[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-528482-105":59,"doc-detail-528482-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","irt-scale-linking-methods-for-mixed-format-tests-research-report-summary","IRT Scale Linking Methods for Mixed-Format Tests - Research Report Summary","","Item Response Theory (IRT) requires a common proficiency scale for many testing applications, but different item formats complicate scale alignment. This paper develops and extends four IRT scale linking approaches—mean/mean, mean/sigma, Haebara, and Stocking-Lord—from dichotomous contexts to mixed-format tests. It covers mixtures of five unidimensional IRT models, including 3PL, graded response, generalized partial credit, nominal response, and multiple-choice models. A simulation study evaluates linking accuracy and discusses limitations under nominal-response and multiple-choice analyses.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/irt-scale-linking-methods-for-mixed-format-tests-research-report-summary/528482/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/irt-scale-linking-methods-for-mixed-format-tests-research-report-summary/528482.png","ImageObject",300,407,{"name":92,"@type":93},"วิน","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-10","2026-10-09",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",11,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"Why is common proficiency scale linking necessary in IRT?","Question",{"text":113,"@type":114},"IRT defines a proficiency scale only up to an arbitrary linear transformation, so linking is needed to place different test forms onto a common scale.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"Which four scale linking methods are extended in this paper?",{"text":118,"@type":114},"The paper extends mean/mean, mean/sigma, Haebara, and Stocking-Lord methods to mixed-format tests.",{"name":120,"@type":111,"acceptedAnswer":121},"How does the simulation study compare the methods’ performance?",{"text":122,"@type":114},"Overall, Haebara and Stocking-Lord produce more accurate linking results than mean/mean and mean/sigma methods for mixed-format tests.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},528482,1791586212,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":145,"read_time":146,"preview_page_count":29,"preview_urls":147},2336475104736,"https://ap-avatar.wpscdn.com/avatar/22000c4c5e0e5b17e70?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786591360781797222","IRT Scale Linking Methods forMixed-Format Tests  \nSeonghoon Kim  \nWon-Chan Lee  \nFor additional copies write:ACT Research Report SeriesPO.Box 168Iowa City,Iowa 52243-0168  \n◎2004 by ACT,Inc.Alt rights reserved.  \nIRT Scale Linking Methods for Mixed-Format Tests  \nSeonghoon KimThe University of lowa  \nWon-Chan Lee  \nACT  \nContents  \nPage  \nAbstract………………………………………………………………………………………………………………………………………………………………iv  \nIntroduction…………………………………………………………………………………………………………………………………………………………1  \nScale Linking Under a Mixture of IRT Models………………………………………………………………………………………3  \nIRT Models for Subtests of a Mixed-Format Test……………………………………………………………………………3  \nThree-parameter logistic mode………………………………………………………………………………………4  \nGraded response model…………………………………………………………………………………………………………4  \nGeneralized partial credit model………………………………………………………………………………………5  \nNominal response mode………………………………………………………………………………………………………5  \nMultiple-choice model…………………………………………………………………………………………………………5  \nDichotomous IRT Models Revisited…………………………………………………………………………………………………………6  \nThe Nature of Scale Linking Through Common Items………………………………………………………………7  \nMoment Methods: Mean/Mean and Mean/Sigma Methods…………………………………………………9  \nMean/mean method……………………………………………………………………………………………………………………10  \nMean/sigma method………………………………………………………………………………………………………10  \nCharacteristic Curve Methods: Haebara and Stocking-Lord Methods……………………………11  \nHaebara method………………………………………………………………………………………………………………………………………12  \nStocking-Lord method……………………………………………………………………………………………………14  \nSimulation Study………………………………………………………………………………………………………………………………………………16  \nFactors Investigated……………………………………………………………………………………………………………………………………17  \nEquivalent versus nonequivalent groups linking……………………………………………………17  \nSample size………………………………………………………………………………………………………………………18  \nTypes of mixed-format