國立高雄大學圖資館 |

語系: 繁體中文

說明(常見問題)

圖資館首頁

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

跳躍風險下馬可夫轉換模型之實證分析 = An Empirical Ana...

國立高雄大學統計學研究所

跳躍風險下馬可夫轉換模型之實證分析 = An Empirical Analysis of Markov Switching Models with Jump Risks

紀錄類型:	書目-語言資料,印刷品 : 單行本
並列題名:	An Empirical Analysis of Markov Switching Models with Jump Risks
作者:	汪昱頡,
其他團體作者:	國立高雄大學
出版地:	[高雄市]
出版者:	撰者;
出版年:	2008[民97]
面頁冊數:	93面圖，表 : 30公分;
標題:	馬可夫轉換模型
標題:	Markov switching model
電子資源:	http://handle.ncl.edu.tw/11296/ndltd/97788564821655645389
附註:	指導教授：林士貴
附註:	參考書目：面35-39
附註:	含附錄
摘要註:	Hamilton (1989) 提出馬可夫轉換模型來形容金融變數之時間序列行為，後續實證文獻也證明馬可夫轉換模型可用來解釋經濟上許多現象，例如：經濟循環、股票市場、匯率及短期利率。不幸地，馬可夫轉換模型卻無法形容當偶發事件發生、重大訊息來臨或是重大金融市場衝擊時所造成之跳躍情況，例如：網際網路泡沫化、總體經濟重大消息、亞洲金融風暴等。Merton (1976) 提出跳躍擴散模型以描述資產受到偶發事件影響所發生的不正常跳躍。本文延伸 Hamilton (1989) 和 Merton (1976)模型進而提出兩種模型: (1) 考量普瓦松跳躍風險之馬可夫轉換模型以及 (2) 考量馬可夫跳躍風險之馬可夫轉換模型。此兩種模型可捕捉在不同狀態下，資產價格的平均成長和波動項以及偶發事件發生時之影響。本文將利用Expectation-Maximization (EM) gradient 演算法來估計本文所提的模型參數，並使用概似比檢定法來檢定模型的配適度能力。在實證分析上，本文分析紐約證券交易所（NYSE）的一組樣本，而實證結果發現部分公司之股價平均成長、波動項和不正常跳躍頻率會受所處狀態影響。 Regime-switching models proposed by Hamilton (1989) are well-suited for capturing the time series behavior of many financial variables. Markov-switching models have proved to be quite useful for modeling a range of economic time series, from the business cycle, the stock market, exchange rates, and short-term interest rates. Unfortunately, the Markov switching model can not work well to accommodate jump phenomenon of the occurrence of abnormal events and large shocks to financial market, such as Internet bubble crash, macroeconomic announcement, the Asian and Russian finance crisis. The jump-diffusion model proposed by Merton (1976) can work well to capture the jump risk of asset price when the occurrence of abnormal events. We extend the model of Hamilton (1989) and Merton (1976) to propose two models: Markov-switching model with Poisson jump risks and Markov-switching model with Markov jump risks, which can address the effect that mean and volatility of the stock price depend on the states of business cycle and the jump effect of abnormal events. This paper use the Expectation-Maximization (EM) gradient algorithm to estimate the parameters of the model and use the likelihood ratio statistics to test which model is appropriate. The data consist of 49 NYSE listed stocks. The empirical results show that, in some of the companies, the mean and volatility of the stock price depend on the states of business cycle and the jump effect of abnormal events.

跳躍風險下馬可夫轉換模型之實證分析 = An Empirical Analysis of Markov Switching Models with Jump Risks
汪, 昱頡

跳躍風險下馬可夫轉換模型之實證分析 = An Empirical Analysis of Markov Switching Models with Jump Risks / 汪昱頡撰 - [高雄市] : 撰者, 2008[民97]. - 93面 ; 圖，表 ; 30公分.
指導教授：林士貴參考書目：面35-39含附錄.
馬可夫轉換模型Markov switching model

