@article {199, title = {Computerized adaptive testing for polytomous motivation items: Administration mode effects and a comparison with short forms}, journal = {Applied Psychological Measurement}, volume = {31}, number = {5}, year = {2007}, note = {10.1177/0146621606297314Journal; Peer Reviewed Journal; Journal Article}, pages = {412-429}, abstract = {In a randomized experiment (n=515), a computerized and a computerized adaptive test (CAT) are compared. The item pool consists of 24 polytomous motivation items. Although items are carefully selected, calibration data show that Samejima{\textquoteright}s graded response model did not fit the data optimally. A simulation study is done to assess possible consequences of model misfit. CAT efficiency was studied by a systematic comparison of the CAT with two types of conventional fixed length short forms, which are created to be good CAT competitors. Results showed no essential administration mode effects. Efficiency analyses show that CAT outperformed the short forms in almost all aspects when results are aggregated along the latent trait scale. The real and the simulated data results are very similar, which indicate that the real data results are not affected by model misfit. (PsycINFO Database Record (c) 2007 APA ) (journal abstract)}, keywords = {2220 Tests \& Testing, Adaptive Testing, Attitude Measurement, computer adaptive testing, Computer Assisted Testing, items, Motivation, polytomous motivation, Statistical Validity, Test Administration, Test Forms, Test Items}, isbn = {0146-6216}, author = {Hol, A. M. and Vorst, H. C. M. and Mellenbergh, G. J.} } @article {401, title = {Assembling a computerized adaptive testing item pool as a set of linear tests}, journal = {Journal of Educational and Behavioral Statistics}, volume = {31}, number = {1}, year = {2006}, pages = {81-99}, publisher = {Sage Publications: US}, abstract = {Test-item writing efforts typically results in item pools with an undesirable correlational structure between the content attributes of the items and their statistical information. If such pools are used in computerized adaptive testing (CAT), the algorithm may be forced to select items with less than optimal information, that violate the content constraints, and/or have unfavorable exposure rates. Although at first sight somewhat counterintuitive, it is shown that if the CAT pool is assembled as a set of linear test forms, undesirable correlations can be broken down effectively. It is proposed to assemble such pools using a mixed integer programming model with constraints that guarantee that each test meets all content specifications and an objective function that requires them to have maximal information at a well-chosen set of ability values. An empirical example with a previous master pool from the Law School Admission Test (LSAT) yielded a CAT with nearly uniform bias and mean-squared error functions for the ability estimator and item-exposure rates that satisfied the target for all items in the pool. }, keywords = {Algorithms, computerized adaptive testing, item pool, linear tests, mathematical models, statistics, Test Construction, Test Items}, isbn = {1076-9986 (Print)}, author = {van der Linden, W. J. and Ariel, A. and Veldkamp, B. P.} } @article {198, title = {A randomized experiment to compare conventional, computerized, and computerized adaptive administration of ordinal polytomous attitude items}, journal = {Applied Psychological Measurement}, volume = {29}, number = {3}, year = {2005}, pages = {159-183}, abstract = {A total of 520 high school students were randomly assigned to a paper-and-pencil test (PPT), a computerized standard test (CST), or a computerized adaptive test (CAT) version of the Dutch School Attitude Questionnaire (SAQ), consisting of ordinal polytomous items. The CST administered items in the same order as the PPT. The CAT administered all items of three SAQ subscales in adaptive order using Samejima{\textquoteright}s graded response model, so that six different stopping rule settings could be applied afterwards. School marks were used as external criteria. Results showed significant but small multivariate administration mode effects on conventional raw scores and small to medium effects on maximum likelihood latent trait estimates. When the precision of CAT latent trait estimates decreased, correlations with grade point average in general decreased. However, the magnitude of the decrease was not very large as compared to the PPT, the CST, and the CAT without the stopping rule. (PsycINFO Database Record (c) 2005 APA ) (journal abstract)}, keywords = {Computer Assisted Testing, Test Administration, Test Items}, author = {Hol, A. M. and Vorst, H. C. M. and Mellenbergh, G. J.} } @article {195, title = {Test construction for cognitive diagnosis}, journal = {Applied Psychological Measurement}, volume = {29}, number = {4}, year = {2005}, pages = {262-277}, abstract = {Although cognitive diagnostic models (CDMs) can be useful in the analysis and interpretation of existing tests, little has been developed to specify how one might construct a good test using aspects of the CDMs. This article discusses the derivation of a general CDM index based on Kullback-Leibler information that will serve as a measure of how informative an item is for the classification of examinees. The effectiveness of the index is examined for items calibrated using the deterministic input noisy "and" gate model (DINA) and the reparameterized unified model (RUM) by implementing a simple heuristic to construct a test from an item bank. When compared to randomly constructed tests from the same item bank, the heuristic shows significant improvement in classification rates. (PsycINFO Database Record (c) 2005 APA ) (journal abstract)}, keywords = {(Measurement), Cognitive Assessment, Item Analysis (Statistical), Profiles, Test Construction, Test Interpretation, Test Items}, author = {Henson, R. K. and Douglas, J.