Published online by Cambridge University Press: 01 January 2025
The tau coefficient is defined, and a computational procedure for tied ranks is described. The procedure maintains continuous computational checks, saves labor, and particularly facilitates the use of tau with large samples. It is also shown how tau correlation may be applied to Q-sorts with any shape of forced distribution or with unforced distributions.
The procedure described was developed in connection with research at the Counseling Center, University of Chicago. The research is supported by a grant (PHS M 903) from the National Institute of Mental Health, of the National Institutes of Health, Public Health Service.