[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-578509-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-578509-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","examining-the-effect-of-item-difficulty-and-rater-leniency-on-iranian-test-takers-performance-on-wdct-and-dsat-a-comparative-study","Examining the Effect of Item Difficulty and Rater Leniency on Iranian Test Takers’ Performance on WDCT and DSAT - A Comparative Study","","Investigating how item difficulty and rater leniency shape assessment outcomes, the study applies the Many Facet Rasch Model to compare the Written Discourse Completion Test (WDCT) and Discourse Self-Assessment Tests (DSAT). Participants included 110 Iranian EFL students. Students completed WDCT and self-rated on DSAT, while four raters scored WDCT. FACETS results reveal systematic differences and distinct difficulty patterns across methods, supporting pragmatic ability measurement while highlighting DSAT fitness concerns and unpredictable DSAT rating patterns.",{"@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/examining-the-effect-of-item-difficulty-and-rater-leniency-on-iranian-test-takers-performance-on-wdct-and-dsat-a-comparative-study/578509/",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/examining-the-effect-of-item-difficulty-and-rater-leniency-on-iranian-test-takers-performance-on-wdct-and-dsat-a-comparative-study/578509.png","ImageObject",300,407,{"name":42,"@type":43},"Hazel","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-16","2026-10-15",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",10,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What model and tests are used in the study?","Question",{"text":63,"@type":64},"The study uses the Many Facet Rasch Model and examines performance on the Written Discourse Completion Test (WDCT) and the Discourse Self-Assessment Tests (DSAT).","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"Who participated and how were they assessed?",{"text":68,"@type":64},"A total of 110 Iranian EFL students completed WDCT and provided self-ratings on DSAT. Four raters scored the WDCT responses.",{"name":70,"@type":61,"acceptedAnswer":71},"What do the results suggest about WDCT and DSAT?",{"text":72,"@type":64},"Both DSAT and WDCT are acceptable measures for pragmatic ability, but DSAT shows fitness problems and an unpredictable pattern of ratings, indicating issues in the self-assessment process.","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},578509,1792210511,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,120,123,126],{"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":112,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":113,"slug":114},8,30,"research-report",{"id":116,"doc_module":4,"doc_module_name":25,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":25,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":55,"slug":125},"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":112,"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":127,"language":139,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":12,"update_tm":143,"read_time":144,"preview_page_count":4},137441390410,"https://ap-avatar.wpscdn.com/avatar/2000252f4ab5702993?_k=1776741390130283984","Examining the Effect of Item Difficulty and Rater Leniency on Iranian Test Takers’ Performance on WDCT and DSAT: A Comparative Study  \nReza Shahi 1, Hamdollah Ravand *2, Golam Reza Rohani3  \n| ARTICLE INFO   ABSTRACT  |  |\n| --- | --- |\n| \u003Cbr>Article History:\u003Cbr>Received: April 2024\u003Cbr>Accepted: May 2024\u003Cbr>| \u003Cbr>The current paper intends to exploit the Many Facet Rasch Model to investigate and compare the impact of situations (items) and raters on test takers' performance on the Written Discourse Completion Test (WDCT) and Discourse Self-Assessment Tests (DSAT) . In this study, the participants were 110 English as a Foreign Language (EFL) students at Vali-e-Asr University of Rafsanjan in Iran. The students were asked to complete the WDCT and rate themselves on that test. Four raters scored the WDCT tests. According to the FACETS results, there were significant differences in