TITLE Critique of the Scoring Construct Validity of Dichotomously Scored Instruments.

This paper makes two criticisms of dichotomously scored instruments. One is that dichotomous scoring restrains the scores to ipsative measures that should not be compared, and the other is that dichotomous scoring ignores the strength with which a subject endorses a response so that the resulting count may imply a different construct measure from that indicated by the sum of rating responses. These criticisms were explored by comparing the reliability and validity of dichotomously scored responses and rating response scores from the Impulsivity Scale (L. Hirschfield, 1965). The concurrent validity of both scoring methods was established by comparison with scores on the Children's Perceived Self-Control Scale (P. Humphrey, 1982). Adolescent ninth graders (n=687) from 14 Jamaican schools were tested and retested with these instruments 2 weeks apart. Results show that rating scores were more reliable in stability and consistency and had greater validity than dichotomous scores. These results give empirical support to the criticisms raised in the paper. (Author/SLD) Reproductions supplied by EDRS are the best that can be made from the original document