Recently arrived English as a second language (ESL) students were compared to their unilingual and multilingual Canadian-born peers on measures of French proficiency. All of the participants were enrolled in secondary core French (CF)--the ESL students were studying introductory French, whereas the Canadian-born students were in Grade 9 CF, their…

The presence of multiple readings of a student response to a constructed-response item in a large-scale assessment requires a procedure for combining the ratings to obtain an item score. An alternative to the averaged item ratings that are usually used is the summing of ratings for each item. This study evaluated the effect of summing as opposed…

This digest describes some basics of the construction of multiple-choice tests. As a rule, the test maker should strive for test item stems (introductory questions or incomplete statements at the beginning of each item that are followed by the options) that are clear and parsimonious, answers that are unequivocal and chosen by the students who do…

The Quest program offers a comprehensive test and questionnaire analysis environment by providing a data analyst (a computer program) with access to the most recent developments in Rasch measurement theory, as well as a range of traditional analysis procedures. This manual helps the user use Quest to construct and validate variables based on…

A new approach to the development of the item characteristic curve (ICC), which expresses the functional relationship between the level of performance on a given task and an independent variable that is relevant to the task, is presented. The approach focuses on knowledge states, decision processes, and other circumstances underlying responses to…

Tests are intended to assess performance of students. However, tests can also be used as an educational tool. Current patterns in education have produced a group of students with weak learning skills, limited confidence in their own abilities, an underlying hostility or distrust of the educational system, and an inhibited attitude towards…

The differences between multiple-choice, simulated, and concurrent tests of software-skills proficiency are discussed. For three basic human-resource functions, the advantages of concurrent tests (i.e., those that use the actual application software) include true performance-based assessment, unconstrained response alternatives, and increased job…

Three methods of estimating test score distributions that may improve on using the observed frequencies (OBFs) as estimates of a population test score distribution are considered: the kernel method (KM); the polynomial method (PM); and the four-parameter beta binomial method (FPBBM). The assumption each method makes about the smoothness of the…

This book is directed toward all persons taking tests and examinations at school, for a new job, for college or university entrance, or for promotion. Topics discussed include: things students should ask themselves before taking a test, the difference between tests and examinations, ways of feeling good about a test or examination, tactics and…

Omitted items cannot properly be treated as wrong when estimating ability and item parameters. A convenient method for utilizing the information provided by omissions is presented. Theoretical and empirical justifications are presented for the estimates obtained by the new method. (Author)

This paper discusses the assumptions required by the item response theory (IRT) true-score equating method (with Stocking & Lord, 1983; scaling approach), which is commonly used in the nonequivalent groups with an anchor data-collection design. More precisely, this paper investigates the assumptions made at each step by the IRT approach to…

This paper focuses on the Non-Equivalent Groups with Anchor Test (NEAT) design for test equating and on two classes of observed--score equating (OSE) methods--chain equating (CE) and poststratification equating (PSE). These two classes of methods reflect two distinctly different ways of using the information provided by the anchor test for…

The purpose of this research was to reinvestigate the accuracy of three item bias detection procedures: (1) Linn and Harnisch's pseudo-IRT(Z) method; (2) Camilli's chi-square technique; and (3) Angoff's revised transformed item difficulty method. These methods are applied when the minority group sample size is too small to obtain stable estimates…

A variety of locally dependent models are introduced having individual difference parameters that may be interpreted as reflecting effective learning abilities. One version is a univariate extension of the Rasch model with a Markov property: the probability that a given individual will pass an item depends on previous items only through the…

This experiment examined the effects of headings and adjunct questions embedded in expository text on the delayed multiple-choice test performance of college students. Subjects in the headings-present group performed significantly better on the retention test than did the subjects in the headings-absent group. The main effect of adjunct questions…