@article {2102, title = {Computer Adaptive-Attribute Testing A New Approach to Cognitive Diagnostic Assessment}, journal = {Zeitschrift f{\"u}r Psychologie / Journal of Psychology}, volume = {216}, year = {2008}, pages = {29-39}, abstract = {

The influence of interdisciplinary forces stemming from developments in cognitive science,mathematical statistics, educational
psychology, and computing science are beginning to appear in educational and psychological assessment. Computer adaptive-attribute testing (CA-AT) is one example. The concepts and procedures in CA-AT can be found at the intersection between computer adaptive testing and cognitive diagnostic assessment. CA-AT allows us to fuse the administrative benefits of computer adaptive testing with the psychological benefits of cognitive diagnostic assessment to produce an innovative psychologically-based adaptive testing approach. We describe the concepts behind CA-AT as well as illustrate how it can be used to promote formative, computer-based, classroom assessment.

}, keywords = {cognition and assessment, cognitive diagnostic assessment, computer adaptive testing}, doi = {10.1027/0044-3409.216.1.29}, author = {Gierl, M. J. and Zhou, J.} } @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 {387, title = {A practitioner{\textquoteright}s guide to variable-length computerized classification testing}, journal = {Practical Assessment, Research and Evaluation}, volume = {12 }, number = {1}, year = {2007}, month = {7/1/2009}, chapter = {January, 2007}, abstract = {Variable-length computerized classification tests, CCTs, (Lin \& Spray, 2000; Thompson, 2006) are a powerful and efficient approach to testing for the purpose of classifying examinees into groups. CCTs are designed by the specification of at least five technical components: psychometric model, calibrated item bank, starting point, item selection algorithm, and termination criterion. Several options exist for each of these CCT components, creating a myriad of possible designs. Confusion among designs is exacerbated by the lack of a standardized nomenclature. This article outlines the components of a CCT, common options for each component, and the interaction of options for different components, so that practitioners may more efficiently design CCTs. It also offers a suggestion of nomenclature. }, keywords = {CAT, classification, computer adaptive testing, computerized adaptive testing, Computerized classification testing}, author = {Thompson, N. A.} } @article {310, title = {Applying Bayesian item selection approaches to adaptive tests using polytomous items}, journal = {Applied Measurement in Education}, volume = {19}, number = {1}, year = {2006}, pages = {1-20}, publisher = {Lawrence Erlbaum: US}, abstract = {This study applied the maximum expected information (MEI) and the maximum posterior- weighted information (MPI) approaches of computer adaptive testing item selection to the case of a test using polytomous items following the partial credit model. The MEI and MPI approaches are described. A simulation study compared the efficiency of ability estimation using the MEI and MPI approaches to the traditional maximal item information (MII) approach. The results of the simulation study indicated that the MEI and MPI approaches led to a superior efficiency of ability estimation compared with the MII approach. The superiority of the MEI and MPI approaches over the MII approach was greatest when the bank contained items having a relatively peaked information function. (PsycINFO Database Record (c) 2007 APA, all rights reserved)}, keywords = {adaptive tests, Bayesian item selection, computer adaptive testing, maximum expected information, polytomous items, posterior weighted information}, isbn = {0895-7347 (Print); 1532-4818 (Electronic)}, author = {Penfield, R. D.} } @article {319, title = {SIMCAT 1.0: A SAS computer program for simulating computer adaptive testing}, journal = {Applied Psychological Measurement}, volume = {30}, number = {1}, year = {2006}, pages = {60-61}, publisher = {Sage Publications: US}, abstract = {Monte Carlo methodologies are frequently applied to study the sampling distribution of the estimated proficiency level in adaptive testing. These methods eliminate real situational constraints. However, these Monte Carlo methodologies are not currently supported by the available software programs, and when these programs are available, their flexibility is limited. SIMCAT 1.0 is aimed at the simulation of adaptive testing sessions under different adaptive expected a posteriori (EAP) proficiency-level estimation methods (Blais \& Ra{\^\i}che, 2005; Ra{\^\i}che \& Blais, 2005) based on the one-parameter Rasch logistic model. These methods are all adaptive in the a priori proficiency-level estimation, the proficiency-level estimation bias correction, the integration interval, or a combination of these factors. The use of these adaptive EAP estimation methods diminishes considerably the