Addresses generalizability theory (GT), which offers a flexible framework for assessing dependability of measurement. GT allows for consideration of multiple sources of error, allowing investigators to assess the overall impact of measurement error. Illustrative analyses demonstrate the special advantages of GT for planning studies in which…

Discusses statistical procedures for increasing test unreliability due to guessing in multiple choice and true/false tests. Proposes two new measures of test unreliability: one concerned with resolution of defined levels of knowledge and the other with the probability of examinees being incorrectly ranked. Both models are based on the binomial…

ACT college test publisher provided scores. On average, non-homeschoolers performed better than homeschoolers, by about two items, out of sixty items, on the ACT mathematics test that was analyzed. This result may be due to the different teaching/learning media used in teaching each of the two groups, to different teacher/student interaction, or…

Two survey instruments were developed and validated to measure early childhood teachers' (1) knowledge of early mathematical development and (2) beliefs about mathematics teaching and learning in the preschool classroom. The Knowledge of Mathematical Development (KMD) Survey was designed to measure teachers' knowledge of mathematical development…

Some basic statistical concepts relevant to the teacher--mean scores, standard deviation, normal and skewed distributions, z scores, item analysis, standard error of measurement, reliability--and their use by the teacher are explained. (RM)

Score equating requires that the forms to be equated are functionally parallel. That is, the two test forms should rank order examinees in a similar fashion. In language proficiency testing situations, this assumption is often put into doubt because of the numerous tests that have been proposed as measures of language proficiency and the…

A procedure for estimating the degree to which a subtest uniquely contributes to total test performance is presented and discussed. Uniqueness analysis may be appropriately applied to any composite measurement instrument such as a multipart test or a multitest battery to assess the unique contribution of each component to the total test. The…

Assuming that the density p of the true ability theta in the binomial test score model is continuous in the closed interval (0, 1), a Bernstein polynomial can be used to uniformly approximate p. Then via quadratic programming techniques, least-square estimates may be obtained for the coefficients defining the polynomial. The approximation, in turn…

An introductory textbook on psychological tests and measurements is presented in paper back booklet form. The style is informal and humorous, and the book is intended to appeal to the contemporary student. Ten chapters constitute the text: (1) On Measurement and Existence; (2) A Brief, Imprecise History of Psychological Testing; (3) The Creation…

Two forms of the CEEB English Composition Test and four tests constructed by the University of Illinois Rhetoric department were compared as final examinations for the freshman English composition course. Results from 2545 students indicate that while the CEEB tests discriminate more between students and are more reliable, the departmental tests…

A good criterion-referenced test item is defined as the one which allows the individual to answer correctly if he masters the criterion behavior represented by the item and answer incorrectly if he actually does not master it. Therefore, a good discriminating item for criterion-referenced tests is the one which has a larger proportion of correct…

A decision model designed to determine the reliability and validity of criterion referenced measures (CRMs) is presented. General procedures which pertain to the model are discussed as to: Measures of relationship, Reliability, Validity (content, criterion-oriented, and construct validation), and Item Analysis. The decision model is presented in…

A least-squares solution for the method of paired comparisons is given. The approach provokes a theorem regarding the amount of data necessary and sufficient for a solution to be obtained. A measure of the internal consistency of the least-squares fit is developed. (Author/CTM)

The reliabilities of various observational measures were determined, and the influence of both the number and the length of the observation periods on reliability was examined, both separately and jointly. A single simplifying assumption leads to a variant of the Spearman-Brown formula, which may have wider application. (Author/CTM)