# ANOVA question (calculating SS s/a or MS s/a without individual observations)

**URL:** <https://boards.straightdope.com/t/anova-question-calculating-ss-s-a-or-ms-s-a-without-individual-observations/511185>\
**Category:** Factual Questions\
**Created:** [September 23, 2009, 2:07am UTC](https://boards.straightdope.com/t/anova-question-calculating-ss-s-a-or-ms-s-a-without-individual-observations/511185 "2009-09-23T02:07:35Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![Cagey\_Drifter](https://avatars.discourse-cdn.com/v4/letter/c/b2d939/32.png) [@Cagey\_Drifter](https://boards.straightdope.com/u/Cagey_Drifter)\
**Post date:** [September 23, 2009, 2:07am UTC](https://boards.straightdope.com/t/anova-question-calculating-ss-s-a-or-ms-s-a-without-individual-observations/511185/1 "2009-09-23T02:07:35Z")

</div>

In an ANOVA analysis, how can I calculate SS s/a or MS s/a without having individual observations, and only having a mean score (and no standard deviation) for each group?

Background: I mentioned last week in a thread about something else that I was looking at a problem in an experimental design book in which certain calculations were made that I could not understand how they were done because individual observations was missing. This is not homework, by the way. I’m trying to understand how the book is able to arrive at answers without what appears to be vital information.

---

<div class="post-metadata">

**Author:** ![Cagey\_Drifter](https://avatars.discourse-cdn.com/v4/letter/c/b2d939/32.png) [@Cagey\_Drifter](https://boards.straightdope.com/u/Cagey_Drifter)\
**Post date:** [September 23, 2009, 2:45am UTC](https://boards.straightdope.com/t/anova-question-calculating-ss-s-a-or-ms-s-a-without-individual-observations/511185/2 "2009-09-23T02:45:49Z")

</div>

sorry, I made an error: there are standard deviations.

---

<div class="post-metadata">

**Author:** ![ultrafilter](https://avatars.discourse-cdn.com/v4/letter/u/3d9bf3/32.png) [@ultrafilter](https://boards.straightdope.com/u/ultrafilter)\
**Post date:** [September 23, 2009, 2:38pm UTC](https://boards.straightdope.com/t/anova-question-calculating-ss-s-a-or-ms-s-a-without-individual-observations/511185/3 "2009-09-23T14:38:00Z")

</div>

Perhaps they had the individual observations, but were only reporting the summary statistics.

---

<div class="post-metadata">

**Author:** ![muttrox](https://avatars.discourse-cdn.com/v4/letter/m/a8b319/32.png) [@muttrox](https://boards.straightdope.com/u/muttrox)\
**Post date:** [September 23, 2009, 3:19pm UTC](https://boards.straightdope.com/t/anova-question-calculating-ss-s-a-or-ms-s-a-without-individual-observations/511185/4 "2009-09-23T15:19:18Z")

</div>

I don’t think it is possible to do those calculations without individual observations. I think ultrafilter has the right answer.