We explored three approaches to resolving or re-scoring constructed-response items in mixed-format assessments: rater agreement, person fit, and targeted double scoring (TDS). We used a simulation study to consider how the three approaches impact the psychometric properties of student achievement estimates, with an emphasis on person fit. We found…

In this paper, we provide an overview of psychometric procedures and guidelines Educational Testing Service (ETS) uses to evaluate automated essay scoring for operational use. We briefly describe the e-rater system, the procedures and criteria used to evaluate e-rater, implications for a range of potential uses of e-rater, and directions for…

Automated Essay Scoring (AES) has garnered a great deal of attention from the rhetoric and composition/writing studies community since the Educational Testing Service began using e-rater[R] and the "Criterion"[R] Online Writing Evaluation Service as products in scoring writing tests, and most of the responses have been negative. While the…

This article demonstrates the use of a new class of model-free cumulative sum (CUSUM) statistics to detect person fit given the responses to a linear test. The fundamental statistic being accumulated is the likelihood ratio of two probabilities. The detection performance of this CUSUM scheme is compared to other model-free person-fit statistics…

Paul Newton (2010), with his characteristic concern about theory, has set out two different ways of thinking about the basis upon which equivalences of one sort or another are established between test score scales. His reason for doing this is a desire to establish "the defensibility of linkages lower on the continuum than concordance."…

The rank-ordering method for standard maintaining was designed for the purpose of mapping a known cut-score (e.g. a grade boundary mark) on one test to an equivalent point on the test score scale of another test, using holistic expert judgements about the quality of exemplars of examinees' work (scripts). It is a novel application of an old…

This article presents the author's rejoinder to thinking about linking from issue 8(1). Particularly within the more embracing linking frameworks, e.g., Holland & Dorans (2006) and Holland (2007), there appears to be a major disjunction between (1) classification discourse: the supposed basis for classification, that is, the underlying theory…

"Linking" is a term given to a general class of procedures by which one represents scores X on one test or measure in terms of scores Y on another test or measure. A recent taxonomy by Holland and Dorans (2006; Holland, 2007) organizes the various types of links into three broad categories: prediction, scale aligning, and equating. In…

Robert Coe has claimed that three broad conceptions of comparability can be identified from the literature: performance, statistical and conventional. Each of these he rejected, in favour of a single, integrated conception which relies upon the notion of a "linking construct" and which he termed "construct comparability".…

The widespread application of personal computers to educational and psychological testing has substantially increased the number of test administration methodologies available to testing programs. Many of these mediums are referred to by their acronyms, such as CAT, CBT, CCT, and LOFT. The similarities between the acronyms and the methods…

Mathematical word problems represent a common item format for assessing student competencies. Automatic item generation (AIG) is an effective way of constructing many items with predictable difficulties, based on a set of predefined task parameters. The current study presents a framework for the automatic generation of probability word problems…

Pupil monitoring systems support the teacher in tailoring teaching to the individual level of a student and in comparing the progress and results of teaching with national standards. The systems are based on the availability of an item bank calibrated using item response theory. The assessment of the students' progress and results can be further…

One promising application of diagnostic classification models (DCM) is in the area of cognitive diagnostic assessment in education. However, the successful application of DCM in educational testing will likely come with a price--and this price may be in the form of new test development procedures and practices required to yield data that satisfy…

Newton's article (2010) makes three main contributions to the literature. First, it is transatlantic, bringing together literatures that have been dealing with similar problems, using sometimes different methods and certainly with distinctive educational, cultural perspectives. He points out that neither of these literatures has all of the…

The paper gives an overview of multidimensional adaptive testing (MAT) and evaluates its applicability in educational and psychological testing. The approach of Segall (1996) is described as a general framework for MAT. The main advantage of MAT is its capability to increase measurement efficiency. In simulation studies conceptualizing situations…