} } @article {68, title = {The relationship between item exposure and test overlap in computerized adaptive testing}, journal = {Journal of Educational Measurement}, volume = {40}, number = {2}, year = {2003}, pages = {129-145}, abstract = {The purpose of this article is to present an analytical derivation for the mathematical form of an average between-test overlap index as a function of the item exposure index, for fixed-length computerized adaptive tests (CATs). This algebraic relationship is used to investigate the simultaneous control of item exposure at both the item and test levels. The results indicate that, in fixed-length CATs, control of the average between-test overlap is achieved via the mean and variance of the item exposure rates of the items that constitute the CAT item pool. The mean of the item exposure rates is easily manipulated. Control over the variance of the item exposure rates can be achieved via the maximum item exposure rate (r-sub(max)). Therefore, item exposure control methods which implement a specification of r-sub(max) (e.g., J. B. Sympson and R. D. Hetter, 1985) provide the most direct control at both the item and test levels. (PsycINFO Database Record (c) 2005 APA )}, keywords = {(Statistical), Adaptive Testing, Computer Assisted Testing, Human Computer, Interaction computerized adaptive testing, Item Analysis, Item Analysis (Test), Test Items}, author = {Chen, S-Y. and Ankemann, R. D. and Spray, J. A.} } @inbook {119, title = {Generating abstract reasoning items with cognitive theory}, booktitle = {Item generation for test development}, year = {2002}, note = {Using Smart Source ParsingItem generation for test development. (pp. 219-250). Mahwah, NJ : Lawrence Erlbaum Associates, Publishers. xxxii, 412 pp}, pages = {219-250}, publisher = {Lawrence Erlbaum Associates, Inc.}, organization = {Lawrence Erlbaum Associates, Inc.}, address = {Mahwah, N.J. USA}, abstract = {(From the chapter) Developed and evaluated a generative system for abstract reasoning items based on cognitive theory. The cognitive design system approach was applied to generate matrix completion problems. Study 1 involved developing the cognitive theory with 191 college students who were administered Set I and Set II of the Advanced Progressive Matrices. Study 2 examined item generation by cognitive theory. Study 3 explored the psychometric properties and construct representation of abstract reasoning test items with 728 young adults. Five structurally equivalent forms of Abstract Reasoning Test (ART) items were prepared from the generated item bank and administered to the Ss. In Study 4, the nomothetic span of construct validity of the generated items was examined with 728 young adults who were administered ART items, and 217 young adults who were administered ART items and the Advanced Progressive Matrices. Results indicate the matrix completion items were effectively generated by the cognitive design system approach. (PsycINFO Database Record (c) 2005 APA )}, keywords = {Cognitive Processes, Measurement, Reasoning, Test Construction, Test Items, Test Validity, Theories}, author = {Embretson, S. E.}, editor = {P. Kyllomen} } @article {418, title = {Mathematical-programming approaches to test item pool design}, number = {RR 02-09}, year = {2002}, note = {Using Smart Source ParsingAdvances in psychology research, Vol. ( Hauppauge, NY : Nova Science Publishers, Inc, [URL:http://www.Novapublishers.com]. vi, 228 pp}, pages = {93-108}, institution = {University of Twente, Faculty of Educational Science and Technology}, address = {Twente, The Netherlands}, abstract = {(From the chapter) This paper presents an approach to item pool design that has the potential to improve on the quality of current item pools in educational and psychological testing and hence to increase both measurement precision and validity. The approach consists of the application of mathematical programming techniques to calculate optimal blueprints for item pools. These blueprints can be used to guide the item-writing process. Three different types of design problems are discussed, namely for item pools for linear tests, item pools computerized adaptive testing (CAT), and systems of rotating item pools for CAT. The paper concludes with an empirical example of the problem of designing a system of rotating item pools for CAT.}, keywords = {Adaptive Testing, Computer Assisted, Computer Programming, Educational Measurement, Item Response Theory, Mathematics, Psychometrics, Statistical Rotation computerized adaptive testing, Test Items, Testing}, isbn = {02-09}, author = {Veldkamp, B. P. and van der Linden, W. J. and Ariel, A.} } @inbook {385, title = {Item response theory applied to combinations of multiple-choice and constructed-response items--approximation methods for scale scores}, booktitle = {Test scoring}, year = {2001}, note = {Using Smart Source ParsingTest scoring. (pp. 293-341). Mahwah, NJ : Lawrence Erlbaum Associates, Publishers. xii, 422 pp}, pages = {289-315}, publisher = {Lawrence Erlbaum Associates}, organization = {Lawrence Erlbaum Associates}, chapter = {8}, address = {Mahwah, N.J. USA}, abstract = {(From the chapter) The authors develop approximate methods that replace the scoring tables with weighted linear combinations of the component scores. Topics discussed include: a linear approximation for the extension to combinations of scores; the generalization of two or more scores; potential applications of linear approximations to item response theory in computerized adaptive tests; and evaluation of the pattern-of-summed-scores, and Gaussian approximation, estimates of proficiency. (PsycINFO Database Record (c) 2005 APA )}, keywords = {Adaptive Testing, Item Response Theory, Method), Multiple Choice (Testing, Scoring (Testing), Statistical Estimation, Statistical Weighting, Test Items, Test Scores}, author = {Thissen, D. and Nelson, L. A. and Swygert, K. A.} } @article {409, title = {An integer programming approach to item bank design}, journal = {Applied Psychological Measurement}, volume = {24}, number = {2}, year = {2000}, pages = {139-150}, abstract = {An integer programming approach to item bank design is presented that can be used to calculate an optimal blueprint for an item bank, in order to support an existing testing program. The results are optimal in that they minimize the effort involved in producing the items as revealed by current item writing patterns. Also presented is an adaptation of the models, which can be used as a set of monitoring tools in item bank management. The approach is demonstrated empirically for an item bank that was designed for the Law School Admission Test. }, keywords = {Aptitude Measures, Item Analysis (Test), Item Response Theory, Test Construction, Test Items}, author = {van der Linden, W. J. and Veldkamp, B. P. and Reese, L. M.} }