Springer Proceedings in Mathematics & Statistics L. Andries van der Ark Marie Wiberg Steven A. Culpepper Jeff rey A. Douglas Wen-Chung Wang Editors Quantitative Psychology The 81st Annual Meeting of the Psychometric Society, Asheville, North Carolina, 2016 Springer Proceedings in Mathematics & Statistics Volume 196 SpringerProceedingsinMathematics&Statistics This book series features volumes composed of selected contributions from workshops and conferences in all areas of current research in mathematics and statistics, including operation research and optimization. In addition to an overall evaluation of the interest, scientific quality, and timeliness of each proposal at the hands of the publisher, individual contributions are all refereed to the high quality standards of leading journals in the field. Thus, this series provides the research community with well-edited, authoritative reports on developments in the most excitingareasofmathematicalandstatisticalresearchtoday. Moreinformationaboutthisseriesathttp://www.springer.com/series/10533 L. Andries van der Ark • Marie Wiberg Steven A. Culpepper • Jeffrey A. Douglas Wen-Chung Wang Editors Quantitative Psychology The 81st Annual Meeting of the Psychometric Society, Asheville, North Carolina, 2016 123 Editors L.AndriesvanderArk MarieWiberg ResearchInstituteforChild DepartmentofStatistics,USBE DevelopmentandEducation UmeåUniversity,Umeå,Sweden UniversityofAmsterdam Amsterdam,TheNetherlands JeffreyA.Douglas DepartmentofStatistics StevenA.Culpepper UniversityofIllinoisatUrbana-Champaign DepartmentofStatistics Champaign,IL,USA UniversityofIllinoisatUrbana-Champaign Champaign,IL,USA Wen-ChungWang DepartmentofPsychology TheEducationalUniversityofHongKong HongKong,China ISSN2194-1009 ISSN2194-1017 (electronic) SpringerProceedingsinMathematics&Statistics ISBN978-3-319-56293-3 ISBN978-3-319-56294-0 (eBook) DOI10.1007/978-3-319-56294-0 LibraryofCongressControlNumber:2017940525 ©SpringerInternationalPublishingAG2017 Thisworkissubjecttocopyright.AllrightsarereservedbythePublisher,whetherthewholeorpartof thematerialisconcerned,specificallytherightsoftranslation,reprinting,reuseofillustrations,recitation, broadcasting,reproductiononmicrofilmsorinanyotherphysicalway,andtransmissionorinformation storageandretrieval,electronicadaptation,computersoftware,orbysimilarordissimilarmethodology nowknownorhereafterdeveloped. Theuseofgeneraldescriptivenames,registerednames,trademarks,servicemarks,etc.inthispublication doesnotimply,evenintheabsenceofaspecificstatement,thatsuchnamesareexemptfromtherelevant protectivelawsandregulationsandthereforefreeforgeneraluse. Thepublisher,theauthorsandtheeditorsaresafetoassumethattheadviceandinformationinthisbook arebelievedtobetrueandaccurateatthedateofpublication.Neitherthepublishernortheauthorsor theeditorsgiveawarranty,expressorimplied,withrespecttothematerialcontainedhereinorforany errorsoromissionsthatmayhavebeenmade.Thepublisherremainsneutralwithregardtojurisdictional claimsinpublishedmapsandinstitutionalaffiliations. Printedonacid-freepaper ThisSpringerimprintispublishedbySpringerNature TheregisteredcompanyisSpringerInternationalPublishingAG Theregisteredcompanyaddressis:Gewerbestrasse11,6330Cham,Switzerland Preface This volume represents presentations given at the 81st annual meeting of the Psychometric Society in Asheville, North Carolina, during July 11–15, 2016. The meeting, organized by the University of North Carolina at Greensboro, was one of the largest Psychometric Society meetings in the United States, both in terms of participants and number of presentations. It attracted 415 participants, with 204 papers being presented, along with 95 poster presentations, 3 pre-conference workshops,3keynotepresentations,6invitedpresentations,2career-awardpresen- tations,adebate,2dissertation-awardwinners,9symposia,atrivial-pursuitlunch, andPsychometrika’s80thanniversarycelebration. Sincethe77thmeetinginLincoln,Nebraska,Springerpublishestheproceedings volume from the annual meeting of the Psychometric Society so as to allow presenters to quickly make their ideas available to the wider research community while