IRT-Estimated Reliability for Tests Containing Mixed Item Formats

被引：4

作者：

Shu, Lianghua ^{[1
]}

Schwarz, Richard D. ^{[2
]}

机构：

[1] CTB McGraw Hill, Res Dept, Monterey, CA 93940 USA

[2] Educ Testing Serv, Princeton, NJ 08541 USA

来源：

JOURNAL OF EDUCATIONAL MEASUREMENT | 2014年 / 51卷 / 02期

关键词：

PARAMETER-ESTIMATION; COEFFICIENT; MODEL;

D O I：

10.1111/jedm.12040

中图分类号：

G44 [教育心理学];

学科分类号：

0402 ; 040202 ;

摘要：

As a global measure of precision, item response theory (IRT) estimated reliability is derived for four coefficients (Cronbach's , Feldt-Raju, stratified , and marginal reliability). Models with different underlying assumptions concerning test-part similarity are discussed. A detailed computational example is presented for the targeted coefficients. A comparison of the IRT model-derived coefficients is made and the impact of varying ability distributions is evaluated. The advantages of IRT-derived reliability coefficients for problems such as automated test form assembly and vertical scaling are discussed.

引用

页码：163 / 177

页数：15

共 39 条

[1]

[Anonymous], 1972, The dependability of behavioural measurements: Theory of generalizability for scores and profiles

[2]

[Anonymous], 2012, Applications of item response theory to practical testing problems

[3]

[Anonymous], 1999, Measurement essentials

[4] The information in multiple ratings [J].