[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125697-en":3,"doc-seo-125697-105":30,"detail-sidebar-cat-0-en-105":91},{"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":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},125697,16904993612988,"Olivia Brown","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Essays on Time Series Analysis and Statistical Machine Learning - PhD Dissertation","This thesis presents three research articles at the intersection of time series analysis and statistical machine learning. It introduces a peaks-over-threshold method to model clustered exceedances by capturing short- and long-range dependence, demonstrated on oceanographic measurements. It further proposes an efficient discrepancy-based inference strategy for intractable generative models using quasi-Monte Carlo, reducing parameter-estimation cost across academic and applied settings. Finally, it develops deep sequential training approaches to improve forecasting under structural breaks, validated via extensive simulations and applied to energy data.","Essays on Time Series Analysis and Statistical Machine Learning  \nVon der Wirtschaftswissenschaftlichen Fakult¨at der Gottfried Wilhelm Leibniz Universit¨at Hannover zur Erlangung des akademischen Grades  \nDoktor(in) der Wirtschaftswissenschaften  \n—Doctor rerum politicarum—  \ngenehmigte Dissertation  \nvon  \nM.Sc. Johanna Meier  \ngeboren am 02.06.1995 in Lemgo  \n2023  \nReferent: Prof. Dr. Philipp Sibbertsen, Leibniz Universit¨at Hannover Korreferent: Prof. Dr. Marcel Prokopczuk, Leibniz Universit¨at Hannover  \nTag der Promotion: 05.10.2023  \nAcknowledgements  \nFirst and foremost, I would like to thank my supervisor and co-author Prof. Dr. Philipp Sibbertsen for giving me the opportunity to earn my PhD degree at the Institute of Statistics as well as for his tireless support and guidance over the last three years. I would also like to express my gratitude to Prof. Dr. Marcel Prokopczuk for taking his time to be my second examiner, to Prof. Dr. Kay Blaufus for chairing my examination board, as well as to Dr. Ute Lohse for advising.  \nFurther, I am grateful to my co-authors Dr. Pushpa Dissanayake, Teresa Flock, and Ziang Niu for countless inspiring discussions, and in particular to Dr. Fran¸cois-Xavier Briol for continuing to share his experience during my PhD journey.  \nSpecial thanks are due to my former and present colleagues for creating a pleasant working environment and their moral support in difficult times. I would like to particularly mention Teresa Flock and Vivien Less who accompanied me since day one of my PhD.  \nLastly, I would like to recognise the unconditional help of my family: the continuous reassurance by my parents, the constant encouragement by my brother, and the emotional support by my fianc´e. To all of you: my deepest gratitude.  \nAbstract  \nThis thesis encompasses three research articles contributing to the fields of time series analysis and statistical machine learning. Firstly, we develop a peaks-over-threshold approach, which captures both short-and long-term correlations in the underlying time series in order to model the clustering behaviour in high-threshold exceedances. The suggested model is motivated by and applied to oceanographic data. Secondly, we propose an efficient discrepancy-based inference approach for intractable generative models based on quasi-Monte Carlo methods. We demonstrate that this method substantially reduces the computational cost of estimating the model parameters in various applications of academic and practical interest. Thirdly, we suggest training methods for deep sequential models, which improve the forecast precision when facing structural breaks in the in-sample period. These mitigation strategies are examined in an extensive simulation study and utilised to forecast energy data. As the developed theory in this thesis is very versatile, it is applicable to a broad range of data types as well as research fields, and in particular to economic time series.  \nKeywords: Peaks-over-threshold · Extremal clustering · Long-range dependence · Intractable generative models · Discrepancy-based inference · Quasi-Monte Carlo · Deep sequential models · Structural breaks  \nContents  \nContents i  \nList of Figures iii  \nList of Tables v  \n1 Introduction 1  \n2 Modelling Short- and Long-Term Dependencies of Clustered HighThreshold Exceedances in Significant Wave Heights 4  \n3 Discrepancy-Based Inference for Intractable Generative Models Using Quasi-Monte Carlo 5  \n4 Forecasting Facing Structural Breaks Using Deep Sequential Models 6  \n4.1 Introduction ................................... 6  \n4.2 Review of Deep Sequential Architectures ................... 8  \n4.3 Fostering Forecast Robustness Facing Mean Shifts .............. 10  \n4.3.1 Multiple Mean Shift Model ....................... 10  \n4.3.2 Effect of Mean Shifts on the Forecast Precision ........... 10  \n4.3.3 Weighted Loss Functions ........................ 12  \n4.3.3.1 Applying Weighted Loss Functions to a Toy Example ... 16  \n4.3","cbCaitUV8RBylBw5","https://ap.wps.com/l/cbCaitUV8RBylBw5","pdf",1039705,1,67,"English","en",105,"# Introduction\n# Modelling Short- and Long-Term Dependencies of Clustered High-Threshold Exceedances in Significant Wave Heights\n# Discrepancy-Based Inference for Intractable Generative Models Using Quasi-Monte Carlo\n# Forecasting Facing Structural Breaks Using Deep Sequential Models","[{\"question\":\"What is the peaks-over-threshold approach developed in the thesis used for?\",\"answer\":\"It models clustering behavior in high-threshold exceedances by capturing short- and long-term correlations in the underlying time series.\"},{\"question\":\"How does the discrepancy-based inference method help with intractable generative models?\",\"answer\":\"It uses quasi-Monte Carlo techniques to substantially reduce computational cost for estimating model parameters in different applications.\"},{\"question\":\"What strategies does the thesis propose for forecasting when structural breaks occur?\",\"answer\":\"It proposes training methods for deep sequential models that improve forecast precision under structural breaks, supported by a simulation study and an energy-data application.\"}]","Essays on Time Series Analysis and Statistical Machine Learning - PhD Dissertation | PDF",1785900711,169,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"essays-on-time-series-analysis-and-statistical-machine-learning-phd-dissertation","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/essays-on-time-series-analysis-and-statistical-machine-learning-phd-dissertation/125697/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is the peaks-over-threshold approach developed in the thesis used for?","Question",{"text":75,"@type":76},"It models clustering behavior in high-threshold exceedances by capturing short- and long-term correlations in the underlying time series.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the discrepancy-based inference method help with intractable generative models?",{"text":80,"@type":76},"It uses quasi-Monte Carlo techniques to substantially reduce computational cost for estimating model parameters in different applications.",{"name":82,"@type":73,"acceptedAnswer":83},"What strategies does the thesis propose for forecasting when structural breaks occur?",{"text":84,"@type":76},"It proposes training methods for deep sequential models that improve forecast precision under structural breaks, supported by a simulation study and an energy-data application.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]