Discusses, for the benefit of research workers and other test users, the ongoing controversy concerning the relative merits of conventional test theory and Rasch scaling in the construction of reading tests. Concludes that a great deal of further research is required to see whether these approaches are educationally valid. (JD)

Thirteen ability tests were administered as defined within a mapping sentence containing four content facets: rule type, expression mode, language of communication and dimensionality of portrayed object. Smallest Space Analysis of intercorrelations among test scores showed the radex structure of the two-dimensional space conformed to the…

The purpose of the study was to determine comparability of an online version to the original paper-pencil version of Defining Issues Test 2 (DIT2). This study employed methods from both Classical Test Theory (CTT) and Item Response Theory (IRT). Findings from CTT analyses supported the reliability and discriminant validity of both versions.…

A behavioral domain is well-defined when it is clear to both test developers and test users which categories of performance should or should not be considered for potential test items. Only those tests that are keyed to well-defined domains meet the definition of criterion-referenced tests. The greatest proliferation of criterion-referenced tests…

Two approaches to criterion-referenced test construction are compared. Classical test theory is based on the practice of random sampling from a well-defined domain of test items; latent trait theory suggests that the difficulty of the items should be matched to the achievement level of the student. In addition to these two methods of test…

Reviews recent theoretical, methodological, and analytical developments in language testing, focusing on more refined models of language ability, reliability and validity, performance testing, innovative test formats, new applications of Item Response Theory and Generalizability Theory to test performance. An annotated bibliography discusses seven…

Research on the potential effects of different item arrangement schemes on item statistics is reviewed for three separate periods. Earliest studies investigated the simple main effect of item order on test performance. The late 1960s emphasized interactions between item order and examinees' characteristics. Current concern focuses on item…

A study examined whether the process of gathering verbal reports of subjects' thinking while taking multiple-choice critical thinking tests could be used to infer the reasoning process used and identify test items which do not require critical thinking skills. Four factors can render an inference of a subject's critical thinking skills…

To explain discrepancies in Utah's elementary school test results under the Elementary and Secondary Education Act's Title I Evaluation and Reporting System (TIERS), researchers investigated the adequacy and validity of TIERS evaluation models. Model A (norm-referenced testing) is used in most Utah school districts, in preference to Models B or C…

To date, little work has been done to ensure limited English proficient (LEP) students are accurately assessed on a large scale. The purpose of this guide is to help scorers in high volume situations to be able to effectively evaluate the open-ended responses of this population. Section one of this guide presents a brief overview of the State…

This paper aims to provide practical advice for creating a placement test for English-as-a-Second-Language (ESL) or English-as-a-foreign-language (EFL) instruction. Three forms of concrete assistance are provided: a detailed literature review; detailed steps focusing on the creation of placement tests; and a set of recommendations focusing on…

This study examined the amount of variance explained by alignment of testing to instruction among low socioeconomic level fourth graders, proposing two instructional alignment hypotheses. Results indicated that alignment had an unusually high effect. Low performing low socioeconomic level students achieved high success levels when conditions of…

The usefulness of three item response theory-based methods and the Mantel Haenszel technique in evaluating the measurement equivalence of translated assessment instruments was demonstrated in a study involving 2,000 French-speaking Canadian adults who took a French test translation and 2,000 English-speaking adults who took the English original.…

Recent experience with the Computerized Adaptive Test (CAT) has raised a number of concerns about its practical applications. The concerns are principally involved with the concept of having the computer construct the test from a precalibrated item pool, and substituting statistical characteristics for the test developer's skills. Problems with…

Classical measurement theory was used to investigate measurement characteristics of both parts of the Finding Embedded Figures Test (FEFT) when the test was: administered in either a "no guessing" supply format or a multiple-choice selection format; administered to either undergraduate college students or middle school students; and…