I have an experiment with several factors. Factors are Condition (condition 1, condition 2), Day (1, 2), Session (1,2,3). Each subjects (N=13) undergoes 3 sessions on 2 separate days (6 sessions total). During each session, a subject undergoes condition 1 then condition 2 (or vice versa - it is counterbalanced).

My main interest is to assess if there is a difference between conditions. However, I would like to factor out possible differences between day 1 and 2, and between the different sessions (as there might be some sequence effect).

Which do you think is preferable? A repeated measures with all the factors (condition 1, condition 2), Day (1, 2), Session (1,2,3) OR collapsing sessions and days if they are not different with ANOVA/T-TEST (condition 1, condition 2). By collapsing, I mean either taking the average of the 6 measures for each subject (each of the 13 subject has 2 measures, one for condition 1 and one for condition 2), or using the values in the repeated measures ANOVA (so each of the 13 subjects has 6 sample measures for condition 1 and 6 sample measures for condition 2).

  • 1
    $\begingroup$ Welcome to CV. Unfortunately, this question is unanswerable as is. Either choice could be more powerful. But you should base your choice of model on the questions you want to answer. What are you trying to find out? My blog post how to ask a statistics question may help you formulate your question in a way that can be answered. $\endgroup$ – Peter Flom Aug 25 '18 at 11:52
  • $\begingroup$ I have edited the question $\endgroup$ – user1097111 Aug 26 '18 at 16:29

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.