A NOTE ON THE RELATIVE SIZES OF THE STANDARD ERRORS OF TWO RELIABILITY ESTIMATES

Authors

  • T. ANNE CLEARY,

    Corresponding author
    1. University of Wisconsin
      CLEARY, T. ANNE. Address: Dept. of Educ. Psychology, Univ. of Wisconsin, Madison 53706. Title: Assistant Professor. Age: 33. Degrees: B.S. Marquette Univ., M.A. Univ. of Minnesota, Ph.D. Univ. of Illinois. Specialization: Psychometric theory.
    Search for more papers by this author
  • ROBERT L. LINN

    Corresponding author
    1. Educational Testing Service
      LINN, ROBERT L. Address: Educational Testing Service, Princeton 08540. Title: Research Psychologist. Age: 30. Degrees: B.A. Univ. of California at Los Angeles, M.A. and Ph.D. Univ. of Illinois. Specialization: Psychometric theory.
    Search for more papers by this author

CLEARY, T. ANNE. Address: Dept. of Educ. Psychology, Univ. of Wisconsin, Madison 53706. Title: Assistant Professor. Age: 33. Degrees: B.S. Marquette Univ., M.A. Univ. of Minnesota, Ph.D. Univ. of Illinois. Specialization: Psychometric theory.

LINN, ROBERT L. Address: Educational Testing Service, Princeton 08540. Title: Research Psychologist. Age: 30. Degrees: B.A. Univ. of California at Los Angeles, M.A. and Ph.D. Univ. of Illinois. Specialization: Psychometric theory.

Abstract

Formulas for the standard error of a parallel-test correlation and for the Kuder-Richardson formula 20 reliability estimate are provided. Given equal values of the two reliabilities in the population, the standard error of the Kuder-Richardson formula 20 is shown to be somewhat smaller than the standard error of a parallel-test correlation for reliability values, sample sizes, and test lengths that are usually encountered in practice.

Ancillary