There is much debate on the merits and pitfalls of standardized tests for college admission, with questions regarding the format (multiple-choice versus constructed response), cognitive complexity, and content of these assessments (achievement versus aptitude) at the forefront of the discussion. This study addressed these questions by…

This study examined variations of a nonequivalent groups equating design used with constructed-response (CR) tests to determine which design was most effective in producing equivalent scores across the two tests to be equated. Using data from a large-scale exam, the study investigated the use of anchor CR item rescoring in the context of classical…

Background: All national curriculum tests in England are pre-tested as part of the development process. Differences in pupil performance between pre-test and live test are consistently found. This difference has been termed the pre-test effect. Understanding the pre-test effect is essential in the test development and selection processes and in…

When a test is adapted from a source language (SL) into a target language (TL), the two forms are usually not psychometrically equivalent. If linking between test forms is necessary, those items that have had their psychometric characteristics altered by the translation (differential item functioning [DIF] items) should be eliminated from the…

Growing recognition of the central importance of fostering an in-depth understanding of natural selection has, surprisingly, failed to stimulate work on the development and rigorous evaluation of instruments that measure knowledge of it. We used three different methodological tools, the Conceptual Inventory of Natural Selection (CINS), a modified…

Three-item orderings and two levels of knowledge of ordering were used to study differences in test results, student's perception of the test's fairness and difficulty, and student's estimation of test performance. No significant order effect was found. (Author/GK)

BRT Math Screening Measures focus on students' mathematics performance in grade-level standards for students in grades 1-8. A total of 24 test forms are available with three test forms per grade corresponding to fall, winter, and spring testing periods. Each form contains computation problems and application problems. BRT Math Screening Measures…

This article examined two item-writing guidelines: the format of the item stem and homogeneity of the answer set. Answering the call of Haladyna, Downing, and Rodriguez (2002) for empirical tests of item writing guidelines and extending the work of Smith and Smith (1988) on differential use of item characteristics, a mock multiple-choice driver's…

The study investigated the effect of "item density" on item difficulty in passage-related language tests. Item density refers to the number and frequency of items in relation to clear text. The format used was a passage with underlinings to signal the language situations out of which the items were constructed. American College Testing…

Randomly equivalent forms (REF) of tests in listening and reading for nonnative speakers of English were created by stratified random assignment of items to forms, stratifying on item content and predicted difficulty. The study included 50 replications of the procedure for each test. Each replication generated 2 REFs. The equivalence of those 2…

A comprehensive review is given of evidence, with a bearing on the recommendation to avoid use of complex multiple choice (CMC) items. Avoiding Type K items (four primary responses and five secondary choices) seems warranted, but evidence against CMC in general is less clear. (SLD)

A rating scale can be expressed as a chain of dichotomous items. The relationship between the dichotomies depends on the manner in which the rating scale is presented to the test taker. Three models for ordered scales are discussed. In the success model, which represents growth, the lowest or easiest category is presented first. If the test taker…

This study compared the item difficulty, item discrimination, and test reliability of three forms of multiple-choice items: (1) one correct answer; (2) "none of the above" as a foil; and (3) "none of the above" as the correct answer. Twelve items in the three formats were administered in a college statistics examination. (BS)

This paper summarizes some of the basic concepts in test equating. Various types of equating methods, as well as data collection designs, are outlined, with attempts to provide insight into preferred methods and techniques. Test equating describes a group of methods that enable test constructors and users to compare scores from two different forms…

Two forms of an undergraduate examination were constructed. Tests varied with respect to item truth value (true, false) and method of phrasing (positive, negative). Negatively stated items were more difficult but not more discriminating than positively stated items. False items were not more difficult but were more discriminating than true items.…