債券投資組合風險值計算之探討

NCUIR > School of Management at National Central University > Graduate Institute of Finance > Electronic Thesis & Dissertation > Item 987654321/68522

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/68522

Title:	債券投資組合風險值計算之探討
Authors:	蕭培均;Hsiao,Pei Jun
Contributors:	財務金融學系
Keywords:	卡爾曼濾波器;二因子利率模型;利率風險;債券投資組合;風險值;Kalman Filter;Canonical-form Vasicek Model;Interest rate risk;Bond portfolio;VaR
Date:	2015-08-03
Issue Date:	2015-09-23 11:58:11 (UTC+8)
Publisher:	國立中央大學
Abstract:	交易債券會面臨許多風險，利率變動的風險是一個主要來源之一，而由於影響利率變動的因素有許多，使得預測利率並不是一件容易的事。因此，如何控管承擔的利率風險是一件重要的事。這份研究中採用了風險值(Value-at-Risk)做為控管可能承擔的最大損失的一個基本工具。而要求出風險值的方法有許多種，基本上可分為三類：變異數-共變數法、歷史模擬法、及蒙地卡羅模擬法，而本文便是將蒙地卡羅模擬法做進一步的延伸。在本文中利用Canonical-form two factor Vasicek Model配適利率期限結構，並以Kalman Filter來進行利率模型的參數估計，再透過模擬殖利率變動的方式，進而做為找債券投資組合分配的方法，並結合了歷史模擬法的概念與蒙地卡羅模擬法計算公債投資組合的風險值。方法便是利用變動利率模型中的參數做為找出債券投資組合折現價格分配的方式，最後再計算風險值。 ;Trading bonds will face lots of risks. The main resource of risk is the interest rate risk. Because there are different kinds of factors to affect the interest rate risk, it is not easy to estimate the future trend of interest rate, then controlling the risk we take is very important. In this research, we use Value-at-Risk as a basic tool to help us to control the possible maximum loss we will take in bond portfolio. And there are three basic ways to calculate Value-at-risk : Variance-Covariance method、Historical simulation method、and Monte Carlo method, we try to extend Monte Carlo method in this paper. In this thesis, we try to fit the Term-Structure of interest rate with Canonical-form two factor Vasicek Model, and we use Kalman Filter to estimate parameters of this interest rate Model. Then, through simulating the changing of yield rate, we can find the distribution of discounted bond price, and we can use the distribution to calculate VaR.
Appears in Collections:	[Graduate Institute of Finance] Electronic Thesis & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	651	View/Open

社群 sharing

Loading...