# Genotype x covariate interactions

**URL:** <https://discuss.hail.is/t/genotype-x-covariate-interactions/319>\
**Category:** Help \[0.1\]\
**Created:** [October 12, 2017, 3:10pm UTC](https://discuss.hail.is/t/genotype-x-covariate-interactions/319 "2017-10-12T15:10:12Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Stephane\_Bourgeois](https://avatars.discourse-cdn.com/v4/letter/s/f04885/32.png) [@Stephane\_Bourgeois](https://discuss.hail.is/u/Stephane_Bourgeois)\
**Post date:** [October 12, 2017, 3:10pm UTC](https://discuss.hail.is/t/genotype-x-covariate-interactions/319/1 "2017-10-12T15:10:12Z")

</div>

Hi,

is it possible to use interaction terms ( genotype x covariate ) in the linear and logistic regression?  
Related question, is it possible to extract Beta, SE, L95, U95, P for each covariate (and interaction), as it is the case in Plink?

Thanks,

Steph

---

<div class="post-metadata">

**Author:** ![jbloom](https://yyz2.discourse-cdn.com/flex036/user_avatar/discuss.hail.is/jbloom/32/109_2.png) [@jbloom](https://discuss.hail.is/u/jbloom)\
**Post date:** [October 12, 2017, 3:38pm UTC](https://discuss.hail.is/t/genotype-x-covariate-interactions/319/2 "2017-10-12T15:38:03Z")

</div>

Hi Steph,  
Currently no, but it’s one of our priorities in development (for 0.2) to make regression flexible to include any function of sample annotations and genotype (such as your interaction term), not only the hard call or dosage fields.