Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Bastien Christian <christian.bastien@univ-lorraine.fr> |
To | statalist@hsphsun2.harvard.edu |
Subject | st: Unable to define between-subject basic unit in a mixed design !!! |
Date | Mon, 4 Feb 2013 17:38:16 +0100 |
Dear Colleagues, In a research dedicated to evaluating the errors subjects make in evaluating distances in a real and augmented reality, we used a mixed experimental design with 1 between-subject factor and 3 within-subject factors. The between-subject factor, "Groupe", has two levels (Reel-RA, RA-Reel). It consists in counterbalancing the order of the context the subjects are confronted to (Real-augmented reality, Augmented reality-real). There are three repeated variables, "Phase" (1 and 2), Distance (5 levels) and Repetition (8 levels). Each subject has 80 values recorded (Phase (2) * Distance (5) * Repetition (8) = 80). In other words subjects are submitted to two phases. In each phase they are submitted to 5 distances and for each distance a stimulus is presented 8 times. As I said in one group subjects go through a real than an augmented reality, and the participants of group 2 go through an augmented reality than a real context. The dependent variable is "Errreur_Absolue". I tried this model but got the following error message "could not determine between-subject basic unit; use bseunit() option" ! anova Erreur_Absolue Groupe / Participant|Groupe Phase Groupe#Phase / Phase#Participant|Groupe Distance Groupe#Distance / Distance#Participant|Groupe Repetition Groupe#Repetition / Repetition#Participant|Groupe Phase#Distance Phase#Repetition Distance#Repetition Phase#Distance#Repetition, repeated(Phase Distance Repetition) bse(Participant|Groupe) baseunit(Participant) I just can't figure out what is wrong !!! By the way, how do you do "contrasts" analyses so as to answer the following question : Are the participants' Erreur_Absolue different between real and augmented situations which consists in comparing [(Group1, Phase1) and (Group2, Phase2)] to [(Group2, Phase 1) and (Group1, Phase2)] Thanks a logy for your help, Christian * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/faqs/resources/statalist-faq/ * http://www.ats.ucla.edu/stat/stata/