{"689445":{"#nid":"689445","#data":{"type":"event","title":"PhD Defense by Zhaoyu Wang","body":[{"value":"\u003Cp\u003E\u003Cstrong\u003EName: Zhaoyu Wang\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ESchool of Psychology \u2013 Ph.D. Dissertation Defense Meeting\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EDate:\u003C\/strong\u003E\u0026nbsp;Friday, April 17th, 2026\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ETime\u003C\/strong\u003E: 3:00 PM - 4:30 PM\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ELocation\u003C\/strong\u003E: Virtual, \u003Ca href=\u0022https:\/\/teams.microsoft.com\/meet\/2932585935091?p=G6dkpjKLTed6VTJNNu\u0022 title=\u0022https:\/\/teams.microsoft.com\/meet\/2932585935091?p=G6dkpjKLTed6VTJNNu\u0022\u003Eclick here\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EDissertation Committee Chair\/Advisor\u003C\/strong\u003E:\u003C\/p\u003E\u003Cp\u003EJames Roberts, Ph.D. (Georgia Tech)\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EDissertation Committee Members\u003C\/strong\u003E:\u003C\/p\u003E\u003Cp\u003ESusan Embretson, Ph.D. (Georgia Tech)\u003C\/p\u003E\u003Cp\u003EBrian Habing, Ph.D. (University of South Carolina)\u003C\/p\u003E\u003Cp\u003EAudrey Leroux, Ph.D. (Georgia Tech)\u003C\/p\u003E\u003Cp\u003EDingjing Shi, Ph.D. (Georgia Tech)\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ETitle: Integrating the Multidimensional Generalized Graded Unfolding Model (MGGUM) and Multidimensional Scaling (MDS) to Improve Estimation Accuracy and Precision\u0026nbsp;\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EAbstract\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003EThis dissertation develops a Hybrid Model to enhance the Multidimensional Generalized\u003C\/p\u003E\u003Cp\u003EGraded Unfolding Model (MGGUM) by integrating Multidimensional Scaling (MDS) to refine\u003C\/p\u003E\u003Cp\u003Eitem location parameter estimates and reduce sample size requirements. The MGGUM,\u003C\/p\u003E\u003Cp\u003Ean extension of the unidimensional generalized graded unfolding model (GGUM), has been\u003C\/p\u003E\u003Cp\u003Eapplied across various psychological domains. It often requires large samples, especially with\u003C\/p\u003E\u003Cp\u003Emultidimensional data, which leads to a difficulty in the practical application of the model in\u003C\/p\u003E\u003Cp\u003Esocial science research where smaller samples prevail. To address this limitation, the present\u003C\/p\u003E\u003Cp\u003Estudy incorporates additional information about MGGUM item locations via MDS scale values\u003C\/p\u003E\u003Cp\u003Ederived from similarity judgments between stimulus pairs. This integration is expected to improve\u003C\/p\u003E\u003Cp\u003Ethe precision of item parameter estimates in the MGGUM. Specifically, the proposed model\u003C\/p\u003E\u003Cp\u003Eframework simultaneously estimates the item parameters of MGGUM and item scale values from\u003C\/p\u003E\u003Cp\u003EMDS by connecting them through a multivariate normal distribution. The variance-covariance\u003C\/p\u003E\u003Cp\u003Ematrix of the multivariate normal distribution specifies the relationship between the perceptual\u003C\/p\u003E\u003Cp\u003Eitem locations (MDS scale values derived from dissimilarities data) and preferential item locations\u003C\/p\u003E\u003Cp\u003E(MGGUM item locations derived from preference or [graded] disagree-agree response data).\u003C\/p\u003E\u003Cp\u003EThis specification allows the information from these two sources to simultaneously contribute to\u003C\/p\u003E\u003Cp\u003Eparameter estimation across models during an MCMC procedure.\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EWe conducted a parameter recovery simulation study and a real data analysis to compare the\u003C\/p\u003E\u003Cp\u003Eperformance of the new (hybrid) model with that of the original MGGUM. Results demonstrated\u003C\/p\u003E\u003Cp\u003Ethat the Hybrid Model improved the precision of MGGUM item location estimates and indirectly\u003C\/p\u003E\u003Cp\u003Eimproved the estimation of other parameters. It also reduced data demand to some extent and\u003C\/p\u003E\u003Cp\u003Esubstantially reduced computation time. These improvements extend the practical application\u003C\/p\u003E\u003Cp\u003Euniverse and efficiency of the MGGUM framework.\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003E\u003Cstrong\u003EIntegrating the Multidimensional Generalized Graded Unfolding Model (MGGUM) and Multidimensional Scaling (MDS) to Improve Estimation Accuracy and Precision\u0026nbsp;\u003C\/strong\u003E\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Integrating the Multidimensional Generalized Graded Unfolding Model (MGGUM) and Multidimensional Scaling (MDS) to Improve Estimation Accuracy and Precision "}],"uid":"27707","created_gmt":"2026-04-03 17:05:38","changed_gmt":"2026-04-03 17:06:40","author":"Tatianna Richardson","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2026-04-17T15:00:00-04:00","event_time_end":"2026-04-17T16:30:37-04:00","event_time_end_last":"2026-04-17T16:30:37-04:00","gmt_time_start":"2026-04-17 19:00:00","gmt_time_end":"2026-04-17 20:30:37","gmt_time_end_last":"2026-04-17 20:30:37","rrule":null,"timezone":"America\/New_York"},"location":"Virtual","extras":[],"groups":[{"id":"221981","name":"Graduate Studies"}],"categories":[],"keywords":[{"id":"100811","name":"Phd Defense"}],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1788","name":"Other\/Miscellaneous"}],"invited_audience":[{"id":"78771","name":"Public"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[],"email":[],"slides":[],"orientation":[],"userdata":""}}}