In a preceding research report, ONR/RR-82-1 (Information Loss Caused by Noise in Models for Dichotomous Items), observations were made on the effect of noise accommodated in different types of models on the dichotomous response level. In the present paper, focus is put upon the three-parameter logistic model, which is widely used among…

The relationship between selected subtests from the Armed Services Vocational Aptitude Battery (ASVAB) and corresponding subtests administered as computerized adaptive tests (CAT) was investigated using a sample of Marine recruits. Results showed that the CAT subtest scores correlated as well with initial ASVAB scores as did ASVAB retest scores,…

One of the important underlying assumptions of all item response theory (IRT) models is that of local independence. This assumption requires that the response to an item on a test not be influenced by the response to any other items. This assumption is often taken for granted, with little or no scrutiny of the response process required to answer…

This document outlines the use of machine-scorable open-ended questions for the evaluation of Physics 30 in Alberta. Contents include: (1) an introduction to the questions; (2) sample instruction sheet; (3) fifteen sample items; (4) item information including the key, difficulty, and source of each item; (5) solutions to items having multiple…

Item banks, large sets of test items, can be used for the construction of achievement tests. Mathematical programming models have been proposed for the selection of items from an item bank for a test. These models make automated test construction possible. However, to find an optimal or even an approximate optimal solution to a test construction…

If elementary science education is to be improved, elementary teachers must be willing to devote more time and energy to the curriculum. Increased self-efficacy and outcome expectancy beliefs were predicted antecedents to the behavior change. This study was designed to provide a valid and reliable measure of the teacher self-efficacy of preservice…

This report summarizes findings on 26 National Teacher Examination specialty area tests provided by faculty reviewers from five Oregon institutions of higher education. Reviewers were asked to judge tests on the basis of: (1) whether students at the reviewer's institution would have the opportunity to acquire the knowledge measured in test items;…

This fastback concentrates on writing technically correct test items that are compatible with the teacher's instructional objectives. The introductory chapter touches on some of the problems associated with preparing classroom tests. The second chapter outlines five steps in preparing a test according to the "Plan-Write" System: (1) prepare a…

In an effort to improve the ways in which words are learned, the Johnson O'Connor Research Foundation (JOCRF) is attempting to determine the difficulty level of all non-technical words in the English language. This item banking project entails: (1) identifying words that should be calibrated; (2) writing a test item for each word; (3) testing the…

Computerized adaptive testing procedures (CATPs) based on the graded response method (GRM) of F. Samejima (1969) and the partial credit model (PCM) of G. Masters (1982) were developed and compared. Both programs used maximum likelihood estimation of ability, and item selection was conducted on the basis of information. Two simulated data sets, one…

Factors affecting a lower-bound estimate of internal consistency reliability, Cronbach's coefficient alpha, are explored. Theoretically, coefficient alpha is an estimate of the correlation between two tests drawn at random from a pool of items like the items in the test under consideration. As a practical matter, coefficient alpha can be an index…

A review of the National Teacher Examinations (NTE) has focused on the Commons Examinations component. The Commons, now named the National Teacher Examinations Core Battery, tests general knowledge, communication skills, and professional knowledge in three separate tests. Users may select portions of the tests that best suit their needs at various…

The Mantel-Haenszel procedure (MH) is a practical, inexpensive, and powerful way to detect test items that function differently in two groups of examinees. MH is a natural outgrowth of previously suggested chi square methods, and it is also related to methods based on item response theory. The study of items that function differently for two…

In latent trait theory the latent space, or space of the hypothetical construct, is usually represented by some unidimensional or multi-dimensional continuum of real numbers. Like the latent space, the item response can either be treated as a discrete variable or as a continuous variable. Latent trait theory relates the item response to the latent…