still undergoing a thorough review process. The first four volumes of the meetings in Lincoln, Arnhem, Madison, and Beijing were received successfully, andweexpectasuccessfulreceptionoftheseproceedingstoo. We asked authors to use their presentation at the meeting as the basis of their chapters,possiblyextendedwithnewideasoradditionalinformation.Theresultisa selectionof36state-of-the-artchaptersaddressingadiversesetoftopics,including itemresponsetheory,equating,classicaltesttheory,factoranalysis,structuralequa- tion modeling, dual scaling, multidimensional scaling, power analysis, cognitive diagnosticmodels,andmultilevelmodels. Amsterdam L.AndriesvanderArk Umeå MarieWiberg Urbana-Champaign,IL StevenA.Culpepper Urbana-Champaign,IL JeffreyA.Douglas HongKong Wen-ChungWang v Contents NewResultsonanImprovedParallelEMAlgorithmforEstimating GeneralizedLatentVariableModels........................................... 1 Matthiasvon Davier Properties of Second-Order Exponential Models as MultidimensionalResponseModels ........................................... 9 CarolynJ.AndersonandHsiu-TingYu Pseudo-Likelihood Estimation of Multidimensional Response Models:PolytomousandDichotomousItems................................. 21 YoungshilPaekandCarolynJ.Anderson FittingGradedResponseModelstoDatawithNon-Normal LatentTraits...................................................................... 31 Tzu-ChunKuoandYanyanSheng AnExtensionofRudner-BasedConsistencyandAccuracyIndices forMultidimensionalItemResponseTheory................................. 43 WenyiWang,LihongSong,andShuliangDing Supporting Diagnostic Inferences Using Significance Tests for SubtestScores .................................................................... 59 WilliamLorié AComparisonofTwoMCMCAlgorithmsforthe2PLIRTModel........ 71 Meng-IChangandYanyanSheng Similar DIFs: Differential Item Functioning and Factorial InvarianceforScaleswithSeven(“PlusorMinusTwo”)Response Alternatives....................................................................... 81 DavidThissen vii viii Contents Finally!AValidTestofConfiguralInvarianceUsingPermutation inMultigroupCFA............................................................... 93 Terrence D. Jorgensen, Benjamin A. Kite, Po-Yi Chen, andStephenD.Short OutcriesofDualScaling:TheKeyIsDuality................................. 105 ShizuhikoNishisato TheMostPredictableCriterionwithFallibleData .......................... 117 Seock-HoKim AsymmetricMultidimensionalScalingofSubjectiveSimilarities AmongOccupationalCategories............................................... 129 AkinoriOkadaandTakuyaHayashi On the Relationship Between Squared Canonical Correlation andMatrixNorm ................................................................ 141 KentaroHayashi,Ke-HaiYuan,andLuLiang BreakingThroughtheSumScoringBarrier.................................. 151 JamesO.RamsayandMarieWiberg Overestimation of Reliability by Guttman’s œ , œ , and œ 4 5 6 andtheGreatestLowerBound................................................. 159 PieterR.Oosterwijk,L.AndriesvanderArk,andKlaasSijtsma ThePerformanceofFiveReliabilityEstimatesinMultidimensional TestSituations.................................................................... 173 ShuyingShaandTerryAckerman WeightedGuttmanErrors:HandlingTiesandTwo-LevelData ........... 183 LettyKoopman,BonneJ.H.Zijlstra,andL.AndriesvanderArk Measuring Cognitive Processing Capabilities in Solving MathematicalProblems......................................................... 191 SusanEmbretson ParameterConstraintsoftheLogitFormoftheReducedRUM........... 207 Hans-FriedrichKöhn HypothesisTestingforItemConsistencyIndexinCognitiveDiagnosis ... 215 LihongSongandWenyiWang IrreplaceabilityofaReachabilityMatrix ..................................... 229 ShuliangDing,WenyiWang,FenLuo,JianhuaXiong,andYaruMeng Ensuring Test Quality over Time by Monitoring the Equating Transformations.................................................................. 239 MarieWiberg AnIllustrationoftheEpanechnikovandAdaptiveContinuization MethodsinKernelEquating.................................................... 