[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-528442-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-528442-en":130},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","a-comparative-study-of-online-pretest-item-calibration-scaling-methods-in-cat","A Comparative Study of Online Pretest Item Calibration-Scaling Methods in CAT","","A comparative study evaluates five online pretest item calibration/scaling approaches used in computerized adaptive testing (CAT), including OEM (one EM cycle), MEM (multiple EM cycles), Stocking’s Method A, Stocking’s Method B, and the BILOG/Prior method. Item parameter recovery is tested under three sample-size conditions (300, 1,000, 3,000). Results indicate MEM yields the smallest parameter estimation errors across all conditions, while Stocking’s Method B performs well but needs anchor items.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/a-comparative-study-of-online-pretest-item-calibration-scaling-methods-in-cat/528442/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/a-comparative-study-of-online-pretest-item-calibration-scaling-methods-in-cat/528442.png","ImageObject",300,407,{"name":42,"@type":43},"Fahsai","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-10","2026-10-09",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",8,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"Which online pretest item calibration/scaling methods are compared in the study?","Question",{"text":63,"@type":64},"The study compares OEM (one EM cycle), MEM (multiple EM cycles), Stocking’s Method A, Stocking’s Method B, and the BILOG/Prior method.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How are the methods evaluated?",{"text":68,"@type":64},"Evaluation is based on item parameter recovery under three sample-size conditions: 300, 1,000, and 3,000.",{"name":70,"@type":61,"acceptedAnswer":71},"What method performs best overall, and why?",{"text":72,"@type":64},"The MEM method appears to be the best choice because it produces the smallest parameter estimation errors across all sample sizes.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},528442,1791733021,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,114,119,122,126],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":112,"slug":113},30,"research-report",{"id":115,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":55,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":139,"language":140,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":12,"update_tm":144,"read_time":145,"preview_page_count":33,"preview_urls":146},549768702563,"https://ap-avatar.wpscdn.com/avatar/8000c4aa63b76e948b?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786536092046926083","# A Comparative Study of\n\nOnline Pretest Item Calibration/Scaling Methods in CAT  \nJae-Chun BanBradley A.HansonTianyou WangQing YiDeborah J.Harris  \nFor additional copies write:ACT Research Report SeriesPO Box 168lowa City,Iowa 52243-0168  \n⑥2000 by ACT,Inc.All rights reserved.  \n# A Comparative Study of Online Pretest ItemCalibration/Scaling Methods in CAT\n\nJae-Chun BanBradley A.HansonTianyou WangQing YiDeborah J.Harris  \nAbstract  \nThe purpose of this study was to compare and evaluate five onlinc pretest itemcalibration/scaling methods in computerized adaptive testing(CAT):the marginal maximumlikelihood estimate with one EM cycle(OEM)method,thc marginal maximum likelihoodestimatc with multiplc EM cycles(MEM)method,Stocking's Method A,Stocking's Method B,and the BILOG/Prior method.The five methods werc evaluated in terms of item parameterrccovery under threc different sample size conditions(300,1,000,and 3,000).The MEMmethod appcars to be the best choice among the methods used in this study,because it producedthe smallcst paramcter estimation errors for all sample size conditions.Stocking's Method Balso worked very well,but it requires anchor items,which would make tcst lengths longer.TheBILOG/Prior method did not seem to work with small sample sizes.Until more appropriateways of handling the sparse data with BILOG arc devised,the BILOG/Prior method may not bea reasonable choice.Because Stocking's Method A has the largest weighted total error,as wellas a thcorctical weakness(i.c.,treating estimated ability as true ability),there appears to be littlereason to usc it.The MEM method should be preferred to the OEM method unless amount oftime involved in iterative computation is a great concern.Otherwise,the OEM method and theMEM method arc mathematically similar,and the OEM method produces larger crrors than the  \nMEM mcthod.  \nA Comparative Study of Online Pretest Item Calibration/Scaling Methods in CAT  \n## Introduction\n\nIn computerized adaptive testing(CAT),pool replenishing is a necessary process formaintaining an item pool because items in the pool would be obsolete or overexposed as timegoes on.To be added as new items in the pool,the pretest items should be calibrated and be onthe same scale as items already in the pool.  \nOnline calibration refers to estimating the parameters of pretest items which are presentedto examinees during the course of their testing with operational items (Stocking,1988:Wainer &Mislevy,1990).Since the item parameter estimates obtained from the paper and pencil dcliverymode are not necessarily comparable to the item parameter estimates calibrated from the CATmode,duc to such factors as item ordering,different mode of test administration,context,localitem dependency,and cognitive difference(Parshall,1998;Spray,Parshall,&Huang,1997),pretest item calibration/scaling methods that utilize the online testing system should bedeveloped.  \nThe complication in online pretest item calibration results from the fact that,typically,item response data obtained from CAT administrations are sparse,based on a restricted range ofability(Folk &Golub-Smith,1996;Haynic &Way,1995;Hsu,Thompson,&Chen,1998;Stocking,1988),and a relatively small number of items are administered compared to the paperand pencil delivery mode.These data characteristics may lead to inaccuratc item parameterestimates for the pretest items.Nevertheless,the online pretest item calibration/scaling hasseveral advantages such as prcserving testing mode and utilizing the pretest data obtained duringoperational testing,and reducing the impact of motivation and representativeness concernscoming from the administration of pretest items to volunteers(Parshall,1998).  \n2  \nSeveral studics have proposed onlinc pretest item calibration methods(Folk &Golub-Smith,1996;Levine &Willams,1998;Samejima,2000;Stocking,1988:Wainer &Mislevy,1990).Among them,some methods involve using parametric item response functions in whichprctest itcm characteristic curves are estim","cbCaiiITUEWgoT3M","https://ap.wps.com/l/cbCaiiITUEWgoT3M","pdf",1151869,32,"English","# Introduction\n## Online Pretest Item Calibration Methods\n### One-EM Cycle Method","[{\"question\":\"Which online pretest item calibration/scaling methods are compared in the study?\",\"answer\":\"The study compares OEM (one EM cycle), MEM (multiple EM cycles), Stocking’s Method A, Stocking’s Method B, and the BILOG/Prior method.\"},{\"question\":\"How are the methods evaluated?\",\"answer\":\"Evaluation is based on item parameter recovery under three sample-size conditions: 300, 1,000, and 3,000.\"},{\"question\":\"What method performs best overall, and why?\",\"answer\":\"The MEM method appears to be the best choice because it produces the smallest parameter estimation errors across all sample sizes.\"}]","A Comparative Study of Online Pretest Item Calibration-Scaling Methods in CAT | PDF",1791518825,81,[147,151,155,159],{"page_no":22,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/e2be47a15ddbe0a81121f2c2aedae4b4.webp",983,1277,{"page_no":26,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/c610692346b96d06dc16f5c12278c84f.webp",982,1266,{"page_no":30,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/354a12a7445cd58d8df968e38b90dbf4.webp",981,1300,{"page_no":33,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/76c960438146f458123c8a66bf749ec6.webp",980,1302]