I'm calculating the Cronbach's alpha on a dataset with the scores of the Coping Orientations to the Problems Experienced (COPE-NVI-25) with the R package psych. I used the following code:

alpha(data[, 73:97])

But got this error:

Some items ( COPE.5 COPE.19 COPE.22 ) were negatively correlated with the total scale and probably should be reversed.

The items have already been correctly reversed when necessary, so I suppose that I have to identify and exclude some careless responders. How I can do that?

  • $\begingroup$ Two questions: (1) ¿how big is your data set? and (2) ¿are you making an attempt to distinguish between careless and disingenuous responders? $\endgroup$
    – Gregg H
    Commented May 1, 2021 at 17:18
  • $\begingroup$ 799 people answered the questionnaire. From this initial sample 386 responses were excluded because incomplete or invalid. I would like to identify those responses that cause the items to correlate negatively and exclude them. So both careless and disingenuos if possible... $\endgroup$
    – Gianluca78
    Commented May 2, 2021 at 7:54


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.