Errors of Measurement and Standard Setting in Mastery Testing
Open Access
- 1 January 1984
- journal article
- research article
- Published by SAGE Publications in Applied Psychological Measurement
- Vol. 8 (1), 107-115
- https://doi.org/10.1177/014662168400800111
Abstract
A number of studies have estimated the dependabil ity of domain-referenced mastery tests for a fixed cut off score. Other studies have estimated the dependa bility of judgments about the cutoff score. Each of these two types of dependability introduces error. Brennan and Lockwood (1980) analyzed the two kinds of errors together but assumed that the two sources of error were uncorrelated. This paper extends that analy sis of the total error in estimates of the difference be tween the domain score and the cutoff score to allow for covariance between the two types of error.Keywords
This publication has 13 references indexed in Scilit:
- A Comparison of the Nedelsky and Angoff Cutting Score Procedures Using Generalizability TheoryApplied Psychological Measurement, 1980
- Agreement Coefficients as Indices of Dependability for Domain-Referenced TestsApplied Psychological Measurement, 1980
- Reliability of multiple classificationsPsychometrika, 1978
- Signal/noise ratios for domain-referenced testsPsychometrika, 1977
- AN INDEX OF DEPENDABILITY FOR MASTERY TESTSJournal of Educational Measurement, 1977
- A Preliminary Investigation of Two Procedures for Setting Examination StandardsEducational and Psychological Measurement, 1976
- Statistical consideration of mastery scoresPsychometrika, 1976
- TOWARD AN INTEGRATION OF THEORY AND METHOD FOR CRITERION‐REFERENCED TESTS1,2Journal of Educational Measurement, 1973
- Passing Scores and Test Lengths for Domain-Referenced MeasuresReview of Educational Research, 1973
- CRITERION‐REFERENCED APPLICATIONS OF CLASSICAL TEST THEORY 1,2Journal of Educational Measurement, 1972