17 April 2013 3 4K Report

ICC to measure internal consistency of a scale is estimated using two-way ANOVA as I understand. But ANOVA has assumptions of normality of data & uncorrelated errors. Still, I read that ICC can be used for interval categorical data such as Likert scale. But what if my data are skewed (responses have ceiling and floor effect)? Also, most importantly, what do I do with clustering in this case?

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