@article {278, title = {Using patterns of summed scores in paper-and-pencil tests and computer-adaptive tests to detect misfitting item score patterns}, journal = {Journal of Educational Measurement}, volume = {41}, number = {2}, year = {2004}, pages = {119-136}, abstract = {Two new methods have been proposed to determine unexpected sum scores on subtests (testlets) both for paper-and-pencil tests and computer adaptive tests. A method based on a conservative bound using the hypergeometric distribution, denoted ρ, was compared with a method where the probability for each score combination was calculated using a highest density region (HDR). Furthermore, these methods were compared with the standardized log-likelihood statistic with and without a correction for the estimated latent trait value (denoted as l-super(*)-sub(z) and l-sub(z), respectively). Data were simulated on the basis of the one-parameter logistic model, and both parametric and nonparametric logistic regression was used to obtain estimates of the latent trait. Results showed that it is important to take the trait level into account when comparing subtest scores. In a nonparametric item response theory (IRT) context, on adapted version of the HDR method was a powerful alterative to ρ. In a parametric IRT context, results showed that l-super(*)-sub(z) had the highest power when the data were simulated conditionally on the estimated latent trait level. (PsycINFO Database Record (c) 2005 APA ) (journal abstract)}, keywords = {Computer Assisted Testing, Item Response Theory, person Fit, Test Scores}, author = {Meijer, R. R.} } @article {277, title = {Outlier detection in high-stakes certification testing}, journal = {Journal of Educational Measurement}, volume = {39}, number = {3}, year = {2002}, pages = {219-233}, abstract = {Discusses recent developments of person-fit analysis in computerized adaptive testing (CAT). Methods from statistical process control are presented that have been proposed to classify an item score pattern as fitting or misfitting the underlying item response theory model in CAT Most person-fit research in CAT is restricted to simulated data. In this study, empirical data from a certification test were used. Alternatives are discussed to generate norms so that bounds can be determined to classify an item score pattern as fitting or misfitting. Using bounds determined from a sample of a high-stakes certification test, the empirical analysis showed that different types of misfit can be distinguished Further applications using statistical process control methods to detect misfitting item score patterns are discussed. (PsycINFO Database Record (c) 2005 APA )}, keywords = {Adaptive Testing, computerized adaptive testing, Educational Measurement, Goodness of Fit, Item Analysis (Statistical), Item Response Theory, person Fit, Statistical Estimation, Statistical Power, Test Scores}, author = {Meijer, R. R.} } @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.} }