{"title":"系数β作为多元计分测验中总和分数和标度分数的KR-21信度扩展","authors":"Rashid S. Almehrizi","doi":"10.1080/08957347.2021.1890740","DOIUrl":null,"url":null,"abstract":"ABSTRACT KR-21 reliability and its extension (coefficient α) gives the reliability estimate of test scores under the assumption of tau-equivalent forms. KR-21 reliability gives the reliability estimate for summed scores for dichotomous items when items are randomly sampled from an infinite pool of similar items (randomly parallel forms). The article extends KR-21 to coefficient to estimate reliability of summed scores for test with any item scoring pattern under the same assumption of KR-21. Also, the article presents coefficient to estimate this reliability for nonlinearly scaled scores for any type of items. The article shows that coefficient is slightly different from the classical index of reliability. Results show that coefficient is not equal to the classical index of reliability for summed scores and scaled scores. Moreover, results using real data on psychological instruments reveal that different score scales yield different coefficient reliability estimates that are less than coefficient Gα by a function related to form-to-form differences in averages.","PeriodicalId":51609,"journal":{"name":"Applied Measurement in Education","volume":"34 1","pages":"139 - 149"},"PeriodicalIF":1.1000,"publicationDate":"2021-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Coefficient β As Extension of KR-21 Reliability for Summed and Scaled Scores for Polytomously-scored Tests\",\"authors\":\"Rashid S. Almehrizi\",\"doi\":\"10.1080/08957347.2021.1890740\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"ABSTRACT KR-21 reliability and its extension (coefficient α) gives the reliability estimate of test scores under the assumption of tau-equivalent forms. KR-21 reliability gives the reliability estimate for summed scores for dichotomous items when items are randomly sampled from an infinite pool of similar items (randomly parallel forms). The article extends KR-21 to coefficient to estimate reliability of summed scores for test with any item scoring pattern under the same assumption of KR-21. Also, the article presents coefficient to estimate this reliability for nonlinearly scaled scores for any type of items. The article shows that coefficient is slightly different from the classical index of reliability. Results show that coefficient is not equal to the classical index of reliability for summed scores and scaled scores. Moreover, results using real data on psychological instruments reveal that different score scales yield different coefficient reliability estimates that are less than coefficient Gα by a function related to form-to-form differences in averages.\",\"PeriodicalId\":51609,\"journal\":{\"name\":\"Applied Measurement in Education\",\"volume\":\"34 1\",\"pages\":\"139 - 149\"},\"PeriodicalIF\":1.1000,\"publicationDate\":\"2021-04-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Applied Measurement in Education\",\"FirstCategoryId\":\"95\",\"ListUrlMain\":\"https://doi.org/10.1080/08957347.2021.1890740\",\"RegionNum\":4,\"RegionCategory\":\"教育学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"EDUCATION & EDUCATIONAL RESEARCH\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Applied Measurement in Education","FirstCategoryId":"95","ListUrlMain":"https://doi.org/10.1080/08957347.2021.1890740","RegionNum":4,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"EDUCATION & EDUCATIONAL RESEARCH","Score":null,"Total":0}
Coefficient β As Extension of KR-21 Reliability for Summed and Scaled Scores for Polytomously-scored Tests
ABSTRACT KR-21 reliability and its extension (coefficient α) gives the reliability estimate of test scores under the assumption of tau-equivalent forms. KR-21 reliability gives the reliability estimate for summed scores for dichotomous items when items are randomly sampled from an infinite pool of similar items (randomly parallel forms). The article extends KR-21 to coefficient to estimate reliability of summed scores for test with any item scoring pattern under the same assumption of KR-21. Also, the article presents coefficient to estimate this reliability for nonlinearly scaled scores for any type of items. The article shows that coefficient is slightly different from the classical index of reliability. Results show that coefficient is not equal to the classical index of reliability for summed scores and scaled scores. Moreover, results using real data on psychological instruments reveal that different score scales yield different coefficient reliability estimates that are less than coefficient Gα by a function related to form-to-form differences in averages.
期刊介绍:
Because interaction between the domains of research and application is critical to the evaluation and improvement of new educational measurement practices, Applied Measurement in Education" prime objective is to improve communication between academicians and practitioners. To help bridge the gap between theory and practice, articles in this journal describe original research studies, innovative strategies for solving educational measurement problems, and integrative reviews of current approaches to contemporary measurement issues. Peer Review Policy: All review papers in this journal have undergone editorial screening and peer review.