The purpose of this paper is to prove that one currently recommended method of obtaining the reliability of an instrument defined on a population of aggregate units is invalid. This method randomly splits the aggregate into two halves, correlates the two half unit scores by a Pearson product moment correlation coefficient, and corrects the…

Restricted sampling with which the Illinois Test of Psycholinguistic Abilities was standardized was investigated by simulating a multivariate population comprised of four variables and having specified means, standard deviations, and intercorrelations. (Author/CL)

The net effect of the conditions under which tests are taken was empirically investigated using the scores obtained by high school students on an English and a mathematics test. (Author/BB)

The DELPHI procedure requires respondents to reply to several questionnaire iterations with subsequent rounds containing previous round feedback. This study investigated the methodology (response rates, effects of feedback) and offered evidence that large-scale DELPHI surveys are not as advantageous as has previously been indicated. Suggestions…

A closed sequential procedure for estimating true score is proposed for use with answer-until-correct tests. The accuracy of determining true score is the same as in conventional sequential solutions, but the possibility of using an unnecessarily large number of items is eliminated. (Author/CM)

Any systematic approach to the assessment of students' ability implies the use of a model. The more explicit the model is, the more its users know about what they are doing and what the consequences are. The Rasch model is a strong model where measurement is a bonus of the model itself. It is based on four ideas: (1) separation of observable…

Six methods of equating Test of English as a Foreign Language (TOEFL) test scores for samples consisting of the usual groups of examinees and groups controlled for native language representation were evaluated in terms of scale stability. The equating methods included three item response theory (IRT) variants (fixed b's scaling, a one-parameter…

With the increasing globalization of human resources practices, a commensurate increase in demand has occurred for multi-language ("global") personality norms for use in selection and development efforts. The combination of data from multiple translations of a personality assessment into a single norm engenders error from multiple sources. This…

The measurement of change is such a broad topic that this article must limit its focus to a few specific subtopics. These specific topics include: longitudinal research design, attrition in research studies, the statistical analysis of difference scores, and the comparison of analysis of variance (ANOVA) and multivariate analysis of variance…

The measurement dilemmas involved in assessing the national educational goals established by the President and governors at the 1989 education summit are discussed. The first and most important choice is what to assess and whether to align assessment to the vision of curriculum reform or to the curriculum that students are actually experiencing.…

For the past six years the National Assessment of Educational Progress has sponsored a national Conference on Large-Scale Assessment, designed to promote and improve communications among educational assessment personnel in State Departments of Education and other agencies. This volume contains most of the papers that were accepted for presentation…