test………………………………………………………………………………………………18  \nTypes of linking through different anchor item sets……………………………………………19  \nComputer programs for calibration(MULTILOG versus PARSCALE)………19  \nData Generation…………………………………………………………………………………………………………………………………………………20  \nTrue item parameters by model…………………………………………………………………………………20  \nDichotomous and graded response data…………………………………………………………………20  \nComputer Software for Scale Linking Methods…………………………………………………………………21  \nEvaluation Criteria……………………………………………………………………………………………………………………………………………21  \nResults…………………………………………………………………………………………………………………………………………………………………23  \nEquivalent versus Nonequivalent Groups……………………………………………………………………………24  \nSample Size…………………………………………………………………………………………………………………………………24  \nTest Types and Linking Types………………………………………………………………………………………………25  \nMULTILOG versus PARSCALE………………………………………………………………………………………………26  \nSummary and Discussion……………………………………………………………………………………………………………………………27  \nReferences…………………………………………………………………………………………………………………………………………………………30  \nAppendix A…………………………………………………………………………………………………………………………………………………………33  \nAppendix B………………………………………………………………………………………………………………………………………………………34  \nTables……………………………………………………………………………………………………………………………………………………………………35  \nFigures…………………………………………………………………………………………………………………………………………………………………36  \nAbstract  \nUnder item response theory(IRT),obtaining a common proficiency scale is required inmany applications.Four IRT linking methods,including the mean/mean,mean/sigma,Haebara,and Stocking-Lord methods,have been developed and widely used to estimate linkingcoefficients(slope and intercept)for a linear transformation from one scale to another.Thesefour methods have typically been used for dichotomous IRT models but can also be extended topolytomous IRT models.This paper further extends the four linking methods to a mixture ofunidimensional IRT models for mixed-format tests.The development in the present study isintended to be as general as possible so that each linking method can be applied to mixed-formattests using any mixture of the following five IRT models:the three-parameter logistic model,thegraded response model,t","cbCaijugWy1mHapa","https://ap.wps.com/l/cbCaijugWy1mHapa","pdf",1539360,56,"English","# Abstract\n# Introduction\n## Scale Linking Under a Mixture of IRT Models\n## IRT Models for Subtests of a Mixed-Format Test\n## Dichotomous IRT Models Revisited\n# Moment Methods and Characteristic Curve Methods\n## Haebara and Stocking-Lord Methods\n# Simulation Study\n## Equivalent vs nonequivalent groups linking\n## Sample size and test types\n# Evaluation Criteria and Results\n# Summary and Discussion\n# References","[{\"question\":\"Why is common proficiency scale linking necessary in IRT?\",\"answer\":\"IRT defines a proficiency scale only up to an arbitrary linear transformation, so linking is needed to place different test forms onto a common scale.\"},{\"question\":\"Which four scale linking methods are extended in this paper?\",\"answer\":\"The paper extends mean/mean, mean/sigma, Haebara, and Stocking-Lord methods to mixed-format tests.\"},{\"question\":\"How does the simulation study compare the methods’ performance?\",\"answer\":\"Overall, Haebara and Stocking-Lord produce more accurate linking results than mean/mean and mean/sigma methods for mixed-format tests.\"}]","IRT Scale Linking Methods for Mixed-Format Tests - Research Report Summary | PDF",1791518889,141,[148,152,156,160,164,168],{"page_no":8,"url":149,"width":150,"height":151},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/e3a79caa0147bb200666b15adb18d986.webp",983,1289,{"page_no":14,"url":153,"width":154,"height":155},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/2c90a65ed44f84c696d3aa8112d4375b.webp",982,1286,{"page_no":81,"url":157,"width":158,"height":159},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/bebed3078b75dd0e5a49ab59427223b2.webp",981,1301,{"page_no":19,"url":161,"width":162,"height":163},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/85d7cfbfe719080bb2250e4749a987c1.webp",980,1300,{"page_no":24,"url":165,"width":166,"height":167},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/faf255cb48e10b9ff37b2e4fb3fa4c92.webp",979,1299,{"page_no":29,"url":169,"width":170,"height":171},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/2e1542b93f798d4c314ed3b67986a3f7.webp",978,1297]