253 JorgeGonzálezandAlinaA.vonDavier Contents ix (The Potential for) Accumulated Linking Error in Trend MeasurementinLarge-ScaleAssessments.................................... 263 LaurenHarrell IRTObserved-ScoreEquatingwiththeNonequivalentGroups withCovariatesDesign.......................................................... 275 ValentinaSansivieriandMarieWiberg CausalInferencewithObservationalMultilevelData:Investigating SelectionandOutcomeHeterogeneity......................................... 287 Jee-SeonKim,Wen-ChiangLim,andPeterM.Steiner NonequivalentGroupswithCovariatesDesignUsingPropensity ScoresforKernelEquating ..................................................... 309 GabrielWallinandMarieWiberg AMixturePartialCreditModelAnalysisUsingLanguage-Based Covariates......................................................................... 321 SeohyunKim,MinhoKwak,andAllanS.Cohen Investigating Constraint-Weighted Item Selection Procedures inUnfoldingCAT ................................................................ 335 Ya-HuiSu Rating Scale Format and Item Sensitivity to Response Style inLarge-ScaleAssessments..................................................... 347 SienDengandDanielM.Bolt ModeComparabilityStudiesforaHigh-StakesTestingProgram.......... 357 DongmeiLi,QingYi,andDeborahJ.Harris PowerAnalysisfort-TestwithNon-normalData andUnequalVariances.......................................................... 373 HanDu,ZhiyongZhang,andKe-HaiYuan Statistical Power Analysis for Comparing Means with Binary orCountDataBasedonAnalogousANOVA.................................. 381 YujiaoMaiandZhiyongZhang RobustBayesianEstimationinCausalTwo-StageLeastSquares ModelingwithInstrumentalVariables ........................................ 395 DingjingShiandXinTong MeasuringGritAmongFirst-GenerationCollegeStudents: APsychometricAnalysis........................................................ 407 BrookeMidkiff,MichelleLanger,CynthiaDemetriou,andA.T.Panter AComparisonofItemParameterandStandardErrorRecovery AcrossDifferentRPackagesforPopularUnidimensionalIRTModels ... 421 TaeyoungKimandInsuPaek New Results on an Improved Parallel EM Algorithm for Estimating Generalized Latent Variable Models MatthiasvonDavier Abstract The second generation of a parallel algorithm for generalized latent variablemodels,includingMIRTmodelsandextensions,onthebasisofthegeneral diagnosticmodel(GDM)ispresented.Thisnewdevelopmentfurtherimprovesthe performanceoftheparallel-Eparallel-Malgorithmpresentedinanearlierreportby means of additional computational improvements that produce even larger gains in performance. The additional gain achieved by this second-generation parallel algorithm reaches factor 20 for several of the examples reported with a sixfold gain based on the first generation. The estimation of a multidimensional IRT model for large-scale data may show a larger reduction in runtime compared to a multiple-group model which has a structure that is more conducive to parallel processing of the E-step. Multiple population models can be arranged such that the parallelism directly exploits the ability to estimate multiple latent variable distributionsseparatelyinindependentthreadsofthealgorithm. Keywords Parallel EM-algorithm • MIRT • Diagnostic modeling • Estimation • Latentvariablemodeling 1 Introduction Thischapterreportsonthesecondgenerationofaparallelalgorithmforgeneralized latent variable models on the basis of the general diagnostic model (von Davier 2005,2008,2014).Thisnewdevelopmentfurtherimprovestheperformanceofthe parallel-Eparallel-Malgorithmpresentedinanearlierreport(vonDavier2016)by means of additional computational improvements that produce even larger gains in performance. The additional gain achieved by this second-generation parallel ThisworkwaspartiallycompletedwhiletheauthorwasattheEducationalTestingService. M.vonDavier((cid:2)) NationalBoardofMedicalExaminers,3750MarketStreet,Philadelphia,PA,19104-3102,USA e-mail:[email protected] ©SpringerInternationalPublishingAG2017 1 L.A.vanderArketal.(eds.),QuantitativePsychology,SpringerProceedings inMathematics&Statistics196,DOI10.1007/978-3-319-56294-0_1
Description: