ISSUES IN ITEM BANKING

An item bank is defined as a relatively large collection of easily accessible test questions. A wide variety of item bank schemes that meet this relatively unrestricted definition is illustrated. Advantages and disadvantages of item banking and the conditions under which item banks have the most potential value are identified. An extensive list of questions to be asked in designing item banking systems is provided. The following five questions were singled out for further discussion: How many items should be in the bank? Should users develop their own item collections or use the collections of others? How should the items be classified? Should items be calibrated? Will each test have different items or will the same test be administered to all?     

ITEM BANKS: WHAT, WHY, HOW

In this paper, we discuss curricular implications of item banking and its practical value to teachers and students, and list a variety of working banks with their sources. We also review the psychometric basis of item banking, outline a family of computer programs for accomplishing banking, and give the equations necessary to build a bank. We conclude with a discussion of item quality control and examples of items that misfit because of miskeying, guessing, or carelessness.     

Embedded Field Test Item Statistics: Can They Be Trusted for Estimating Student Proficiency?

Assessment items are commonly field tested prior to operational use to observe statistical item properties such as difficulty. Item parameter estimates from field testing may be used to assign scores via pre-equating or computer adaptive designs. This study examined differences between item difficulty estimates based on field test and operational data and the relationship of such differences to item position changes and student proficiency estimates. Item position effects were observed for 20 assessments, with items in later positions tending to be more difficult. Moreover, field test estimates of item difficulty were biased slightly upward, which may indicate examinee knowledge of which items were being field tested. Nevertheless, errors in field test item difficulty estimates had negligible impacts on student proficiency estimates for most assessments. Caution is still warranted when using field test statistics for scoring, and testing programs should conduct investigations to determine whether the effects on scoring are inconsequential.     

Measuring knowledge integration: Validation of four‐year assessments

Science education needs valid, authentic, and efficient assessments. Many typical science assessments primarily measure recall of isolated information. This paper reports on the validation of assessments that measure knowledge integration ability among middle school and high school students. The assessments were administered to 18,729 students in five states. Rasch analyses of the assessments demonstrated satisfactory item fit, item difficulty, test reliability, and person reliability. The study showed that, when appropriately designed, knowledge integration assessments can be balanced between validity and reliability, authenticity and generalizability, and instructional sensitivity and technical quality. Results also showed that, when paired with multiple‐choice items and scored with an effective scoring rubric, constructed‐response items can achieve high reliabilities. Analyses showed that English language learner status and computer use significantly impacted students' science knowledge integration abilities. Students who took the assessment online, which matched the format of content delivery, performed significantly better than students who took the paper‐and‐pencil version. Implications and future directions of research are noted, including refining curriculum materials to meet the needs of diverse students and expanding the range of topics measured by knowledge integration assessments. © 2011 Wiley Periodicals, Inc. J Res Sci Teach 48: 1079–1107, 2011     

AN INSTRUMENT TO MEASURE SELF‐RESPONSIBILITY FOR WELLNESS IN OLDER ADULTS

Literature relating to the well‐being of older adults was reviewed to identify indicators relevant to the construct of self‐responsibility for wellness. The wellness model proposed by Travis (1981) has produced a variety of concepts which can be useful in improving the quality of life for older adults. The purpose of this study was to develop an instrument which would assess an individual's self‐responsibility for wellness. A 47‐item instrument developed for this purpose was evaluated by experts in gerontology and psychology. After revision and reevaluation it was field‐tested on a sample of 180 older adults (60 years of age and over). In order to take preliminary steps in establishing the validity and reliability of this instrument, the data were evaluated and an item analysis conducted to identify poor items. Cronbach's coefficient alpha was also computed (α = .90). A test‐retest correlation coefficient was computed, and an analysis of variance was performed to test for the relationship between self‐responsibility for wellness and demographic variables obtained during the field test.

The field testing of the instrument served as an educational needs assessment study. Evidence has been provided that there is a significant need for education programs which can provide training in the wellness skills as assessed by the instrument.     

Effects of Item Modifications on Test Accessibility for Persistently Low-Performing Students with Disabilities

ABSTRACT

Construct-irrelevant cognitive complexity of some items in the statewide grade-level assessments may impose performance barriers for students with disabilities who are ineligible for alternate assessments based on alternate achievement standards. This has spurred research into whether items can be modified to reduce complexity without affecting item construct. This study uses a generalized linear mixed modeling analysis to investigate the effects of item modifications on improving test accessibility by reducing construct-irrelevant cognitive barriers for persistently low-performing fifth-grade students with cognitive disabilities. The results showed item scaffolding was an effective modification for both mathematics and reading. Other modifications, such as bolding/underlining of key words, hindered test performance for low-performing students. We discuss the findings’ potential impact on test development with universal design.     

