- 學位論文
金融海嘯時期應用風險值控管投資組合之研究
A STUDY OF APPLING VaR TO THE CONTROL OF PORTFOLIO IN FINANCIAL TSUNAMI
摘要
近年來，重大的金融危機事件層出不窮，使得風險管理的概念越來越受重視。而風險值可將風險量化成為當今企業或金融機構管理市場風險不可或缺的管理工具。本研究主要探討以風險值的觀念，應用於共同基金投資組合的風險衡量上，希望能提供基金管理者另一管控的參考準則。基此，根據2008 年4月1日至2009年03月27 日期間以投資組合為實證對象。利用不同的風險值模型（變異數-共變異數法、歷史模擬法及蒙地卡羅模擬法）來衡量共同基金投資組合之市場風險。其次，進行回溯測試探討這些不同的模型，是否可以真實的反映出投資組合面臨的市場風險。接續利用個別標的資產之邊際風險值進行風險調節與評估調節後之績效表現。 經回溯測試實證結果顯示，變異數-共變異數法中之指數加權移動平均法的表現優於歷史模擬法與蒙地卡羅模擬法。可見在給予近期歷史資料較重的權重，在某種程度上，反映出波動群聚性與隨時間而改變的現象，近期市場上的任何衝擊將快速的反應在波動性的估計值上。另外，應用邊際風險值進行風險調節，其結果發現選擇邊際風險值最大的個別資產進行調節，其風險下降效果最大。其調節後之投資績效亦顯着的提昇。
並列摘要
In recent years, there are more and more significant financial markets crises. Many practitioners and researchers pay a lot of attention to the risk management. As a result, value at risk (VaR) has become a widely used measure of market risk in risk management for enterprise or financial institution. This thesis presents an application of VaR to measure the portfolio of Mutual Fund, and hope to provide the suggestions for the Fund managers. This study uses the portfolio data during the periods of April 1, 2008 to March 27, 2009 and different types of VaR models (Variance-Covariance method, Historical simulation method, Monte-Carlo simulation method) to measure the market risk of Mutual Fund. We also use Back Testing to examine whether each VaR model that can get the exact market risk or not. Finally, we use marginal VaR of individual underlying asset to make risk adjustment and evaluate the performance. The conclusions of this thesis are: The Exponentially Weighted Moving Average approaches of Variance-Covariance method is better than Historical simulation method and Monte-Carlo simulation method. Through adjusting underlying assets with the greatest marginal VaR , we can significantly reduce risk and increase performance.