新巴塞尔资本协定下资产报酬相关系数分配之探讨---贝氏统计方法之应用.doc

新巴塞爾資本協定下資產報酬相關係數分配之探討---貝氏統計方法之應用 The application of Bayesian method to the distribution of asset return correlation in the New Basel Accord 趙若堯 Jo-Yao Chao 國立台北大學統計學系研究生 鍾麗英 Lyinn Chung 國立台北大學統計學系副教授 李詩政 Shih-Cheng Lee 元智大學會計學系助理教授 中文摘要： 巴塞爾委員會於1999年發布新資本規範，進一步肯定自有資本比率規範的精神，在新巴塞爾資本協定2001年第二版諮詢文（CP2）中，並沒有將資產報酬相關係數列為變數，僅表示資產報酬相關係數均為0.2；而在2003年4月的第三版諮詢文（CP3），正式將資產報酬相關係數列為計算資本需求之重要變數，除了更改範圍為0.12~0.24外，更提出資產報酬相關係數與違約機率呈現負相關，且擁有一函數關係；但由於沒有詳加說明此函數之理論基礎，也造成了各界的眾說紛紜；有鑑於此，本文使用北美2004上市上櫃公司資料，將貝氏統計方法應用在單因子模型上，來討論資產報酬相關係數的機率分配，期望能以實證結果推導出資產報酬相關係數的分配。 而本篇論文的實證研究結果顯示，資產報酬相關係數的範圍並沒有如新巴塞爾所估計的那麼大，並且不同財務狀況下，資產報酬相關係數也會明顯的不同；且新巴塞爾的違約機率與資產報酬相關係數的轉換公式也會導致一些錯誤訊息的產生，因此向巴塞爾委員會提出建議與修正。 關鍵詞：巴塞爾委員會、資本需求、資產報酬相關係數、貝氏統計方法。 ABSTRACT： The asset return correlation is the key variable for calculating the regulatory capital in the New Basel Accord. The Second Consultative paper (CP2) in 2001 considered the asset return correlation as a constant 0.2. The third Consultative paper (CP3) announced in April, 2003 formally introduced the asset return correlation as a decreasing function of default probability. It not only defined that the range of asset return correlation is 0.12 to 0.24 for corporations but also addressed that asset return correlation and probability of default are negatively correlated. However, as CP3 did not explain the theoretical concept for the formula of asset return correlation, there were many research papers discussing the appropriateness of this formula from different aspects. This study applied Bayesian method to a single risk factor model in order to discuss the probability distribution of asset return correlation. We use the data for the listed companies of North America in 2004 from CRSP to derive the distribution of asset return correlation. The empirical results reveal that the range of asset return correlation is not as wide (0.12,0.24) for corporations. And the range of asset return correlation varies for different financial statuses of corporations. Since we found t