I am not sure how the results of this study should be analysed given its design. I have searched everywhere for this info on this TYPE of experimental design and have had no luck. I don't even know what it is called so I'm hoping someone can shed some light.
It's a nested repeated measures design. The aim is to measure the effect of a treatment on an outcome variable.
So, There is one DV, measured at 3 time periods, across 3 groups: Group 1, group 2, and a control group. All subjects were randomly sampled into those groups from a larger random sample of the population. So there are no systematic character differences between subjects of all three groups. There is a difference between Groups 1 and Group 2, which is when the were given the treatment.
There is one treatment, issued in the following way to the groups:
At time1, The outcome variable is measured for all three groups, no treatment given.
[between time1 and time2, group1 is given the treatment.]
At time2, the outcome variable is measured for all three groups.
[between time2 and time3, group 2 is given the treatment.]
At time3, the outcome variable is measured for all groups.
Just for the record, all subjects are nested within a higher cluster in case it should affect the answer.
I guess my question is how can/should this type of design for the TIME factor be dealt with in analysis to show whether the treatment had an effect?
Currently a mixed model is being used with time as a factor.