Thanks for the suggestions. Unfortunately I don't have any other data to
do propensity matching. It turns out for many of the forms student
initials were written on the back. Using these I'm able to match 2/3 of
the sample (roughly 21 out of 30 kids). Now I'm not sure if I'm better off
using the dependent test with the 21 kids or independent with 30 kids? I
know that the dependent test has more power but I'm concerned about losing
1/3 of the sample.
Thanks,
Arlin
Arlin Cuncic, M.A.
Research and Assessment Associate
Research and Assessment Department
Thames Valley District School Board
1250 Dundas St.
London, ON N5W 5P2
519-452-2000 ext. 20115
[hidden email]
Locked
