Hello everybody.
I have a question in the experimental design.
I have a pile of questionnaires given to some secondary schools, to both the teachers and the principals.
The task of interest is to see whether the teachers and the principals answer in a similar fashion. To be more precise, the response is
the principals' answers and the predictor variable is the teachers' answers. So, I would like something like a t-test, but for correlated samples.
The answers are in the Likert scale, i.e. 1-5 (not efficiently at all - very efficiently).
You may leave the list at any time by sending the command
SIGNOFF allstat
to [log in to unmask], leaving the subject line blank.
|