Unidimensional Interpretations for Multidimensional Test Items

This article considers potential problems that can arise in estimating a unidimensional item response theory (IRT) model when some test items are multidimensional (i.e., show a complex factorial structure). More specifically, this study examines (1) the consequences of model misfit on IRT item parameter estimates due to unintended minor item‐level multidimensionality, and (2) whether a Projection IRT model can provide a useful remedy. A real‐data example is used to illustrate the problem and also is used as a base model for a simulation study. The results suggest that ignoring item‐level multidimensionality might lead to inflated item discrimination parameter estimates when the proportion of multidimensional test items to unidimensional test items is as low as 1:5. The Projection IRT model appears to be a useful tool for updating unidimensional item parameter estimates of multidimensional test items for a purified unidimensional interpretation.     

Controlling Bias in Both Constructed Response and Multiple‐Choice Items When Analyzed With the Dichotomous Rasch Model

Even though guessing biases difficulty estimates as a function of item difficulty in the dichotomous Rasch model, assessment programs with tests which include multiple‐choice items often construct scales using this model. Research has shown that when all items are multiple‐choice, this bias can largely be eliminated. However, many assessments have a combination of multiple‐choice and constructed response items. Using vertically scaled numeracy assessments from a large‐scale assessment program, this article shows that eliminating the bias on estimates of the multiple‐choice items also impacts on the difficulty estimates of the constructed response items. This implies that the original estimates of the constructed response items were biased by the guessing on the multiple‐choice items. This bias has implications for both defining difficulties in item banks for use in adaptive testing composed of both multiple‐choice and constructed response items, and for the construction of proficiency scales.     

Developing and evaluating instructionally sensitive assessments in science

The purpose of this article is to address a major gap in the instructional sensitivity literature on how to develop instructionally sensitive assessments. We propose an approach to developing and evaluating instructionally sensitive assessments in science and test this approach with one elementary life‐science module. The assessment we developed was administered to 125 students in seven classrooms. The development approach considered three dimensions of instructional sensitivity; that is, assessment items should: represent the curriculum content, reflect the quality of instruction, and have formative value for teaching. Focusing solely on the first dimension, representation of the curriculum content, this study was guided by the following research questions: (1) What science module characteristics can be systematically manipulated to develop items that prove to be instructionally sensitive? and (2) Are the instructionally sensitive assessments developed sufficiently valid to make inferences about the impact of instruction on students' performance? In this article, we describe our item development approach and provide empirical evidence to support validity arguments about the developed instructionally sensitive items. Results indicated that: (1) manipulations of the items at different proximities to vary their sensitivity were aligned with the rules for item development and also corresponded with pre‐to‐post gains; and (2) the items developed at different distances from the science module showed a pattern of pre‐to‐post gain consistent with their instructional sensitivity, that is, the closer the items were to the science module, the larger the observed gains and effect sizes. © 2012 Wiley Periodicals, Inc. J Res Sci Teach 49: 691–712, 2012     

Teachers’ and students’ perceptions of assessments: A review and a study into the ability and accuracy of estimating the difficulty levels of assessment items

In today's higher education, high quality assessments play an important role. Little is known, however, about the degree to which assessments are correctly aimed at the students’ levels of competence in relation to the defined learning goals. This article reviews previous research into teachers’ and students’ perceptions of item difficulty. It focuses on the item difficulty of assessments and students’ and teachers’ abilities to estimate item difficulty correctly. The review indicates that teachers tend to overestimate the difficulty of easy items and underestimate the difficulty of difficult items. Students seem to be better estimators of item difficulty. The accuracy of the estimates can be improved by: the information the estimators or teachers have about the target group and their earlier assessment results; defining the target group before the estimation process; the possibility of having discussions about the defined target group of students and their corresponding standards during the estimation process; and by the amount of training in item construction and estimating. In the subsequent study, the ability and accuracy of teachers and students to estimate the difficulty levels of assessment items was examined. In higher education, results show that teachers are able to estimate the difficulty levels correctly for only a small proportion of the assessment items. They overestimate the difficulty level of most of the assessment items. Students, on the other hand, underestimate their own performances. In addition, the relationships between the students’ perceptions of the difficulty levels of the assessment items and their performances on the assessments were investigated. Results provide evidence that the students who performed best on the assessments underestimated their performances the most. Several explanations are discussed and suggestions for additional research are offered.     

A Process for Reviewing and Evaluating Generated Test Items

Testing organization needs large numbers of high‐quality items due to the proliferation of alternative test administration methods and modern test designs. But the current demand for items far exceeds the supply. Test items, as they are currently written, evoke a process that is both time‐consuming and expensive because each item is written, edited, and reviewed by a subject‐matter expert. One promising approach that may address this challenge is with automatic item generation. Automatic item generation combines cognitive and psychometric modeling practices to guide the production of items that are generated with the aid of computer technology. The purpose of this study is to describe and illustrate a process that can be used to review and evaluate the quality of the generated item by focusing on the content and logic specified within the item generation procedure. We illustrate our process using an item development example from mathematics drawn from the Common Core State Standards and from surgical education drawn from the health sciences domain.     

How Can Released State Test Items Support Interim Assessment Purposes in an Educational Crisis?

