I am conducting an experiment where participants are randomly assigned to one of 2 training groups.

Participants are tested on 6 intelligence questionnaires,whereby they are scored on a points system. 3/6 will be related broadly to each on of the training techniques. They are then assigned to 1 of the 2 training groups, and retested a week later.

However, as I have been out of college for some time I am struggling to figure out whether I should be using and anova or ancova or what ?

The aim of the experiment is to find out whether test scores can be improved through training.

Please help.

Thank you in advance.

EDIT I would also be interested to see if age or gender affect performance improvements


1 Answer 1


Since you are testing the same people more than once, your data is not going to be independent. This violates the assumptions of both ANOVA and ANCOVA. I recommend a multilevel model. Since you are evidently a novice at statistics, I also recommend hiring someone to do this for you.

  • $\begingroup$ Hi, Thank you, I can;t hire somebody, this is just for an assignment. I am a novice but just need to know analysis type then I will have no problem executing it on SPSS $\endgroup$
    – SlipSkip
    Aug 8, 2017 at 14:45

Your Answer

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

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