The Northwest Evaluation Association, serving over 300 U.S. school districts, is developing an Internet-enabled assessment system that adapts questions to each student's performance. Shorter, adaptive tests help students avoid frustrations or boredom caused by too-difficult or -easy questions. Scores are as valid as traditional test scores. (MLH)

Derives three reliability estimates for the Bayes modal estimate (BME) and the maximum-likelihood estimate (MLE) of theta in computerized adaptive tests (CATs). Computes the three reliability estimates and the true reliabilities of both BME and MLE for seven simulated CATs. Results show the true reliabilities for BME and MLE to be nearly identical…

Demonstrates that both meanings of an ambiguity are accessed at the onset of the ambiguity when the context is biased towards the secondary meaning. This evidence does not support the context-dependent model, which says that contextual bias should aid the processor in selecting a meaning. (Author/VWL)

Embarking on a high-stakes online testing program is a major enterprise that requires planning, teamwork, communication, flexibility and good problem-solving skills. It is important to be aware of the issues that one may confront and what hurdles might have to be overcome to be successful in the job. The Virginia Department of Education…

In two experiments, naive participants took turns telling each other to click on a target picture while gaze was monitored. Critical trials included a "contrast" picture that differed from the target only in size. In both experiments, the timing of speakers' fixations on the contrast predicted whether the contrast was encoded in a phrase with a…

Most educators agree that the primary criterion of school success is the ongoing growth and achievement of every student even in the midst of constant debate about the state of the US education and conflicting opinions regarding the value of No Child Left Behind (NCLB). Standardized tests have their place, but computerized adaptive testing aimed…

There are eight commercially available computer-based test interpretations (CBTIs) for the Minnesota Multiphasic Personality Inventory-2 (MMPI-2), of which few have been empirically evaluated. Prospective users of these programs have little scientific data to guide choice of a program. This study compared ratings of these eight CBTIs. Test users…

Test equivalence can be evaluated in terms of four aspects: psychometric, behavioral, experiential, and individual differences (i.e., relativity of equivalence) (Honaker, 1988). This study examined the psychometric properties of the Attitude Towards Computerized Assessment Scale (ATCAS) designed to assess one of these criteria, namely,…

The authors examined the effect of prereading relevance instructions on reading time and learning for 2 types of text. Experiment 1 found that relevance instructions increased learning for relevant segments without increasing reading time when reading a scientific text sentence by sentence on a computer. In contrast, the same segments were learned…

This paper deals with optimal partitioning of limited testing time in order to achieve maximum total test score. Nonlinear optimization theory was used to analyze this problem. A general case using a generic item response model is first presented. A special case that applies a response time model proposed by Wang and Hanson (2005) is also…

In addition to the potential that computer-based testing (CBT) offers, empirical evidence has found that identical computerized and paper-and-pencil tests have not produced equivalent test-taker performance. Referred to as the "mode effect," previous literature has identified many factors that may be responsible for such differential performance.…

Powers, Burstein, Chodorow, Fowles, and Kukich (2002) suggested that automated essay scoring (AES) may benefit from the use of "general" scoring models designed to score essays irrespective of the prompt for which an essay was written. They reasoned that such models may enhance score credibility by signifying that an AES system measures the same…

Choosing a strategy for controlling item exposure has become an integral part of test development for computerized adaptive testing (CAT). This study investigated the performance of six procedures for controlling item exposure in a series of simulated CATs under the generalized partial credit model. In addition to a no-exposure control baseline…

Multidimensional adaptive testing (MAT) procedures are proposed for the measurement of several latent traits by a single examination. Bayesian latent trait estimation and adaptive item selection are derived. Simulations were conducted to compare the measurement efficiency of MAT with those of unidimensional adaptive testing and random…

This article shows how set covering with item sampling (SCIS) methods can be used in the analysis and preanalysis of linear programming models for test assembly (LPTA). LPTA models can construct tests, fulfilling a set of constraints set by the test assembler. Sometimes, no solution to the LPTA model exists. The model is then said to be…