{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/129818"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/129818","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Statistical inference with complex datasets: from self normalization to machine learning","abstract":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-20 without embargo terms","abstract_html":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-20 without embargo terms","abstract_has_math":false,"creators":["Zhang, Yi"],"institution":"University of Illinois Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Statistics","degree_department":null,"school":null,"contributors":["Shao, Xiaofeng","Yang, Yun","Zhu, Ruoqing","Fellouris, Georgios"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-05-30","date_published":"2025-05-30","updated_at":"2026-07-22T22:25:05Z","subjects":["Self Normalization","Machine Learning","Time Series","Nonparametric Statistics"],"languages":["en","eng"],"rights":["Copyright 2025 Yi Zhang"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/129818","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Shao, Xiaofeng","Yang, Yun","Zhu, Ruoqing","Fellouris, Georgios"]},{"key":"dc:creator","label":"Author","values":["Zhang, Yi"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-05-30","2025-08"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Statistics"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph.D."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Self Normalization","Machine Learning","Time Series","Nonparametric Statistics"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en","eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2025 Yi Zhang"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/129818"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-20 without embargo terms","The student, Yi Zhang, accepted the attached license on 2025-05-28 at 12:45.","The student, Yi Zhang, submitted this Dissertation for approval on 2025-05-28 at 12:52.","This Dissertation was approved for publication on 2025-05-30 at 10:32.","DSpace SAF Submission Ingestion Package generated from Vireo submission #22313 on 2025-10-20 at 16:57:04","This thesis is based on four projects I did to develop reliable inferential tools for complex datasets during my PhD study. I started working on this problem by considering bandwidth free hypothesis testing for time series data, resulting in a self normalization based test procedure that greatly reduces the size distortion of existing tests for multi-dimensional parameters. With the intuition and novel theoretical tools gained, I then considered the hypothesis testing problem for functional (i.e., infinite-dimensional) parameters and for metric space valued time series, leading to several new tests, as there was a lack of bandwidth free tests for these data types. By leveraging modern machine learning tools such as deep neural network and generative neural network, I also worked on developing new tests for some traditional statistical testing problems, with the goal of accommodating both low- and high-dimensional data. Examples include new nonparametric conditional independence tests that work well when the conditioning variable is of high dimension and can have high-dimensional data (e.g., texts and images) as the covariates of interests and/or the response."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Statistical inference with complex datasets: from self normalization to machine learning"]}]}],"canonical_facts":{"dc:contributor":["Shao, Xiaofeng","Yang, Yun","Zhu, Ruoqing","Fellouris, Georgios"],"dc:creator":["Zhang, Yi"],"dc:date":["2025-05-30","2025-08"],"dc:description":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-20 without embargo terms","The student, Yi Zhang, accepted the attached license on 2025-05-28 at 12:45.","The student, Yi Zhang, submitted this Dissertation for approval on 2025-05-28 at 12:52.","This Dissertation was approved for publication on 2025-05-30 at 10:32.","DSpace SAF Submission Ingestion Package generated from Vireo submission #22313 on 2025-10-20 at 16:57:04","This thesis is based on four projects I did to develop reliable inferential tools for complex datasets during my PhD study. I started working on this problem by considering bandwidth free hypothesis testing for time series data, resulting in a self normalization based test procedure that greatly reduces the size distortion of existing tests for multi-dimensional parameters. With the intuition and novel theoretical tools gained, I then considered the hypothesis testing problem for functional (i.e., infinite-dimensional) parameters and for metric space valued time series, leading to several new tests, as there was a lack of bandwidth free tests for these data types. By leveraging modern machine learning tools such as deep neural network and generative neural network, I also worked on developing new tests for some traditional statistical testing problems, with the goal of accommodating both low- and high-dimensional data. Examples include new nonparametric conditional independence tests that work well when the conditioning variable is of high dimension and can have high-dimensional data (e.g., texts and images) as the covariates of interests and/or the response."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/129818"],"dc:language":["en","eng"],"dc:rights":["Copyright 2025 Yi Zhang"],"dc:subject":["Self Normalization","Machine Learning","Time Series","Nonparametric Statistics"],"dc:title":["Statistical inference with complex datasets: from self normalization to machine learning"],"dc:type":["text"],"thesis:degree_discipline":["Statistics"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:05Z"}