Possible Duplicate:
Best practice when analysing pre-post treatment-control designs

I'm doing an action research study with 2 of my classes: 1 is the 'treatment' class and the other is the 'control'.

Both classes undertook a pre-test prior to the 'treatment'.

Then, after the 'treatment' stage (the control class didn't receive any 'treatment'), both classes did a post-test.

What statistics should I use? Paired t-tests? ANOVA with repeated measure? Help!


Covariance analysis.
The post-test is your dependent variable.
Class 1 versus class 0 is the independent variable. The pretest is the covariate.

| cite | improve this answer | |

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