# design.file for statistical analysis

**URL:** <https://forum.mothur.org/t/design-file-for-statistical-analysis/2944>\
**Category:** Commands in mothur\
**Created:** [August 8, 2016, 7:46am UTC](https://forum.mothur.org/t/design-file-for-statistical-analysis/2944 "2016-08-08T07:46:07Z")\
**Posts on this page:** 5\
**Page:** 1

<div class="post-metadata">

**Author:** ![kristinvh](https://avatars.discourse-cdn.com/v4/letter/k/d07c76/32.png) [@kristinvh](https://forum.mothur.org/u/kristinvh)\
**Post date:** [August 8, 2016, 7:46am UTC](https://forum.mothur.org/t/design-file-for-statistical-analysis/2944/1 "2016-08-08T07:46:07Z")

</div>

Hello

I am using mothur for my 16S rRNA data. I have several groups I want to compare statistically, however, the “mouse.time.design” in MiSeq SOP only compare two groups (Early vs. Late). I have tried to add more groups, but it does not work. It must be possible to add more than 2 groups in the design.file? It would be very helpful to see an example of a design.file in which several groups are included.

Thank you very much!

---

<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:** [August 9, 2016, 10:29am UTC](https://forum.mothur.org/t/design-file-for-statistical-analysis/2944/2 "2016-08-09T10:29:24Z")

</div>

You would change the “Early” and “Late” to the names of the groups you are interested in. Can you post your design file and the error you are getting?

Pat

---

<div class="post-metadata">

**Author:** ![kristinvh](https://avatars.discourse-cdn.com/v4/letter/k/d07c76/32.png) [@kristinvh](https://forum.mothur.org/u/kristinvh)\
**Post date:** [August 9, 2016, 2:42pm UTC](https://forum.mothur.org/t/design-file-for-statistical-analysis/2944/3 "2016-08-09T14:42:26Z")

</div>

Great, thank you! It works fine when the groups are the same in both of these files “design.file” and “stability.an.thetayc.0.03.lt.ave.tre”. However, if I only want to include a subset of the groups from the file “stability.an.thtay…”, should I choose another size here: mothur \> sub.sample(shared=stability.an.shared, size=2241), or should I make another “stability.file” and run all the steps from the beginning?

It is perhaps a way of specifying the groups to be used from the file “stability.an…” when I use this command:  
parsimony(tree=stability.an.thetayc.0.03.lt.ave.tre, group=mouse.time.design, groups=all)? I tried to specify the groups in groups=cDNA10-cDNA11-cDNA12-cDNA13, but this does not work.

my design file is shown here:  
group sample\_type  
cDNA10 mucosa\_active\_bacteria  
cDNA11 mucosa\_active\_bacteria  
cDNA12 mucosa\_active\_bacteria  
cDNA13 mucosa\_active\_bacteria  
cDNA14 mucosa\_active\_bacteria  
cDNA15 mucosa\_active\_bacteria  
cDNA16 mucosa\_active\_bacteria  
cDNA17 mucosa\_active\_bacteria  
cDNA18 mucosa\_active\_bacteria  
cDNA19 mucosa\_active\_bacteria  
cDNA1 mucosa\_active\_bacteria  
cDNA20 mucosa\_active\_bacteria  
cDNA21 mucosa\_active\_bacteria  
cDNA22 mucosa\_active\_bacteria  
cDNA23 mucosa\_active\_bacteria  
cDNA24 mucosa\_active\_bacteria  
cDNA25 mucosa\_active\_bacteria  
cDNA27 mucosa\_active\_bacteria  
cDNA2 mucosa\_active\_bacteria  
cDNA42 mucosa\_active\_bacteria  
cDNA5 mucosa\_active\_bacteria  
cDNA6 mucosa\_active\_bacteria  
cDNA7 mucosa\_active\_bacteria  
cDNA8 mucosa\_active\_bacteria  
fDNA10 faeces  
fDNA11 faeces  
fDNA12 faeces  
fDNA13 faeces  
fDNA14 faeces  
fDNA15 faeces  
fDNA16 faeces  
fDNA17 faeces  
fDNA18 faeces  
fDNA19 faeces  
fDNA1 faeces  
fDNA20 faeces  
fDNA21 faeces  
fDNA22 faeces  
fDNA23 faeces  
fDNA24 faeces  
fDNA25 faeces  
fDNA26 faeces  
fDNA27 faeces  
fDNA28 faeces  
fDNA29 faeces  
fDNA2 faeces  
fDNA30 faeces  
fDNA31 faeces  
fDNA3 faeces  
fDNA4 faeces  
fDNA5 faeces  
fDNA6 faeces  
fDNA7 faeces  
fDNA8 faeces  
fDNA9 faeces  
mDNA10 mucosa  
mDNA11 mucosa  
mDNA12 mucosa  
mDNA13 mucosa  
mDNA14 mucosa  
mDNA15 mucosa  
mDNA16 mucosa  
mDNA17 mucosa  
mDNA18 mucosa  
mDNA19 mucosa  
mDNA1 mucosa  
mDNA20 mucosa  
mDNA21 mucosa  
mDNA22 mucosa  
mDNA23 mucosa  
mDNA24 mucosa  
mDNA25 mucosa  
mDNA27 mucosa  
mDNA2 mucosa  
mDNA42 mucosa  
mDNA5 mucosa  
mDNA6 mucosa  
mDNA7 mucosa  
mDNA8 mucosa

Thank you 🙂

---

<div class="post-metadata">

**Author:** ![westcott](https://yyz2.discourse-cdn.com/flex036/user_avatar/forum.mothur.org/westcott/32/18_2.png) [@westcott](https://forum.mothur.org/u/westcott)\
**Post date:** [August 11, 2016, 4:19pm UTC](https://forum.mothur.org/t/design-file-for-statistical-analysis/2944/4 "2016-08-11T16:19:52Z")

</div>

The groups parameter in the parsimony command is used to select items from the second column of the group or design file. If you would like to select of remove groups from your files you can uses the get.groups and remove.groups commands. [http://www.mothur.org/wiki/Get.groups](http://www.mothur.org/wiki/Get.groups)[http://www.mothur.org/wiki/Remove.groups](http://www.mothur.org/wiki/Remove.groups)

---

<div class="post-metadata">

**Author:** ![kristinvh](https://avatars.discourse-cdn.com/v4/letter/k/d07c76/32.png) [@kristinvh](https://forum.mothur.org/u/kristinvh)\
**Post date:** [August 12, 2016, 3:48pm UTC](https://forum.mothur.org/t/design-file-for-statistical-analysis/2944/5 "2016-08-12T15:48:43Z")

</div>

Great, that was very helpful, thank you very much 🙂
