# Paired tests

**URL:** <https://forum.mothur.org/t/paired-tests/3327>\
**Category:** Feature requests\
**Created:** [July 12, 2017, 6:58pm UTC](https://forum.mothur.org/t/paired-tests/3327 "2017-07-12T18:58:45Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Alex\_Thibodeau](https://avatars.discourse-cdn.com/v4/letter/a/e9a140/32.png) [@Alex\_Thibodeau](https://forum.mothur.org/u/Alex_Thibodeau)\
**Post date:** [July 12, 2017, 6:58pm UTC](https://forum.mothur.org/t/paired-tests/3327/1 "2017-07-12T18:58:45Z")

</div>

Statistical tests to use when samples are paired would be awesome.

Unless they are already implemented and I missed them but I beleive that AMOVA, HOMOVA, lefse, indicator and so on should not be used on paired samples. Or I am wrong?

---

<div class="post-metadata">

**Author:** ![pschloss](https://yyz2.discourse-cdn.com/flex036/user_avatar/forum.mothur.org/pschloss/32/4_2.png) [@pschloss](https://forum.mothur.org/u/pschloss)\
**Post date:** [July 13, 2017, 11:31am UTC](https://forum.mothur.org/t/paired-tests/3327/2 "2017-07-13T11:31:11Z")

</div>

That’s correct - you’d need to do this in something like R where you would compare the distances between paired samples for two or more groups.

Pat