Tell me more ×
Mathematica Stack Exchange is a question and answer site for users of Mathematica. It's 100% free, no registration required.
up vote 11 down vote favorite
2

Repeated measures designs or "Within-Subjects" designs are very important in live sciences and social sciences. Unfortunately, Mathematica's ANOVA package is not able to analyze those designs. It only handles "Between-Subjects" type of analyses.

During my whole research career I haven't been able to use Mathematica to analyze most of the studies I performed, which really is a pity.

In an e-mail exchange I had with WRI's Andy Ross in the beginning of this year he confirmed that I wasn't overlooking built-in functionality.

The question is: is any one aware of third party packages that handle these types of ANOVAs?

share|improve this question
1  
I don't mean to sound like a jerk, but if you had your "whole research career" to build some tools for this in Mathematica why didn't you? Is the algorithm behind it that prohibitive? – Mr.Wizard♦ Jul 1 '12 at 6:32
1  
@Mr.Wizard have you read the linked article? It's sufficiently complex and error-prone that I preferred to use the other tools that I had readily available (Statistica in my case) instead of trying to come up with something myself. – Sjoerd C. de Vries Jul 1 '12 at 6:58
Okay, just asking. It went over my head but that didn't surprise me. I guess it really is complex. :^) – Mr.Wizard♦ Jul 1 '12 at 7:00

1 Answer

up vote 10 down vote accepted

Well, it's typical that just when you don't need it anymore (as I switched to a totally different discipline) the required functionality pops-up. I found that Vol. 13 (2011) of The Mathematica Journal contains an article about these types of designs, Computing Mixed-Design (Split-Plot) ANOVA. I thought it good to post it here, as I know many people would love to have this.

share|improve this answer

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.