[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-267276-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-267276-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","investigating-generative-factors-of-score-matrices","Investigating Generative Factors of Score Matrices","","An implicit assumption in psychometrics and educational statistics is that the generative model for student scores on test questions is driven by question topics and each student’s aptitude in those topics. This paper analyzes university-level computer science score matrices and shows that no such topic-based structure can be extracted from the data. Using unsupervised machine learning, it provides evidence that challenges this foundational assumption in educational statistics.",{"@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/investigating-generative-factors-of-score-matrices/267276/",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/investigating-generative-factors-of-score-matrices/267276.png","ImageObject",300,407,{"name":42,"@type":43},"Levi","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-24","2026-09-14",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",6,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What core assumption does the paper investigate about score matrices?","Question",{"text":63,"@type":64},"It investigates the assumption that the generative model for a score matrix is determined by the topics of the test questions and each student’s aptitude in those topics.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"What do the authors conclude from their analysis of university-level CS datasets?",{"text":68,"@type":64},"They demonstrate that no topic-based structure can be extracted from these score matrices, and that common assumptions may not hold for naturally arising datasets.",{"name":70,"@type":61,"acceptedAnswer":71},"What methods are used to provide evidence against the assumption?",{"text":72,"@type":64},"The paper uses unsupervised machine learning techniques to analyze the score matrices and assess whether topic-related structure can be found.","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},267276,1789416595,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,105,110,114,119,122,126],{"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":55,"doc_module":4,"doc_module_name":25,"category_name":102,"show_sort_weight":103,"slug":104},"Technology",50,"technology",{"id":106,"doc_module":4,"doc_module_name":25,"category_name":107,"show_sort_weight":108,"slug":109},7,"Healthcare",40,"healthcare",{"id":111,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":112,"slug":113},8,30,"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":111,"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":111,"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":80,"read_time":117,"preview_page_count":4},7971461740909,"https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d","Book Title  \nBook Editors IOS Press, 2003  \n1  \nInvestigating Generative Factors of Score  \nMatrices  \nTitus Winters a ; 1 , Christian R. Shelton a and Tom Payne aa UC Riverside, Riverside CA, USA  \nAbstract. An implicit assumption in psychometrics and educational statistics is that the generative model for student scores on test questions is governed by the topics of those questions and each student's aptitude in those topics. That is, a function to generate the matrix of scores for m students on n questions should rely on each student's ability in a set of t topics, and the relevance of each question to those topics. In this paper, we investigate score matrices from university-level computer science courses, and demonstrate that no such structure can be extracted from this data. Utilizing unsupervised machine learning techniques we provide evidence  \ncalling into question this fundamental assumption of educational statistics.  \nKeywords. Cognitive Science, Clustering, Dimensionality reduction, Educational  \nData Mining  \n1. Introduction  \nOver the past century, psychometrics has utilized mathematical techniques to extract meaning from collections of educational data. One of the most common data types in psychometrics is the score matrix, storing the scores for a collection of students on each question from a test. Commonly, educational researchers will apply algorithms developed in the early 20th century to discover the structure or generative model of these matrices. While advanced for their time, and sufficient for some problem types, the great advances made in machine learning may have surpassed these techniques, and may even invalidate some of the assumptions made by early psychometric techniques.  \nThis paper presents an investigation into the generative model of score matrices recorded in computer science (CS) courses in our department. Here we apply machine learning techniques to this canonical psychometric problem and show that on some naturally-arising datasets, the assumptions made for the past century may not be valid.  \nSpecifically, this paper investigates the assumption that a generative model for ascore matrix should take into account the topics being covered on the test. From our investigations on course data, the factors that are considered most important by machine learning algorithms consistently have no relationship with human-identified topics.  \n2. Psychometrics  \nAt its root, the quantitative branch of education that is most applicable to machine learning and educational data mining is psychometrics. Psychometrics focuses on measuring  \n1 Correspondence to: Tel.: +1 909 262 0385; E-mail: [titus@cs.ucr.edu](titus@cs.ucr.edu).  \n2 T. Winters et al. / Factors of Score Matrices  \nTable 1. Descriptions of datasets. MC indicates multiple choice questions, FR indicates free-response questions subjectively graded, PC indicates partial-credit.  \n\n| Data set | Course | m | n | Question Types | Scores |\n| --- | --- | --- | --- | --- | --- |\n| 008 | Intro Computing | 269 | 80 | MC | Binary |\n| 010 | CS 1 | 190 | 68 | MC | Binary |\n| 141 | Algorithms | 19 | 15 | FR | PC |\n| 153 | O. S. | 66 | 34 | MC,FR | Binary,PC |\n| 164 | Networks | 23 | 72 | MC,FR | Binary,PC |\n| Academic | Online | 267 | 40 | FR | Binary |\n| Trivia | Online | 467 | 40 | FR | Binary |\n\nlatent quantities of knowledge and ability in the human mind [1] . These are difficult values to quantify, as there is no direct way to measure them and no implicit units or dimensionality to such a measurement.  \nOne of the most important developments in psychometrics was the development of common factor analysis (CFA), which became the primary area of research in psychometrics for half a century [2] . The dominant theory at the time was that intelligence was univariate (g-theory) . However, some data simply did not match the proposed model. Utilizing then-new techniques for calculating correlations between measured values, Charles Spearman developed common factor a","cbCaitlp1FmmsUKN","https://ap.wps.com/l/cbCaitlp1FmmsUKN","pdf",288621,"English","# Abstract\n# 1. Introduction\n# 2. Psychometrics\n# 3. Datasets","[{\"question\":\"What core assumption does the paper investigate about score matrices?\",\"answer\":\"It investigates the assumption that the generative model for a score matrix is determined by the topics of the test questions and each student’s aptitude in those topics.\"},{\"question\":\"What do the authors conclude from their analysis of university-level CS datasets?\",\"answer\":\"They demonstrate that no topic-based structure can be extracted from these score matrices, and that common assumptions may not hold for naturally arising datasets.\"},{\"question\":\"What methods are used to provide evidence against the assumption?\",\"answer\":\"The paper uses unsupervised machine learning techniques to analyze the score matrices and assess whether topic-related structure can be found.\"}]","Investigating Generative Factors of Score Matrices | PDF"]