# Multiple Exposures in MR

**URL:** <https://isgw-forum.colorado.edu/t/multiple-exposures-in-mr/895>\
**Category:** Day 7\
**Created:** [June 11, 2026, 3:46pm UTC](https://isgw-forum.colorado.edu/t/multiple-exposures-in-mr/895 "2026-06-11T15:46:04Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![anonymous](https://isgw-forum.colorado.edu/letter_avatar_proxy/v4/letter/a/8491ac/32.png) [@anonymous](https://isgw-forum.colorado.edu/u/anonymous)\
**Post date:** [June 11, 2026, 3:46pm UTC](https://isgw-forum.colorado.edu/t/multiple-exposures-in-mr/895/1 "2026-06-11T15:46:04Z")

</div>

How is it possible to model 2SMR with multiple traits or outcomes?

> Replying to “How is it possible to model 2SMR with multiple tra…”:

If you want to include multiple exposures you can (under certain assumptions) use multivariable MR. DIfferent outcomes would be different MR analyses

> Replying to “How is it possible to model 2SMR with multiple tra…”:

> **[Multivariable MR - Mendelian randomization dictionary](https://mr-dictionary.mrcieu.ac.uk/term/multivariable/)**

Replying to “How is it possible to model 2SMR with multiple tra…”:

Ok, thanks!

* * *

Is possible to do a MR with more than one exposure?

> Replying to “Is possible to do a MR with more than one exposure…”:

Yes, please see the comments above - about Multivariable MR

* * *

Can we have more than one exposure to an outcome for one IV?

> Replying to “Can we have more than one exposure to an outcome f…”:

ideally, you have an instrument that’s not pleiotropic with any confounders. You can have an IV that’s also associated with some trait that’s on the causal pathway (i.e., a mediator), which you can test with multivariable MR