0
$\begingroup$

"Can i put two binary variables in the between factors part of the repeated measures ANOVA?"

Participants: Patients, Healthy Controls Task: All participants do a task (Pre intervention Score). Then they are randomised to either intervention or control. Then all the participants do the same task (Post intervention Score).

Data: 1) Pre intervention score VS Post intervention score (within as the same people do the task). The form of the score is a mean ranging from 1 to 6 in both cases. 2) Intervention group VS Control group (Binary variable) 3) Patients VS Healthy Controls (Binary variable)

I want to see whether the group that does the intervention ends up with a significantly higher difference (Pre Score, Post Score) compared to the group that does not, the control group. In other words, if the intervention ameliorates the performance in the task. Apart from this, I want to see whether the above applies to both patients and healhty controls or whether there is a differencec between them. Does the intervention work irrespective of the group (patient or healthy controls)? For example, if in the Healthy controls group the ones that did the intervention had a significantly higher difference compared to controls but in the patients group there was no difference between Intevention VS control, it would mean the intervention worked only for the healthy controls but not for the patients.

My thought was to use repeated measures ANOVA as the task is tested to the same people in different times (pre and post intervention). So, Pre Score and Post Score will be put in within factor. Can i use two in between factors? Intervention (binary: Intervention, Control), Participant Group (binary: Patients, Healthy Controls)

Is this possible or do i have to separate the file with select cases (pick only the patients) and include just the pre intervention VS post intervention as within and intervention VS control as between?

Furthermore, if the repeated measures ANOVA is possible, do i need to do a further test to see the differences between each group?

Improve this question
$\endgroup$
0

1 Answer 1

Reset to default
0
$\begingroup$

You can include as many between factors as you wish and they can have as many categories as you like. The same applies to the within factors although you did not ask about them. From your description of the factors I would think you probably want to include the interaction between the two factors as well but without more details about your scientific question I cannot be sure about that.

Improve this answer
$\endgroup$
6
  • $\begingroup$ Thank you for your reply!! I was thinking of puting in within factors: PreScore, Post Score and in between factors: Intervention(Intervention VS Control), Disorder(Patients VS HC). I am not sure about what you mean with the interaction between two factors.. do you mean between Intervention and Disorder? This will come up in the output $\endgroup$
    – Jo Psy
    Aug 4, 2018 at 12:39
  • $\begingroup$ My question is whether the intervention will produce a greater difference between Pre intervention Score and Post intervention Score, compaired to the group that does not receive intervention. Also, if this applies to both patients and healthy controls, or whether there is a difference between them. $\endgroup$
    – Jo Psy
    Aug 4, 2018 at 12:43
  • $\begingroup$ The last phrase "or whether here is ..." is about an interaction. $\endgroup$
    – mdewey
    Aug 4, 2018 at 12:48
  • $\begingroup$ So if i get it right, i will see if there was a difference between patients and healthy controls AND intervention- no intervention from the significance in Intervention*Group. Then, if i want to be more specific, i will have to do a post-hoc test in order to comment on which group has a higher mean? Apart from this, Is there anything i can do if the Levene's test is significant? Does this violate an assumption? If assumptions are violated, are there tests or corrections to do? $\endgroup$
    – Jo Psy
    Aug 4, 2018 at 12:54
  • $\begingroup$ I think you might do better to edit your question to include these as part of your question as comments are not supposed to be for answers to questions. $\endgroup$
    – mdewey
    Aug 4, 2018 at 12:59

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.

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