{"id":{"repo_id":"buffalo","oai_identifier":"oai:ubir.buffalo.edu:10477/80902"},"canonical_url":"https://search.dev.ndltd.org/etd/buffalo/oai:ubir.buffalo.edu:10477/80902","repository":{"repo_id":"buffalo","name":"Buffalo","base_url":"https://ubir.buffalo.edu/oai/request"},"display":{"title":"Improvement of Estimation of Optimal Covariance Matrix and Forecast for Financial Risk Management: The Perspective of Global Stock Market","abstract":"Ph.D.","abstract_html":"Ph.D.","abstract_has_math":false,"creators":["Kim, Sanghyeon"],"institution":"State University of New York at Buffalo","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Revankar, Nagesh","Economics"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2019,"date_issued":"2019-10-29T16:48:00Z","date_published":"2019-10-29T16:48:00Z","updated_at":"2026-07-27T19:05:25Z","subjects":["economics"],"languages":["eng"],"rights":["Users of works found in University at Buffalo Institutional Repository (UBIR) are responsible for identifying and contacting the copyright owner for permission to reuse. University at Buffalo Libraries do not manage rights for copyright-protected works and cannot assist with permissions.","Copyright retained by author."],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/10477/80902","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Revankar, Nagesh","Economics"]},{"key":"dc:creator","label":"Author","values":["Kim, Sanghyeon"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2019-10-29T16:48:00Z","2019","2019-08-07 15:24:30"]},{"key":"dc:publisher","label":"Institution","values":["State University of New York at Buffalo"]},{"key":"dc:type","label":"Dc Type","values":["Text","Dissertation"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["economics"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Users of works found in University at Buffalo Institutional Repository (UBIR) are responsible for identifying and contacting the copyright owner for permission to reuse. University at Buffalo Libraries do not manage rights for copyright-protected works and cannot assist with permissions.","Copyright retained by author."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/10477/80902"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Ph.D.","Modeling and forecasting the volatility and correlation of financial asset returns is crucial for risk management, portfolio selection and analysis of phenomenon of the synchronization for global economy in the fields of finance and financial econometrics. The challenging problems for the estimation of the covariance matrices and the forecast of the volatilities are the so-called ‘Curse of dimensionality’ and ‘Measurement error’. In this dissertation, we propose a methodology that is applicable in large-dimensional cases and can reduce the error or noise inherent in the simpler covariance estimator such as sample covariance matrix. The shrinkage method used in this study is applicable in large-dimensional covariance matrix and also in the dynamic attenuation models, which exploits information about the time-varying measurement error, introduced by Bollerslev, Patton and Quaedvlieg (2016, 2018). We analyze the effect of the reduction of noise inherent in the sample covariance matrix and the effect of the reduction of variance from the realized covariance estimator by applying the shrinkage method. Also, we discuss the estimates of stock return volatility and dynamic correlation among global stock market, and forecast one-step-ahead stock return volatility to compare the forecasting performance of the volatility forecasts in terms of the forecast losses. Especially, we focus on the impact of the volatility of the U.S stock market to the volatility of the Asian stock markets such as Korea, Japan and China stock markets. This dissertation consists of four chapters: the first chapter introduces the shrinkage method proposed by Ledoit and Wolf (2003) and describes the shrinkage intensity that is a process of finding out an optimal weight between two different covariance estimators. We suggest a modification from the shrinkage method of Ledoit and Wolf (2003). The second chapter describes various volatility forecasts and also evaluates the forecasting performance of the volatility forecasts, and analyzes the effect of applying the shrinkage method to the volatility forecasts in terms of forecast losses. In addition, we apply the shrinkage method to the dynamic attenuation models using ten individual stock indexes used in the study of Bollerslev, Patton and Quaedvlieg (2016, 2018) for an additional economic implication. Finally, we compare the results of the forecasting performance of the volatility forecasts and confirm the additional effect from our suggested method in terms of the forecasting performance of the volatility forecasts. Third chapter analyzes an activity between global stock market and futures market. We analyze the recent movement between global stock market and oil market after the Shale Gas Revolution. Last chapter summarizes the results and draw conclusions."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Improvement of Estimation of Optimal Covariance Matrix and Forecast for Financial Risk Management: The Perspective of Global Stock Market"]}]}],"canonical_facts":{"dc:contributor":["Revankar, Nagesh","Economics"],"dc:creator":["Kim, Sanghyeon"],"dc:date":["2019-10-29T16:48:00Z","2019","2019-08-07 15:24:30"],"dc:description":["Ph.D.","Modeling and forecasting the volatility and correlation of financial asset returns is crucial for risk management, portfolio selection and analysis of phenomenon of the synchronization for global economy in the fields of finance and financial econometrics. The challenging problems for the estimation of the covariance matrices and the forecast of the volatilities are the so-called ‘Curse of dimensionality’ and ‘Measurement error’. In this dissertation, we propose a methodology that is applicable in large-dimensional cases and can reduce the error or noise inherent in the simpler covariance estimator such as sample covariance matrix. The shrinkage method used in this study is applicable in large-dimensional covariance matrix and also in the dynamic attenuation models, which exploits information about the time-varying measurement error, introduced by Bollerslev, Patton and Quaedvlieg (2016, 2018). We analyze the effect of the reduction of noise inherent in the sample covariance matrix and the effect of the reduction of variance from the realized covariance estimator by applying the shrinkage method. Also, we discuss the estimates of stock return volatility and dynamic correlation among global stock market, and forecast one-step-ahead stock return volatility to compare the forecasting performance of the volatility forecasts in terms of the forecast losses. Especially, we focus on the impact of the volatility of the U.S stock market to the volatility of the Asian stock markets such as Korea, Japan and China stock markets. This dissertation consists of four chapters: the first chapter introduces the shrinkage method proposed by Ledoit and Wolf (2003) and describes the shrinkage intensity that is a process of finding out an optimal weight between two different covariance estimators. We suggest a modification from the shrinkage method of Ledoit and Wolf (2003). The second chapter describes various volatility forecasts and also evaluates the forecasting performance of the volatility forecasts, and analyzes the effect of applying the shrinkage method to the volatility forecasts in terms of forecast losses. In addition, we apply the shrinkage method to the dynamic attenuation models using ten individual stock indexes used in the study of Bollerslev, Patton and Quaedvlieg (2016, 2018) for an additional economic implication. Finally, we compare the results of the forecasting performance of the volatility forecasts and confirm the additional effect from our suggested method in terms of the forecasting performance of the volatility forecasts. Third chapter analyzes an activity between global stock market and futures market. We analyze the recent movement between global stock market and oil market after the Shale Gas Revolution. Last chapter summarizes the results and draw conclusions."],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/10477/80902"],"dc:language":["eng"],"dc:publisher":["State University of New York at Buffalo"],"dc:rights":["Users of works found in University at Buffalo Institutional Repository (UBIR) are responsible for identifying and contacting the copyright owner for permission to reuse. University at Buffalo Libraries do not manage rights for copyright-protected works and cannot assist with permissions.","Copyright retained by author."],"dc:subject":["economics"],"dc:title":["Improvement of Estimation of Optimal Covariance Matrix and Forecast for Financial Risk Management: The Perspective of Global Stock Market"],"dc:type":["Text","Dissertation"]},"updated_at":"2026-07-27T19:05:25Z"}