Linear models for optimal test design.
ability measurementability scaleabsolute targetactive constraintsadaptive test assemblyaggregated boundAlpha stratificationBayesian item-selection criterionBIB designbig-shadow-testbinomial-error modelBirnbaum approachblueprintbranch-and-bound searchcategorical constraintsclassical test designclassification of attributescomposite abilityconditional item-exposure controlconvex spacecost functioncutoff scoredesign modeldifferent item pooldynamic modeledited-setenumerationequating transformationequipercentilefeasibilityfixed test lengthgenetic algorithmsgoodness-of-fitGreedy heuristicsGulliksen's matched random subsets methodheuristic correctioninconsistent constraintsineligibility constraintsinfeasibilityinformation functioninteger programmingintentional factoritem authoritem calibrationitem mappingitem matchingitem overlapitem setitem swappingitem writingitem-criterion correlationitem-difficultyitem-discriminationitem-exposure controlitem-parameter estimationitem-response theoryKelderman methodKullback-Leibler informationlinear approximationlinear decompositionlinear on-the-fly testinglocal search heuristicslogical constraintsLord-Wingersky algorithmLuecht heuristicsmarginal item-exposure controlminimax approachmodern test designMonte Carlo methodmultidimensional abilitymultiobjective test assemblymultiple abilitiesmultiple-shadow-testnetwork-flow approximationnonlinear objectivesnuisance abilityobjective functionobserved-scoreoperational item pooloptimal designoverconstraintingparallel formspivot-itempower-setpredictive validitypretest-posttest designpruningquantitative constraintsrandom test lengthredundant constraintsreference testrelative targetresponse functionresponse-timesequential optimizationsimplex algorithmsimulated annealingsimultaneous optimizationsingle testSwanson-Stocking heuristicsSympson-Hetter methodtest assemblytest characteristic functiontest reliabilitytest splittingthree-stage approachtransshipment pointstree searchtwo-stageunidimensional abilityvariance functionweighted-deviation methodweighted-objective approach
This book begins with a reflection on the history of test design -- the core activity of all educational and psychological testing. It then presents a standard language for modeling test design problems as instances of multi-objective constrained optimization. The main portion of the book discusses test design models for a large variety of problems from the daily practice of testing, and illustrates their use with the help of numerous empirical examples. The presentation includes models for the assembly of tests to an absolute or relative target for their information functions, classical test assembly, test equating problems, item matching, test splitting, simultaneous assembly of multiple tests, tests with item sets, multidimensional tests, and adaptive test assemblies. Two separate chapters are devoted to the questions of how to design item banks for optimal support of programs with fixed and adaptive tests. This book, which does not require any specific mathematical background, has been written to be a helpful resource on the desk of any test specialist. The book is organized as follows. Chapter 1 introduces the current practice of test development and explains some elementary concepts from test theory, such as reliability and validity, and item and test information. Chapter 2 introduces a standard language for formulating test specifications. In Chapter 3, it is shown how this language can be used to model test assembly problems as simple linear models. Chapter 4 discusses general approaches available in mathematical programming, more specifically integer or combinatorial programming, to solve these models. A variety of empirical examples of the applications of the techniques to test-assembly problems, including such problems as IRT-based and classical test assemblies, assembling multiple test forms, assembling tests with item sets, multidimensional test assemblies, and adaptive test assemblies, are presented in Chapters 5-9. The topic of item-pool design for programs with fixed and adaptive tests is treated in Chapter 10 and 11, respectively. The book concludes with a few more reflective observations on the topic of test design. Note that summaries and exercises are given in the end of each chapter. In addition, basic concepts in linear programming that are required to understand the modelling approaches are reviewed in Appendix 1; an example of a test-assembly problem is provided in Appendix 2. This book is intended for graduate students, researchers, test specialists, and especially for anyone seriously interested in the psychometric methods field.
- Multidimensional adaptive testing with optimal design criteria for item selection
- Models for uncertainty in educational testing
- A shadow-test approach to adaptive item calibration
- A hierarchical framework for modeling speed and accuracy on test items
- On the use of MCMC computerized adaptive testing with empirical prior information to improve efficiency
- Practical considerations in computer-based testing
- An optimal test design to evaluate the ability of an examinee by using the stress–strength model
- CUSUM hypothesis tests and alternative response probabilities for finite Poisson trials
- Application of robust optimization to automated test assembly
- Exact and approximate methods for a one-dimensional minimax bin-packing problem
- Optimal test designs for polytomously scored items
- Optimal designs for the generalized partial credit model
- 33 Statistical Procedures Used in College Admissions Testing
- Estimating and using block information in the Thurstonian IRT model
- A review of multiobjective programming and its application in quantitative psychology
- On compensation in multidimensional response modeling
- Integer programming in psychology: a review and directions for future research
- Extending the bicriterion approach for anticlustering: exact and hybrid approaches
- Optimal designs for the Rasch model
- A latent variable model with change-points and its application to time pressure effects in educational assessment
- A genetic algorithm for automated assembly of linear multidimensional forced-choice questionnaires
- Optimal Bayesian adaptive design for test-item calibration
- Uniform test assembly
- Statistical tests of conditional independence between responses and/or response times on test items
- Determining targets for multi-stage adaptive tests using integer programming
This page was built for publication: Linear models for optimal test design.
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5693240)
