[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-621099-105":59,"doc-detail-621099-en":130},{"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":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","exploring-the-use-of-item-response-theory-models-for-analysing-high-tariff-items-paper","Exploring the use of item response theory models for analysing high-tariff items - paper","","Many high-stakes examinations in the UK combine constructed-response and selected-response items. Growing use of constructed-response questions with high-tariff score categories has increased interest in polytomous item response theory (IRT) models. This study investigates Samejima’s Continuous Response Model (CRM) for high-tariff items where response-category frequencies may be zero. The CRM is evaluated against an extended Nominal Response Model (eNRM) with fixed slopes using simulated data and 2018 data.",{"@graph":69,"@context":122},[70,84,105],{"@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/exploring-the-use-of-item-response-theory-models-for-analysing-high-tariff-items-paper/621099/",{"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/exploring-the-use-of-item-response-theory-models-for-analysing-high-tariff-items-paper/621099.png","ImageObject",300,407,{"name":92,"@type":93},"Fahsai","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-04","2026-10-20",true,{"@type":102,"interactionType":103,"userInteractionCount":44},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"Why are polytomous IRT models needed for high-tariff items?","Question",{"text":112,"@type":113},"High-tariff constructed-response items create many score categories per item, and some categories may never be observed. This motivates the use of polytomous IRT models tailored to such structures.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What problem makes the Partial Credit Model unsuitable for high-tariff items?",{"text":117,"@type":113},"The Partial Credit Model assumes a fixed number of categories. When not all categories are observed for all items, it loses meaning and cannot provide meaningful results.",{"name":119,"@type":110,"acceptedAnswer":120},"How does the study evaluate the CRM against the eNRM?",{"text":121,"@type":113},"The CRM is tested using both simulated data and 2018 data for the referenced GCSE subject. Its performance is compared with an extended Nominal Response Model (eNRM) with fixed slopes.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},621099,1793068547,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":44,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":144,"read_time":145},549768702563,"https://ap-avatar.wpscdn.com/avatar/8000c4aa63b76e948b?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786536092046926083","Exploring the use of item response theory models for analysing high-tariff items  \nYaw Bimpeh  \nAbstract  \nMany high-stakes examinations in the UK use both constructed-response items and selectedresponse items. The increased use of constructed-response items with high-tariff response categories has motivated interest in polytomous item response theory ( IRT) models. Paper 1 for one of AQA’s GCSE qualifications (referred to herein as ‘Subject A’) consists entirely of high-tariff items (e.g. worth 8, 12, 16, 24 marks), resulting in a large number of response categories per item. Furthermore, there is a likelihood that category frequency of responses can be zero for some items. An IRT model like the Partial Credit Model completely fails to provide any meaningful results when applied to high-tariff items. The purpose of this study is to examine the application of Samejima’s Continuous Response Model (CRM) as a suitable measurement model for hightariff items.  \nThis paper discusses the application of the CRM to the high-tariff items data, using both simulated data and 2018 data for Subject A. We compared the performance of the CRM with a new model known as an extended Nominal Response Model (eNRM) with fixed slopes, which has recently been suggested as suitable for high-tariff items in the technical report for the National Reference Test (NFER, 2018) . The results suggest that both the CRM and eNRM models fit these items well. Both approaches can be used with constructed-response items scored externally by human markers.  \nHowever, the empirical evaluation shows that the CRM has some advantages over the eNRM. The CRM method does not require calibration using large numbers of response category parameters per item. One attractive feature of the eNRM approach is its robustness against violation of the postulated population distribution of ability.  \nIntroduction  \nItem response theory (IRT) is one of the test theories that may be applied to assessment data to describe test performance, inferences, and estimates of particular traits or abilities of examinees from responses to test items. It provides a model for explaining exam performance in relation to factors that are understood to influence item response. It also uses the characteristics of the persons and the characteristics of the items to predict response patterns.  \nOne critical task of the application of IRT models in performance assessment is equating scores or linking scales and assessing item bias. The attractive features of IRT models are the capability to provide invariance of item and ability parameter values. The successful use of an IRT model is only realised when the model accurately represents the test data.  \nMany high-stakes examinations in the UK use both constructed-response items and selectedresponse items. The increased use of constructed-response items with high-tariff response categories has motivated interest in polytomous IRT models. Paper 1 for one of AQA’s GCSE qualifications (referred to herein as ‘Subject A’) consists entirely of high-tariff items (e.g. worth 8, 12, 16, 24 marks), resulting in a large number of response categories per item. Furthermore, thereis a likelihood that the category frequency of responses can be zero for some items. An IRT model like the Partial Credit Model (PCM) is not fit for purpose when applied to high-tariff items. It only accepts a fixed number of categories and loses its meaning when not all categories are observed for all items. One approach to this problem is to reduce by one the score of each category above the not-observed category, for any item in any category. For example, an item with category scores 0, 1 , 2, 3, 4, 5, 6, 7, 8, 9 , 10 in which category 2, 3, 7 are never observed would become a new item with scores 0, 1, 2, 3, 4, 5, 6, 7. According to Wilson and Masters (1993) , this is often not a good idea. To address this problem, they proposed treating the item with a Nominal Response Model (NRM) with fixed slo","cbCaiq7a7TrlT1Ha","https://ap.wps.com/l/cbCaiq7a7TrlT1Ha","pdf",774566,31,"English","# Introduction\n## Item response theory and polytomous models\n## Challenges with high-tariff response categories\n# Continuous Response Model (CRM)\n## Framework for high-tariff item analysis\n## Parameter estimation benefits\n# Empirical evaluation and comparison","[{\"question\":\"Why are polytomous IRT models needed for high-tariff items?\",\"answer\":\"High-tariff constructed-response items create many score categories per item, and some categories may never be observed. This motivates the use of polytomous IRT models tailored to such structures.\"},{\"question\":\"What problem makes the Partial Credit Model unsuitable for high-tariff items?\",\"answer\":\"The Partial Credit Model assumes a fixed number of categories. When not all categories are observed for all items, it loses meaning and cannot provide meaningful results.\"},{\"question\":\"How does the study evaluate the CRM against the eNRM?\",\"answer\":\"The CRM is tested using both simulated data and 2018 data for the referenced GCSE subject. Its performance is compared with an extended Nominal Response Model (eNRM) with fixed slopes.\"}]","Exploring the use of item response theory models for analysing high-tariff items - paper | PDF",1792464951,78]