Balancing assessment of learning outcomes with the expectations of students is a perennial challenge in education. Difficult exams, in which many students perform poorly, exacerbate this problem and can inspire a wide variety of interventions, such as a grading curve. However, addressing poor performance can sometimes distort or inflate grades and…

An investigation of the effect on the difficulty value of an item due to position placement within a test was made. Using a 60-item operational test comprised of 5 subtests, 60 items were placed as experimental items on a number of spiralled test forms in three different positions (first, middle, last) within the subtest composed of like items.…

A number of empirical studies are suggested to answer certain questions in connection with flexilevel tests. (MS)

Analyses of student responses to Introductory Psychology test questions were discussed. The publisher supplied a two thousand item test bank on computer tape. Instructors selected questions for fifteen item tests. The test questions were labeled by the publisher as factual or conceptual. The semester course used a mastery learning format in which…

Five statistical indices are developed and described which may be used for determining (1) when linear equating of two approximately parallel tests is adequate, and (2) whan a more complex method such as equipercentile equating must be used. The indices were based on: (1) similarity of cumulative score distributions; (2) shape of the raw-score to…

Factor analysis is the traditional method for studying the dimensionality of test data. However, under common conditions, the factor analysis of tetrachoric correlations does not recover the underlying structure of dichotomous data. The purpose of this paper is to demonstrate that the factor analyses of tetrachoric correlations is unlikely to…

This study was designed to increase knowledge of the functioning of item bias techniques in detecting biased items. Previous studies have used computer-generated data or real data with unknown amounts of bias. The present project extends previous studies by using items that are logically generated and subjectively evaluated a priori to be biased…

The purpose of this study was to determine whether item difficulty is significantly affected by language difficulty and response set convergence. Language difficulty was varied by increasing sentence (stem) length, increasing syntactic complexity, and substituting uncommon words for more familiar terms in the item stem. Item wording ranged from…

The effects of a multidimensional latent trait space on estimation of item and person parameters by the computer program LOGIST are examined. Several item pools were simulated that ranged from truly unidimensional to an inconsequential general latent trait. Item pools with intermediate levels of prepotency of the general latent trait were also…

A study compared college students' performance on complex multiple-choice tests with scores on multiple true-false clusters. Researchers concluded that the multiple-choice tests did not accurately measure students' knowledge and that cueing and guessing led to grade inflation. (PP)

It is important to estimate the number of examinees who reached a test item, because item difficulty is defined by the number who answered correctly divided by the number who reached the item. A new method is presented and compared to the previously used definition of three categories of response to an item: (1) answered; (2) omitted--a…

Multidimensional item difficulty (MID) is proposed as a means of describing test items which measure more than one ability. With mathematical story problems, for instance, both mathematical and verbal skills are required to obtain a correct answer. The proposed measure of MID is based upon three general assumptions: (1) the probability of…

A case study of the Florida Teacher Certification Examination (FTCE) program was described to assist others launching the development of large scale item banks. FTCE has four subtests: Mathematics, Reading, Writing, and Professional Education. Rasch calibrated item banks have been developed for all subtests except Writing. The methods used to…

The problem of measuring growth across the target grade and, typically, the two adjacent grades, concerns most developers of standardized, norm-referenced achievement tests, particularly at the item selection stage. Opinion is divided on whether to retain or drop items that do not get easier from grade to grade. The controversy has focused on…

A one-parameter latent trait model was the basis of the test development procedures in the Basic Skills Assessment Program (BSAP) of the Department of Defense Dependents Schools (DoDDS). Several issues are involved in applying the Rasch model to an assessment program in a large school district. Separate sets of skills continua are arranged by…