State testing programs regularly release previously administered test items to the public. We provide an open-source recipe for state, district, and school assessment coordinators to combine these items flexibly to produce scores linked to established state score scales. These would enable estimation of student score distributions and achievement levels. We discuss how educators can use resulting scores to estimate achievement distributions at the classroom and school level. We emphasize that any use of such tests should be tertiary, with no stakes for students, educators, and schools, particularly in the context of a crisis like the COVID-19 pandemic. These tests and their results should also be lower in priority than assessments of physical, mental, and social–emotional health, and lower in priority than classroom and district assessments that may already be in place. We encourage state testing programs to release all the ingredients for this recipe to support low-stakes, aggregate-level assessments. This is particularly urgent during a crisis where scores may be declining and gaps increasing at unknown rates.     

IRT Estimation of Domain Scores

In classical test theory, a test is regarded as a sample of items from a domain defined by generating rules or by content, process, and format specifications, l f the items are a random sample of the domain, then the percent-correct score on the test estimates the domain score, that is, the expected percent correct for all items in the domain. When the domain is represented by a large set of calibrated items, as in item banking applications, item response theory (IRT) provides an alternative estimator of the domain score by transformation of the IRT scale score on the test. This estimator has the advantage of not requiring the test items to be a random sample of the domain, and of having a simple standard error. We present here resampling results in real data demonstrating for uni- and multidimensional models that the IRT estimator is also a more accurate predictor of the domain score than is the classical percent-correct score. These results have implications for reporting outcomes of educational qualification testing and assessment.     

VALIDITY OF THE DISCRIMINATION INDEX AS A MEASURE OF ITEM QUALITY1

Numerous writers have suggested that the discrimination index may be helpful in identifying faulty test items. The purpose of this study was to investigate systematically the validity of the index for this purpose. To attain this objective, two forms of an arithmetic-reasoning test were written. In each form, the items were designed to vary in quality with respect to nine item-writing principles, and on the basis of the responses of 364 examinees, a discrimination index was computed for each item. Next, the items were rated independently for quality by three judges who used a check list of the nine item-writing principles. The average of their ratings for each item was used as the criterion for determining the validity of the indices. The results indicate that the discrimination index is a moderately valid measure of item quality. The implications of this finding are discussed.     

Procedures for Selecting Items for Computerized Adaptive Tests

Many procedures have been developed for selecting the "best" items for a computerized adaptive test. There is a trend toward the use of adaptive testing in applied settings such as licensure tests, program entrance tests, and educational tests. It is useful to consider procedures for item selection and the special needs of applied testing settings to facilitate test design. The current study reviews several classical approaches and alternative approaches to item selection and discusses their relative merit. This study also describes procedures for constrained computerized adaptive testing (C-CAT) that may be added to classical item selection approaches to allow them to be used for applied testing, while maintaining the high measurement precision and short test length that made adaptive testing attractive to practitioners initially.     

Instructional Topics in Educational Measurement (ITEMS) Module: Using Automated Processes to Generate Test Items

Changes to the design and development of our educational assessments are resulting in the unprecedented demand for a large and continuous supply of content‐specific test items. One way to address this growing demand is with automatic item generation (AIG). AIG is the process of using item models to generate test items with the aid of computer technology. The purpose of this module is to describe and illustrate a template‐based method for generating test items. We outline a three‐step approach where test development specialists first create an item model. An item model is like a mould or rendering that highlights the features in an assessment task that must be manipulated to produce new items. Next, the content used for item generation is identified and structured. Finally, features in the item model are systematically manipulated with computer‐based algorithms to generate new items. Using this template‐based approach, hundreds or even thousands of new items can be generated with a single item model.     

On the Performance of Semi- and Nonparametric Item Response Functions in Computer Adaptive Tests

Large-scale assessments often use a computer adaptive test (CAT) for selection of items and for scoring respondents. Such tests often assume a parametric form for the relationship between item responses and the underlying construct. Although semi- and nonparametric response functions could be used, there is scant research on their performance in a CAT. In this work, we compare parametric response functions versus those estimated using kernel smoothing and a logistic function of a monotonic polynomial. Monotonic polynomial items can be used with traditional CAT item selection algorithms that use analytical derivatives. We compared these approaches in CAT simulations with a variety of item selection algorithms. Our simulations also varied the features of the calibration and item pool: sample size, the presence of missing data, and the percentage of nonstandard items. In general, the results support the use of semi- and nonparametric item response functions in a CAT.     

An Examination of the Instructional Sensitivity of the TIMSS Math Items: A Hierarchical Differential Item Functioning Approach

In recent years, students’ test scores have been used to evaluate teachers’ performance. The assumption underlying this practice is that students’ test performance reflects teachers’ instruction. However, this assumption is generally not empirically tested. In this study, we examine the effect of teachers’ instruction on test performance at the item level using a hierarchical differential item functioning approach. The items are from the U.S. TIMSS 2011 4th-grade math test. Specifically, we tested whether students who had received instruction on a given item performed significantly better on that item compared with students who had not received such instruction when their overall math ability was controlled for, whether with or without controlling for student-level and class-level covariates. This study provides preliminary findings regarding why some items show instructional sensitivity and sheds light on how to develop instructionally sensitive items. Implications and directions for further research are also discussed.