Multidimensional item response data were created. The strength of a general factor, the number of common factors, the distribution of items loadingon common factors, and the number of items in simulated tests were manipulated. LOGIST effectively recovered both item and trait parameters in nearly all of the experimental conditions. (Author/JAZ)

Examines traditional psychometric approaches to measuring intelligence and recent work by cognitive psychologists to develop a rationale for a non-verbal reasoning test for 10- to 11-year-olds. Recent studies providing basis for analyzing structure of test items are outlined, and benefits of analyzing items at a sub-type level are discussed.…

A British polytechnic's first experiences with having one segment of a major examination be known to students ahead of time is discussed, and an empirical comparison of this and the traditional test type is presented. (MSE)

The influence of item arrangement on students' total test performance was investigated. Two hierarchical multiple regression analyses were used to analyze the data. The main finding within the context of this study was that item arrangements based on item difficulties did not influence achievement examination performance. (Author/DWH)

Analyzes several questions and student answers, and the graders' evaluations of student responses on each of two advanced placement examinations--the one which tests Vergil and the one which tests Catallus and Horace. The percentages of participants scoring at each grade level of the exam are also presented. (SED)

Multiple-choice reading comprehension items from a conventional, norm-referenced reading comprehension test were successfully analyzed using a simple latent class model. Results support the use of latent class, state mastery models with more heterogenous item pools than has been previously advocated. (Author/PN)

Tests seven- , 10- , and 13-year-olds for developmental differences in processes and strategies involved in geometric matrix solution and the relationship between strategy differences and item complexity. (AS)

This study examined the impact of rater agreement on decisions concerning the alignment between the Golden State Examination (GSE) in High School Mathematics and the University of California (UC) "Statement on Competencies in Mathematics." UC faculty and high school mathematics teachers (n = 20) rated the mathematics items of the GSE…

The purpose of this document is to familiarize educators and parents with the text-based portion of the Delaware Student Testing Program (DSTP) writing assessment for third grade. The DSTP writing assessment consists of one "stand-alone" writing prompt (representing 2/3 of the overall writing score) and one "text-based" prompt…

The purpose of this study was to compare and evaluate three online pretest item calibration/scaling methods in terms of item parameter recovery when the item responses to the pretest items in the pool would be sparse. The three methods considered were the marginal maximum likelihood estimate with one EM cycle (OEM) method, the marginal maximum…

The focus in this study was on science achievement measures and their relationships to three reasoning dimensions: basic knowledge and reasoning, spatial-mechanical reasoning, and quantitative science reasoning. Thirty multiple-choice items, 8 constructed response items, and 3 performance assessments, each nominally assigned to 1 of the reasoning…

In a previous study (1998), how to evaluate whether adaptive testing data used for online calibration sufficiently fit the item response model used by C. Glas was studied. Three approaches were suggested, based on a Lagrange multiplier (LM) statistic, a Wald statistic, and a cumulative sum (CUMSUM) statistic respectively. For all these methods,…

The main purpose of this study was to illustrate a polytomous IRT-based linking procedure that adjusts for rater variations. Test scores from two administrations of a statewide reading assessment were used. An anchor set of Year 1 students' constructed responses were rescored by Year 2 raters. To adjust for year-to-year rater variation in IRT…

A new standard setting approach is introduced, called the cognitive components approach. Like the Angoff method, the cognitive components method generates minimum pass levels (MPLs) for each item. In both approaches, the item MPLs are summed for each judge, then averaged across judges to yield the standard. In the cognitive components approach,…

The psychometric research done by G. Rasch between 1951 and 1959, which is explained and illustrated in this book, takes psychometrics from being purely descriptive to being a science of objective measurement. Individual centered statistics require models in which each individual is characterized separately and from which, given adequate data,…