Do you think it is allowed to delete items from the further analysis if these items result in a lower measurement of test-retest-reliability?

I would like to discuss the following idea about the assessment of test-retest-reliability: Imagine that we conducted a study (n=100) with 20 items (it1, it2, …, it20) and the questionnaire was...

08 August 2016 4,382 16 View