The purpose of this study was to gauge the disadvantage, if any, of reaching difficult items that appear earlier in a test, at the expense of not reaching easier items that appear later in a test. The study focused on Scholastic Aptitude Test (SAT) and Graduate Management Admissions Test (GMAT) data and examined the effect for females, Asian…

Three new computer-administered item types for the analytical scale of the Graduate Record Examination (GRE) General Test were developed and evaluated. One item type was a free-response version of the current analytical reasoning item type. The second item type was a somewhat constrained free-response version of the pattern identification (or…

The purpose of the Graduate Record Examinations (GRE) figural-response project was to design a prototype computer assessment system for delivering and scoring figural-response items in the domain of cell and molecular biology and to begin to investigate properties of the item format. This report describes progress to date in an effort that is…

Time limits on tests often prevent some examinees from finishing all of the items on the test; the extent of this effect has been called the "speededness" of the test. Traditional speededness indices focus on the number of unreached items. Other examinees in the same situation rapidly fill in answers in the hope of getting some of the…

The construction of parallel editions of conventional tests for purposes of test security while maintaining score comparability has always been a recognized and difficult problem in psychometrics and test construction. The introduction of new modes of test construction, e.g., adaptive testing, changes the nature of the problem, but does not make…

Applications of item response theory to practical testing problems including equating, differential item functioning, and computerized adaptive testing, require that item parameter estimates be placed onto a common metric. In this study, three methods for developing a common metric under item response theory are compared: (1) linking separate…

One of the item types in the Listening Comprehension section of the Test of English as a Foreign Language (TOEFL) test is the dialogue. Because the dialogue item pool needs to have an appropriate balance of items at a range of difficulty levels, test developers have examined items at various difficulty levels in an attempt to identify their…

This study investigates whether or not the factor structure of reading comprehension is invariant across large, nationally representative samples of 14-year-old students from four different countries. The data from French-speaking Belgium, Hungary, Italy, and the United States were collected as part of the Reading Literacy Study of 1990-91,…

Advanced Placement Calculus examinations were administered to nearly 7,000 students in order to determine the impact of calculator use. Both experimental examinations had two sections. Section I items were designed so that a calculator was not needed, but approximately half of the students were permitted to use calculators. Section II items…

The purpose of this study was to compare the scores of students who were allowed unlimited retakes of a multiple-choice test with the scores of students who were limited to only four retakes (five trials) of the same test. The tests were each made up of 20 randomly drawn questions from a large pool of questions about research methods. Three…

This digest introduces three issues to consider when evaluating test items for bias: fairness, bias, and stereotyping. In any bias investigation, the first step is to identify the subgroups of interest. Bias reviews and studies generally focus on differential performance for sex, ethnic, cultural, and religious groups. In preparing an item bias…

An important principle in constructing rating scales is to develop items that reflect various degrees of the "pro" (positive) and "contra" (negative) aspects of the trait being measured. Where both positive and negative items are pooled, they can be arranged in order along the trait continuum, but for classical and item…

To generalize test results beyond the particular test administration, an examinee's ability estimate must be independent of the particular items attempted, and the item difficulty calibrations must be independent of the particular sample of people attempting the items. This stability is a key concept of the Rasch model, a latent trait model of…

Possible population differences in speed versus level of Graduate Record Examinations (GRE) reading comprehension scores were explored. The study used operational measures computed post hoc from item-level data in GRE files for a pre-October 1977 version of the verbal test in which 40 GRE reading comprehension (RC) items were included as a…

When self-administered surveys or questionnaires are administered, there is often a question of whether respondents have attended to the items in a thoughtful manner. This paper examines the results of three different surveys to investigate the occurrence of nonattending behaviors such as missing items, patterns that indicate lack of…