跳躍風險下馬可夫轉換模型之實證分析 = An Empirical Analysis of Markov Switching Models with Jump Risks
LDR:04086nam0a2200301 450 001 133587
005 20170214100024.0
009 133587
010 0 $b 精裝
010 0 $b 平裝
100 $a 20170214y2008 k y0chiy09 b
101 1 $a eng $d chi $d eng
102 $a tw
105 $a ak am 000yy
200 1 $a 跳躍風險下馬可夫轉換模型之實證分析 $d An Empirical Analysis of Markov Switching Models with Jump Risks $z eng $f 汪昱頡撰
210 $a [高雄市] $c 撰者 $d 2008[民97]
215 0 $a 93面 $c 圖，表 $d 30公分
300 $a 指導教授：林士貴
300 $a 參考書目：面35-39
300 $a 含附錄
328 $a 碩士論文--國立高雄大學統計學研究所
330 $a Hamilton (1989) 提出馬可夫轉換模型來形容金融變數之時間序列行為，後續實證文獻也證明馬可夫轉換模型可用來解釋經濟上許多現象，例如：經濟循環、股票市場、匯率及短期利率。不幸地，馬可夫轉換模型卻無法形容當偶發事件發生、重大訊息來臨或是重大金融市場衝擊時所造成之跳躍情況，例如：網際網路泡沫化、總體經濟重大消息、亞洲金融風暴等。Merton (1976) 提出跳躍擴散模型以描述資產受到偶發事件影響所發生的不正常跳躍。本文延伸 Hamilton (1989) 和 Merton (1976)模型進而提出兩種模型: (1) 考量普瓦松跳躍風險之馬可夫轉換模型以及 (2) 考量馬可夫跳躍風險之馬可夫轉換模型。此兩種模型可捕捉在不同狀態下，資產價格的平均成長和波動項以及偶發事件發生時之影響。本文將利用Expectation-Maximization (EM) gradient 演算法來估計本文所提的模型參數，並使用概似比檢定法來檢定模型的配適度能力。在實證分析上，本文分析紐約證券交易所（NYSE）的一組樣本，而實證結果發現部分公司之股價平均成長、波動項和不正常跳躍頻率會受所處狀態影響。 Regime-switching models proposed by Hamilton (1989) are well-suited for capturing the time series behavior of many financial variables. Markov-switching models have proved to be quite useful for modeling a range of economic time series, from the business cycle, the stock market, exchange rates, and short-term interest rates. Unfortunately, the Markov switching model can not work well to accommodate jump phenomenon of the occurrence of abnormal events and large shocks to financial market, such as Internet bubble crash, macroeconomic announcement, the Asian and Russian finance crisis. The jump-diffusion model proposed by Merton (1976) can work well to capture the jump risk of asset price when the occurrence of abnormal events. We extend the model of Hamilton (1989) and Merton (1976) to propose two models: Markov-switching model with Poisson jump risks and Markov-switching model with Markov jump risks, which can address the effect that mean and volatility of the stock price depend on the states of business cycle and the jump effect of abnormal events. This paper use the Expectation-Maximization (EM) gradient algorithm to estimate the parameters of the model and use the likelihood ratio statistics to test which model is appropriate. The data consist of 49 NYSE listed stocks. The empirical results show that, in some of the companies, the mean and volatility of the stock price depend on the states of business cycle and the jump effect of abnormal events.
510 1 $a An Empirical Analysis of Markov Switching Models with Jump Risks $z eng
610 0 $a 馬可夫轉換模型 $a 普瓦松跳躍風險之馬可夫轉換模型 $a 普瓦松跳躍風險之馬可夫轉換模型 $a EM 演算法 $a 概似比檢定法
610 1 $a Markov switching model $a Markov-switching model with Poisson jump risks $a Markov-switching model with Markov jump risks $a Expectation-Maximization algorithm $a Likelihood ratio test
681 $a 008M/0019 $b 343201 3164 $v 增定八版
700 1 $a 汪 $b 昱頡 $4 撰 $3 166082
712 0 2 $a 國立高雄大學 $b 統計學研究所 $3 166081
801 0 $a tw $b NUK $c 20081016 $g CCR
801 1 $a tw $b NUK $c 20081016 $g CCR
856 7 $z 電子資源 $2 http $u http://handle.ncl.edu.tw/11296/ndltd/97788564821655645389