0
$\begingroup$

This question already has an answer here:

I have 6 Treatment groups (A-F, with A as control) and measure parameter A at four time points 1-4. Now I am particular interested in time*treatment as I want to know if the change over time of the parameter of the groups B-F is significantly different to the control A. However, with a mixed multiple measures ANOVA including all groups (A-F) I only get a general answer: time*treatment is significant or not. Consequently, I did mixed multiple measures ANOVA for each group and the control group (A and B, A and C, A and D etc.).

My question now: Is it appropriate to do seperate analyses? (I am thinking of the issue with multiple t-test and the increase in type 1 error)

Is there another way to calculate the time*treatment significancies for all groups (B-F) to the control within a single analysis?

I am working with SPSS btw. - Thank you already in advance!

EDIT: This is a repeated measures ANOVA with one dependent variable and not a MANOVA where you have multiple independent variables

$\endgroup$

marked as duplicate by kjetil b halvorsen, mdewey, gung, John, mpiktas Nov 23 '16 at 9:30

This question has been asked before and already has an answer. If those answers do not fully address your question, please ask a new question.

0
$\begingroup$

After a meeting with a biostatistics Professor I can say: It is appropriate to do this and there is no possibility to calculate significancies for all groups in a single analysis.

In fact you can discuss the significancies only based on profil plots and individual analyses of the respective group combinations which are the most interesting for you

$\endgroup$

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