[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128347-en":3,"doc-seo-128347-105":31,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},128347,962085564549,"Genevieve","https://ap-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",8,"Research & Report","Machine Learning Approaches to Latent Variable Modeling - Dissertation","This dissertation investigates approaches for dealing with bias in multidimensional item response theory (IRT) models, focusing on nonparametric, tree-based machine learning methods. It develops procedures to estimate model parameters and latent variable scores while accounting for how measured and unmeasured covariates can distort parameter estimation. The work covers latent item effect variables for longitudinal models, model-based recursive partitioning to control differential item functioning, ensemble-based unbiased latent score estimation, and efficient computation of parameter instability tests for ordinal factor models.","Machine Learning Approaches to Latent Variable Modeling  \nFranz Classe  \nM¨unchen 2025  \nMachine Learning Approaches to Latent Variable Modeling  \nFranz Classe  \nDissertation  \nan der Fakult¨at f¨ur Mathematik, Informatik und Statistik der Ludwig–Maximilians–Universit¨at M¨unchen  \nvorgelegt von  \nFranz Classe  \naus N¨urnberg  \nM¨unchen, den 06.03.2025  \nErstgutachter: Prof. Dr. Frauke Kreuter  \nZweitgutachter: Prof. Dr. Daniel Oberski Tag der m¨undlichen Pr¨ufung: 25.07.2025  \nAcknowledgements  \nI would like to express my sincere gratitude to everyone who contributed to this dissertation. Special thanks go to...  \n... Prof. Dr. Christoph Kern for always taking time to advise and to support me on all kinds of research ideas. Thank you for introducing me to the world of algorithmic modeling and machine learning. Without your backing, this dissertation would not have been possible.  \n... Prof. Dr. Frauke Kreuter for giving me the opportunity to write this dissertation and for believing in the potential of this endeavor.  \n... PD Dr. Rudolf Debelak for supporting me in the attempt to use the parameter instability test on ordinal factor models and for advising me in all stages of this project.  \n... Prof. Dr. Daniel Oberski and Prof. Dr. Helmut K¨uchenhoff for their willingness tobe part of the examination committee.  \n... Prof. Yves Rosseel for including my code in his R-package and helping me tackle the mathematical and technical challenges of GEE estimation.  \n... Prof. Dr. Susanne Kuger for giving me the opportunity to pursue this dissertation while being employed at the German Youth Institute.  \n... Prof. Dr. Rolf Steyer for inspiring and patiently supporting me to become a statistician and psychometrician.  \n... my family and friends for believing in me and for building me up so often.  \nZusammenfassung  \nDiese Arbeit enth¨alt vier Beitr¨age (Manuskripte I bis IV), die jeweils neue methodische Ans¨atze zum Umgang mit Verzerrungen und Bias in mehrdimensionalen IRT-Modelleneinf¨uhren. Insbesondere wird das Potenzial nichtparametrischer, maschineller Lernverfahren eingehend untersucht. Die im Rahmen dieser Arbeit verfassten Manuskripte stellen Methoden zur Sch¨atzung von Modellparametern und latenten Variablen-Scores multidimensionaler IRT-Modelle vor. Diese Methoden ber¨ucksichtigen die Verzerrung, die ungemessene und/oder gemessene Kovariaten auf die Parametersch¨atzung haben k¨onnen.  \nIn Manuskript I wird gezeigt, dass die Einbeziehung von latenten Item-Effekt-Variablen in longitudinale IRT-Modelle f¨ur ordinale Antwortvariablen interindividuelle Unterschiedein den Item-Schwierigkeits-Parametern kontrollieren kann. Auf diese Weise wird die Verzerrung, die gemessene oder nicht gemessene Kovariaten auf die Sch¨atzung der ItemSchwierigkeits-Parameter haben k¨onnen, ber¨ucksichtigt.  \nAußerhalb der L¨angsschnittforschung ist es nicht m¨oglich, solche Item-Effekt-Variablen zu sch¨atzen. Interindividuelle Unterschiede in den Item-Parametern, die auch als Differential Item Functioning (DIF) bezeichnet werden, k¨onnen jedoch mit Hilfe von Model Based Recursive Partitioning (MOB) ber¨ucksichtigt werden, einem algorithmischen Modellierungsansatz, der aus den Methoden des maschinellen Lernens stammt. Manuskript II zeigt, dass MOB zur Kontrolle von DIF in mehrdimensionalen IRT-Modellen verwendet werden kann. Dies funktioniert, indem automatisch Untergruppen mit stabilen ItemParametersch¨atzungen erkannt werden.  \nManuskript III stellt eine Methode zur Sch¨atzung latenter Variablen-Scores von Individuen vor, die in Bezug auf bestimmte gemessene Kovariaten unverzerrt sind. Zu diesem Zweck wird ein Ensemble von MOB-Trees gebildet. Innerhalb des MOB-Tree-Ensembles werden Untergruppen mit stabilen Item-Parameter-Sch¨atzungen verwendet, um latente Variablen-Scores zu sch¨atzen, die in Bezug auf relevante Untergruppen in der Population unverzerrt sind. Somit sind diese latenten Variablen-Scores im Hinblick auf systematische Einfl¨usse dieser ","cbCaimYcamQxzXMe","https://ap.wps.com/l/cbCaimYcamQxzXMe","pdf",10322041,2,1,169,"English","en",105,"# Acknowledgements\n# Zusammenfassung\n## Four contributions and objectives\n## Manuscript I: latent item effect variables\n## Manuscript II: MOB for DIF control\n## Manuscript III: unbiased latent variable score estimation\n## Manuscript IV: efficient contributions to the score function\n# Summary","[{\"question\":\"What problem does the dissertation address in multidimensional IRT models?\",\"answer\":\"It addresses bias in parameter estimation caused by measured and/or unmeasured covariates, and develops methods to handle this distortion.\"},{\"question\":\"How does the dissertation control differential item functioning (DIF)?\",\"answer\":\"It uses model based recursive partitioning (MOB) to automatically identify subgroups with stable item parameter estimates, enabling DIF control in multidimensional IRT models.\"},{\"question\":\"How are unbiased latent variable scores estimated outside longitudinal contexts?\",\"answer\":\"An ensemble of MOB trees is built so that latent variable scores are estimated within subgroup structures, targeting scores that are interpretable as unbiased with respect to specific measured covariates.\"}]","Machine Learning Approaches to Latent Variable Modeling - Dissertation | PDF",1785946989,426,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"machine-learning-approaches-to-latent-variable-modeling-dissertation","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,48,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":20},"https://docshare.wps.com/document/","Document",{"item":49,"name":12,"@type":44,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/machine-learning-approaches-to-latent-variable-modeling-dissertation/128347/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-23","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What problem does the dissertation address in multidimensional IRT models?","Question",{"text":76,"@type":77},"It addresses bias in parameter estimation caused by measured and/or unmeasured covariates, and develops methods to handle this distortion.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the dissertation control differential item functioning (DIF)?",{"text":81,"@type":77},"It uses model based recursive partitioning (MOB) to automatically identify subgroups with stable item parameter estimates, enabling DIF control in multidimensional IRT models.",{"name":83,"@type":74,"acceptedAnswer":84},"How are unbiased latent variable scores estimated outside longitudinal contexts?",{"text":85,"@type":77},"An ensemble of MOB trees is built so that latent variable scores are estimated within subgroup structures, targeting scores that are interpretable as unbiased with respect to specific measured covariates.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]