김성훈 (사범대학)

김성훈은 한양대학교 사범대학 교육학과 교수이다.

학력

• 서울대학교 교육학과 학사 및 석사
• 미국 University of Iowa, Educational Measurement & Statistics 전공 박사(PhD)

연구실적

• An extension of four IRT linking methods for mixed-format tests (공저, Journal of Educational Measurement, 43)
• Robustness to format effects of IRT linking methods for mixed-format tests (공저, Applied Measurement in Education, 19)
• A comparative study of IRT fixed parameter calibration methods (단독, Journal of Educational Measurement, 43)
• Testing the difference between two alpha coefficients with small samples of subjects and raters (공저, Educational and Psychological Measurement, 66)
• A method for estimating classification consistency indices for two equated forms (공저, Applied Psychological Measurement, 31)
• Effects on scale linking of different definitions of criterion functions for the IRT characteristic curve methods (공저, Journal of Educational and Behavioral Statistics, 32)
• A comparison of tests for equality of two or more independent alpha coefficients (공저, Journal of Educational Measurement, 45)
• The estimation of the IRT reliability coefficients and its lower and upper bounds, with comparisons to CTT reliability statistics (공저, Asia Pacific Education Review, 11)
• An extension of least squares estimation of IRT linking coefficients for the graded response model (단독, Applied Psychological Measurement, 34)
• A note on the reliability coefficients for item response model-based ability estimates (단독, Psychometrika, 77)
• Generalization of the Lord-Wingersky algorithm to computing the distribution of summed test scores based on real-number item scores (단독, Journal of Educational Measurement, 50)
• Cronbach's coefficient alpha: Well known but poorly understood (공저, Organizational Research Methods, 18)
• Methods for obtaining a common scale under unidimensional IRT models: A technical review and further extensions (공저, Iowa Testing Programs Occasional Paper No. 52)
• A diagnosis on the performance of BILOG-MG's empirical reliability estimators for IRT ability scores (단독, 교육평가연구, 26)
• 유한혼합분포에 대한 EM 알고리듬을 사용한 다집단 IRT 추정 방법의 원리와 기능 (단독, 교육평가연구, 26)