A number of different reliability coefficients have recently been proposed for tests used to differentiate between groups such as masters and nonmasters. One promising index is the proportion of students in a class that are consistently assigned to the same mastery group across two testings. The present paper proposes a single test administration…

A free-response method of data collection (questionnaires), in conjunction with nonmetric multidimensional scaling, produced results highly similar to those of a previous study, i.e., that an effective college teacher could be characterized in terms of "research,""teaching," and "service to the university." (Author/RC)

Four different methods for estimating the proportions of testees properly classified as having mastered or not mastered test content are examined, using data from the Scholastic Aptitude Test. All four methods prove reasonably accurate and all show some bias under certain conditions. (JKS)

Measurement error in dependent variables reduces the power of statistical tests to detect mean differences of specified magnitude. Procedures for determining power and sample size that consider the reliability of the dependent variable are discussed and illustrated. Methods for estimating reliability coefficients used in these procedures are…

A nonmetric multidimensional analysis is used to identify the subscale structure of a creativity inventory. The instrument used assesses attitudes, interests, motivations, values, and other personality and biographical matters which characterize creative individuals. (Author)

Current methods for obtaining reliability indices for mastery tests can be laborious. This paper offers practitioners tables from which agreement and kappa coefficients can be read directly and provides criterion for acceptable values of agreement and kappa coefficients. (TJH)

Biased test items were intentionally imbedded within a test and administered to large samples of Black and White college students. Three item bias detection methods (the three-parameter item characteristic curve procedure, the chi-square method, and the transformed item difficulty approach) were applied to the data. (Author/PN)

Huynh (1976) suggested a method of approximating the reliability coefficient of a mastery test. The present study examines the accuracy of Huynh's approximation and also describes a computationally simpler approximation which appears to be generally more accurate than the former. (Author/RL)

Test data from two diverse culture groups were analyzed to determine the agreement among four methods of detecting item bias (transformed difficulty, discrimination differences, chi-square, and item characteristic curve). The test battery contained 155 items from six subtests: vocabulary, reading comprehension, mathematics, letter groups,…