Ilona posted on Friday, September 03, 2010 - 11:54 am
I would like to analyze data with these conditions and sample sizes with nonrandom group assignments:
Sample (in a single grade level): Clusters of about 20 students per classroom Clusters of about 4 classrooms per school Clusters of about 5 schools per district =Total of about 400 students per district
There are two similar districts: District 1 gets treatment (400 students) District 2 is control (400 students)
All students in both districts get a pretest and posttest.
Purpose 1: Want to see if growth from pretest to posttest is greater for treatment district than control district overall.
Purpose 2: Want to see if growth from pretest to posttest is greater for treatment district than control district. Wish to examine this effect separately by race of students (Black/White).
And if possible: Wish to examine differences in growth trajectories based on initial pretest score. (I.e., wish to view growth trajectory differences by pretest scores overall, and pretest scores by race.)
------------------------------------ Please advise on best method, plus references to guide me with this.