Some aspects of test reliability are discussed. Topics covered are: (1) how high should a reliability coefficient be?; (2) two factors affecting the interpretation of reliability coefficients--range of talent and interval between testings; (3) some common misconceptions--reliability of speed tests, part vs. total reliability, reliability for what…

Issues related to the evaluation of instructional programs developed under the auspices of the Southwest Educational Development Laboratory are briefly discussed. The Laboratory develops criterion-referenced tests which form an integral part of each instructional program. The importance of examining the reliability and validity of these tests is…

Concern over the reading and writing programs in Vancouver, British Columbia Schools culminated in the establishment in June 1974 of a Task Force on English. In response to the request from the Task Force for a survey of the writing ability of Grade 11 students, a committee of English Department Heads assisted in developing an instrument and the…

Illustrates a multivariate approach to item analysis. Previous formulation is extended by investigating techniques simultaneously taking into account scale variance with the goal of reducing the average correlation between scales. Study examines problems in determining optimum values for combinations of item parameters selected for personality…

A computer program for item evaluation, reliability estimation, and test scoring is described. The program contains a variable format procedure allowing flexible input of responses. Achievement tests and affective scales may be analyzed. (Author)

Variance components from split-plot factorial design (SPF) were used to estimate reliability for schools and persons within schools. Reliability for persons within SPF and randomized block design (RB) schools were compared and reliability for SPF and RB design schools were compared. (Author/BJG)

Reliability and validity data are reported for a questionnaire measure of individual differences in dominance-submissiveness. The 48-item questionnaire, which was balanced for response bias, had high internal consistency and correlated highly with other available measure of dominance. (Author/JKS)

The use of Cohen's kappa index as a measure of the reliability of multiple classifications is developed. Special cases of the index as well as the effects of test length on the index are also explored. (JKS)

Cites evidence showing that the "natural order" found using the Bilingual Syntax Measure to measure morpheme order is not an artifact of the test. (Author/AM)

A modification of Hoyt's analysis of variance model for test analysis was proposed by Lu. A difficulty that may be encountered in using Lu's modification is examined, and a solution is proposed. (JKS)

Ordinal measurement is the rank ordering of individuals in a population. For ordinal measurement, the concept of an individual propensity distribution is his or her true score. Estimation of, as well as other aspects of the distribution, are discussed. (Author/JKS)

The usual formulas for the reliability of differences between two test scores are based on the assumption that the error scores are uncorrelated. Formulas are presented for the general case where this assumption is unnecessary. (Author/JKS)

Finding and interpreting lower bounds for reliability coefficients for tests with nonhomogenous items has been a problem for psychometricians. This paper presents a mathematical formula for finding the greatest lower bound for such a coefficient. (Author/JKS)

A method to improve personality inventory validity by presenting positively keyed items from a single trait in descending order of endorsement and encouraging subjects to respond in terms of the resulting Guttman scale is presented. Experimental results show increases in reliability and validity. (Author/JKS)

The Personal Attribute Inventory was compared to the Adjective Check List as a measure of self concept on a sample of college students. The Personal Attribute Inventory showed strong correlation to two subscales of the Adjective Check List, and more stability over time. (JKS)