antonis\_Mav](https://yyz2.discourse-cdn.com/flex036/user_avatar/discourse.pymc.io/antonis_mav/32/3344_2.png) [@Antonis\_Mav](https://discourse.pymc.io/u/Antonis_Mav)\
**Post date:** [December 13, 2021, 6:11pm UTC](https://discourse.pymc.io/t/prior-based-on-sample/8438/3 "2021-12-13T18:11:19Z")

</div>

Thank you very much. Your response was quite helpful!