I'm currently looking at a 2x2 Repeated Measure Anova for an undergrad project but I'm struggling to find information about which means to report.

I will be reporting the Within-Subjects Anova,the Interaction and the Between Subjects Anova.

I have a Profile Plot to show the Estimated Marginal Means of Measure1 which I will be using to show that there is no interaction between the two.

However - I'm am struggling to find information regarding the reporting of means.

I have a table of descriptive with the Mean and SD. Then towards the end of the SPSS output I have a section with Estimated Marginal Means.

Which of these would I report and how would they be reported? Would this before or after details of the Anova are reported?

Any help appreciated as I have been sat here for hours struggling with this.


I'm a bit confused by your question, but as you are planning on reporting both within- and between-subjects effects, I assume you are actually conducting a mixed-design ANOVA.

Regardless, the tables of descriptives are what you probably want to report; the estimated marginal means are the means controlling for covariates (i.e., the mean of X when Y is held constant at its mean value). How you report these depends on how many descriptives you have to report; I would report the means and standard deviations in text if there are only a few of them, and in a table if there are many.

  • $\begingroup$ Sorry I should have been clearer - Yes it is a mixed design Anova. I have conducted two initial Multivariate Anovas to run comparisons of my conditions to look at differences in responses. The mixed Anova mentioned above is to see if there are any interactions between responses to the questionnaire. So would I only report the Means and SD given in the Descriptives output? I imagine as the Estimated Marginal Means are shown by the profile plot (i.e. showing that there is no interaction), that this data does not need to be replicated in table form? $\endgroup$ – S Sam Mar 26 '12 at 12:27
  • $\begingroup$ Also - Would the details of the Means and SD be reported after the Anova's have been reported, or prior to reporting them? $\endgroup$ – S Sam Mar 26 '12 at 12:33
  • 1
    $\begingroup$ Yes, normally only the raw means and standard deviations are reported as descriptive statistics. The question of when/where to report them is stylistic; I personally would report the significance of the effect, then describe the pattern of the effect by referring to the cell means (or in the case of a nonsignificant interaction, just state that the Ms and SDs are displayed in Table X). $\endgroup$ – Jehu Mar 26 '12 at 17:56
  • $\begingroup$ Thanks - That is a great help. I've been struggling to find textbooks that give a simple explanation so that makes it a lot easier :) $\endgroup$ – user10156 Mar 27 '12 at 13:49

Your Answer

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

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