[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-528460-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-528460-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","data-sparseness-and-online-pretest-item-calibration-scaling-methods-in-cat","Data Sparseness and Online Pretest Item Calibration - Scaling Methods in CAT","","This study compares three online pretest item calibration and scaling methods for computerized adaptive testing (CAT) under sparse item response conditions. Item parameter recovery accuracy is evaluated through simulations using three approaches: OEM with one EM cycle, MEM with multiple EM cycles, and Stocking’s Method B. MEM produces the smallest total error in recovering 240 pretest item characteristic curves and maintains scale best; OEM shows larger parameter errors and notable scale deviation.",{"@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/data-sparseness-and-online-pretest-item-calibration-scaling-methods-in-cat/528460/",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/data-sparseness-and-online-pretest-item-calibration-scaling-methods-in-cat/528460.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},"What is the main goal of the study?","Question",{"text":63,"@type":64},"To compare and evaluate three online pretest item calibration/scaling methods in terms of item parameter recovery when responses to pretest items are sparse.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"Which method performed best for recovering pretest item characteristic curves?",{"text":68,"@type":64},"The MEM method produced the smallest average total error when recovering the 240 pretest item characteristic curves.",{"name":70,"@type":61,"acceptedAnswer":71},"How does scale maintenance differ among the methods?",{"text":72,"@type":64},"MEM and Stocking’s Method B perform well in keeping the pretest item scale aligned with the true parameters, while OEM shows scale deviations from the true parameters.","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},528460,1791754224,{"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","# Data Sparseness and Online\n\nPretest Item Calibration/ScalingMethods in CAT  \nJae-Chun BanBradley A.HansonQing YiDeborah J.Harris  \nFor additional copies write:ACT Research Report SeriesPO.Box 168Iowa City,Iowa 52243-0168  \n◎2002 by ACT,Inc.All rights reserved.  \n## Data Sparseness and Online Pretest ItemCalibration/Scaling Methods in CAT\n\nJae-Chun Ban  \nBradley A.Hanson  \nQing Yi  \nDeborah J.Harris  \nAbstract  \nThe purpose of this study was to compare and evaluate three online pretest itemcalibration/scaling methods in terms of item parameter recovery when the item responses to thepretest items in the pool would be sparse.The three methods considered were the marginalmaximum likelihood estimate with one EM cycle(OEM)method,the marginal maximumlikelihood estimate with multiple EM cycles(MEM)method,and Stocking's Method B.Thethree methods were evaluated using simulations of data from computerized adaptive tests(CAT).  \nThe MEM method produced the smallest average total error in recovering the 240 pretestitem characteristic curves.Stocking's Method B yielded the second smallest average total errorin parameter estimation.The OEM method yielded a large average total error in parameterestimation.In terms of scale maintenance,the MEM method and Stocking's Method Bperformed well in keeping the scale of the pretest items on the same scale as that of the trueparameters.With the OEM method,the scale of the pretest item parameter estimates deviatedfrom that of the true parameters.  \nData Sparseness and Online Pretest ItemCalibration/Scaling Methods in CAT  \nCalibrating pretest items is a necessary part of a large computerized adaptive testing(CAT)program.Collecting online pretest item responses and calibrating the pretest items basedon those responses are a way of replenishing an item pool.Online pretest item calibration refersto estimating the parameters of the pretest items that are presented to examinees along withoperational items under CAT or computer based testing(CBT).Several studies have proposedonline pretest item calibration methods (Ban,Hanson,Wang,Yi,&Harris,2000;Stocking,1988;Wainer &Mislevy,1990)using parametric item response functions in which pretest itemcharacteristic curves are estimated through a specific mathematical model such as a three-parameter logistic(3-PL)item response theory(IRT)model.  \nWhen pretest items are administered with operational items,item responses on the pretestitems as well as the operational items are,typically,sparse.That is,not all examinees respond toall items.The sparse item response data is one of the challenges to accurately calibrating pretestitem parameters(Ban et al.,2000;Haynie &Way,1995;Hsu,Thompson,&Chen,1998;Stocking,1988).Hsu et al.(1998)compared the precision of item parameter estimates obtainedunder the sparse matrix to that of estimates calibrated under the item-examinee full matrix.Theyshowed that using a pretest item calibration method,the sparse data lowers the precision of itemparameter estimates.  \nIn realistic settings,sparse data may exist for both the pretest item responses and theoperational item responses.When there is a pretest item pool,each examinee may take only asubset of the pretest items in the pool.If the examinees were administered different sets ofpretest items,the item responses to the pretest items in the pool would be sparse.Due to thenature of a CAT,operational item responses are also sparse.  \n2  \nBan et al.(2000)compared and evaluated five pretest item calibration methods withdifferent sample sizes in terms of item parameter recovery when there was sparse data only onoperational items:the marginal maximum likelihood estimate with one EM cycle(OEM)method(Wainer &Mislevy,1990),the marginal maximum likelihood estimate with multiple EM cycles(MEM)method (Ban et al.,2000),BILOG with Strong Priors(Ban et al.,2000),Stocking'sMethod A(Stocking,1988),and Stocking's Method B(Stocking,1988).They reported that theMEM method and Stocking's Method B worked very well","cbCaifJbz9QEvUzT","https://ap.wps.com/l/cbCaifJbz9QEvUzT","pdf",907207,28,"English","# Abstract\n# Data Sparseness and Online Pretest Item Calibration/Scaling Methods in CAT\n# A Brief Review of Pretest Item Calibration Methods\n## The OEM Method\n## The MEM Method","[{\"question\":\"What is the main goal of the study?\",\"answer\":\"To compare and evaluate three online pretest item calibration/scaling methods in terms of item parameter recovery when responses to pretest items are sparse.\"},{\"question\":\"Which method performed best for recovering pretest item characteristic curves?\",\"answer\":\"The MEM method produced the smallest average total error when recovering the 240 pretest item characteristic curves.\"},{\"question\":\"How does scale maintenance differ among the methods?\",\"answer\":\"MEM and Stocking’s Method B perform well in keeping the pretest item scale aligned with the true parameters, while OEM shows scale deviations from the true parameters.\"}]","Data Sparseness and Online Pretest Item Calibration - Scaling Methods in CAT | PDF",1791518855,71,[147,151,155,159],{"page_no":22,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/3b4f997112b685672e5ef584deed5127.webp",983,1260,{"page_no":26,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/1363f29f473721466ac4f3f0e7711397.webp",982,1275,{"page_no":30,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/d23129815839237dc7d57af2fd7f8813.webp",981,1300,{"page_no":33,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/4a9cdde6c2c02295b5470ac4a6c4357b.webp",980,1310]