students'performance between the two methods. The stable fit statistics and differing levels of difficulty measures for each test method indicated that each test had a unique way of differentiating the test taker's pragmatic ability. Based on the results, both DSAT and WDCT are acceptable measures for pragmatic ability; however, there are some fitness problems in DSAT. This shows the unpredictable pattern of ratings in the DSAT. It is recommended to have rater training to obtain more accurate\u003Cbr>Finally the implications discussed |\n| \u003Cbr>KEYWORDS\u003Cbr>DSAT\u003Cbr>Many Facet Rasch Model Pragmatic test WDCT\u003Cbr>|  |\n|  | results from the DSAT. , were . |\n\n1. Introduction  \nOver the last few decades, pragmatics has turned into a field that attracts considerable attention in language teaching research (Mao & He, 2021; Purpura, 2017), and a large array of research studies on pragmatics assessment have significantly contributed to the advancement of researchers’understandings of pragmatics as an assessment construct (Roever ,2011; Youn, 2015) . To date, researchers have developed and validated some tests for measuring different aspects of pragmatic competence. However, measures are prone to contamination by factors other than the construct being measured.  \nConstruct-irrelevant factors impair validity by adding systematic error variation to scores. This shows that we can increase validity if we can lessen the influence of construct-irrelevant elements (Wise, 2019). To identify and minimize the impact of the construct irrelevant factors on pragmatics, researchers have started to examine the role of various factors involved in assessing second /foreign language pragmatics, such as the rater role (e.g., Alemi & Rezanejad, 2014; Dabbagh& Babaii,2021; Li et al., 2023; Liu & Xie, 2014; Sydorenko et al., 2014; Taguchi, 2011; Sonnenburg-Winkle et al., 2020; Tajeddin & Alemi, 2014; Walters, 2007), impacts of test takers’ characteristics on test functioning (Roever, 2013; Youn & Brown, 2013), development and validation of rating scale (e.g., Chen & Liu, 2016; Derakhshan et al., 2020; Li et al., 2019; Su & Shin, 2024; Youn, 2015), and the function of items (e.g., Cordier et al., 2019; Roever, 2008) .  \nDespite this increasing attention, the research on assessing the impact of construct irrelevant factors is mostly limited to some factors, including raters and rating scale functions (e.g., Brown & Ahn, 2012; Li et al., 2023; Liu, 2006; Liu & Xie, 2014; Tajeddin & Alemi, 2014; Youn, 2007) . In addition,  \n1 PhD, Ilam University, Ilam, Iran, [Email: Reza.Shahi411@gmail.com](Email: Reza.Shahi411@gmail.com)  \n2 Associate professor, Vali-e-Asr University of Rafsanjan, Kerman, Iran, [Email:](Email: Ravand@vru.ac.ir)[ ](Email: Ravand@vru.ac.ir)[Ravand@vru.ac.ir](Email: Ravand@vru.ac.ir)  \n3 Assistant professor, Shahid Bahonar University of Kerman, Iran, Email: [r.rohani@uk.ac.ir](r.rohani@uk.ac.ir)  \n[Cite this paper as: Shahi](Cite this paper as: Shahi), [R](R)., [Ravand](Ravand), H., & Rohani, G. R. (2025). Examining the effect of item difficulty andrater leniency on Iranian test take","cbCaid4qZstVM0XC","https://ap.wps.com/l/cbCaid4qZstVM0XC","pdf",485323,"English","# Abstract\n# Introduction\n## Effective Factors on Testing\n# Background of the Study","[{\"question\":\"What model and tests are used in the study?\",\"answer\":\"The study uses the Many Facet Rasch Model and examines performance on the Written Discourse Completion Test (WDCT) and the Discourse Self-Assessment Tests (DSAT).\"},{\"question\":\"Who participated and how were they assessed?\",\"answer\":\"A total of 110 Iranian EFL students completed WDCT and provided self-ratings on DSAT. Four raters scored the WDCT responses.\"},{\"question\":\"What do the results suggest about WDCT and DSAT?\",\"answer\":\"Both DSAT and WDCT are acceptable measures for pragmatic ability, but DSAT shows fitness problems and an unpredictable pattern of ratings, indicating issues in the self-assessment process.\"}]","Examining the Effect of Item Difficulty and Rater Leniency on Iranian Test Takers’ Performance on WDCT and DSAT - A Comparative Study | PDF",1792033883,48]