shrinking, and therefore biasing, effect of the estimated a priori proficiency level encountered when this a priori is fixed at a constant value independently of the computed previous value of the proficiency level. SIMCAT 1.0 also computes empirical and estimated skewness and kurtosis coefficients, such as the standard error, of the estimated proficiency-level sampling distribution. In this way, the program allows one to compare empirical and estimated properties of the estimated proficiency-level sampling distribution under different variations of the EAP estimation method: standard error and bias, like the skewness and kurtosis coefficients. (PsycINFO Database Record (c) 2007 APA, all rights reserved)}, keywords = {computer adaptive testing, computer program, estimated proficiency level, Monte Carlo methodologies, Rasch logistic model}, isbn = {0146-6216 (Print)}, author = {Ra{\^\i}che, G. and Blais, J-G.} } @article {102, title = {A Bayesian student model without hidden nodes and its comparison with item response theory}, journal = {International Journal of Artificial Intelligence in Education}, volume = {15}, number = {4}, year = {2005}, pages = {291-323}, publisher = {IOS Press: Netherlands}, abstract = {The Bayesian framework offers a number of techniques for inferring an individual{\textquoteright}s knowledge state from evidence of mastery of concepts or skills. A typical application where such a technique can be useful is Computer Adaptive Testing (CAT). A Bayesian modeling scheme, POKS, is proposed and compared to the traditional Item Response Theory (IRT), which has been the prevalent CAT approach for the last three decades. POKS is based on the theory of knowledge spaces and constructs item-to-item graph structures without hidden nodes. It aims to offer an effective knowledge assessment method with an efficient algorithm for learning the graph structure from data. We review the different Bayesian approaches to modeling student ability assessment and discuss how POKS relates to them. The performance of POKS is compared to the IRT two parameter logistic model. Experimental results over a 34 item Unix test and a 160 item French language test show that both approaches can classify examinees as master or non-master effectively and efficiently, with relatively comparable performance. However, more significant differences are found in favor of POKS for a second task that consists in predicting individual question item outcome. Implications of these results for adaptive testing and student modeling are discussed, as well as the limitations and advantages of POKS, namely the issue of integrating concepts into its structure. (PsycINFO Database Record (c) 2007 APA, all rights reserved)}, keywords = {Bayesian Student Model, computer adaptive testing, hidden nodes, Item Response Theory}, isbn = {1560-4292 (Print); 1560-4306 (Electronic)}, author = {Desmarais, M. C. and Pu, X.} } @article {85, title = {Dynamic assessment of health outcomes: Time to let the CAT out of the bag?}, journal = {Health Services Research}, volume = {40}, number = {5, part2}, year = {2005}, pages = {1694-1711}, publisher = {Blackwell Publishing: United Kingdom}, abstract = {Background: The use of item response theory (IRT) to measure self-reported outcomes has burgeoned in recent years. Perhaps the most important application of IRT is computer-adaptive testing (CAT), a measurement approach in which the selection of items is tailored for each respondent. Objective. To provide an introduction to the use of CAT in the measurement of health outcomes, describe several IRT models that can be used as the basis of CAT, and discuss practical issues associated with the use of adaptive scaling in research settings. Principal Points: The development of a CAT requires several steps that are not required in the development of a traditional measure including identification of "starting" and "stopping" rules. CAT{\textquoteright}s most attractive advantage is its efficiency. Greater measurement precision can be achieved with fewer items. Disadvantages of CAT include the high cost and level of technical expertise required to develop a CAT. Conclusions: Researchers, clinicians, and patients benefit from the availability of psychometrically rigorous measures that are not burdensome. CAT outcome measures hold substantial promise in this regard, but their development is not without challenges. (PsycINFO Database Record (c) 2007 APA, all rights reserved)}, keywords = {computer adaptive testing, Item Response Theory, self reported health outcomes}, isbn = {0017-9124 (Print); 1475-6773 (Electronic)}, author = {Cook, K. F. and O{\textquoteright}Malley, K. J. and Roddey, T. S.} } @article {304, title = {Recent trends in comparability studies}, number = {05-05}, year = {2005}, month = {August, 2005}, institution = {Pearson}, keywords = {computer adaptive testing, Computerized assessment, differential item functioning, Mode effects}, isbn = {05-05}, author = {Paek, P.} }