22 April 2013 1 744 Report

I have a question regarding the rel estimate you used. You refer to Raykov's composite scale reliability coeff but from what I could find his coefficient is only applied to two-level data with continuous outcomes. Or have I misunderstood it? The reason I am asking is that I am searching myself for a reliability estimate that would be appropriate to use with clustered categorical data (responses on 4-point Likert scale). I would be very grateful to you if you could share with me your ideas. I've looked through MPlus discussion board but haven't found my answer there.

Article The Safety Attitudes Questionnaire: Psychometric Properties,...

More Elina Dale's questions See All
Similar questions and discussions