透過您的圖書館登入
IP:3.144.41.22
  • 學位論文

貝氏門檻自迴歸GARCH模型之應用

A Bayesian Analysis of Threshold AR-GARCH Model Using the Reversible Jump MCMC Approach

指導教授 : 林余昭

摘要


自我迴歸條件異質變異數分析模型(GARCH Model),反映了經濟變數之間變異數特殊的不確定形式,特別在金融時間序列波動群聚現象上已證實是非常成功的。一些根據馬可夫鏈蒙地卡羅方法(MCMC)所作貝氏分析也已成功應用在估計GARCH參數上。而且可逆跳躍馬可夫鏈蒙地卡洛法(RJMCMC)可以更進一步的解決模型選擇的問題;它使得吉氏取樣法(Gibbs sampling)能夠突破以往的限制,在不同空間的模型之間跳動。 更近一步,我們推廣RJMCMC的想法,可以從無限多種可能的模型之中來選取適合的模型,而不是只能從現有的模型選擇。另外,我們選擇臺灣股票指數(2004-2006)來分析,並且為了改善GARCH Model反應不對稱波動現象的預測能力不足,考慮門檻 AR-GARCH 模型並且找出適合此資料的模型。 在將來研究中,我們也希望將RJMCMC法應用在變異數參數長度不同的GARCH模型。與我們這份論文的方法一起配合,希望最佳的AR-GARCH 模型能自動地因而被選擇。

並列摘要


Generalized autoregressive conditional heteroskedasticity (GARCH) models have been important in analyzing the time series; they capture the volatility clustering behavior of financial stock data. Some Bayesian analysis based on Markov Chain Monte Carlo method have been also successful in estimating the parameters of GARCH. Moreover, the Reversible Jump Markov Chain Monte Carlo (RJMCMC) gives us a way to the model selection problem; it enables the Gibbs samplers to jump between models with different space. Instead of choosing from the existing models, we generalize the idea of RJMCMC to possibly infinite number of model choices. In addition, we also consider the threshold AR-GARCH model and fit it to the stock data (Taiwan stock index, 2003- 2006). In the future research, we’d like to apply the RJMCMC to the unequal size of variance parameters of GARCH model. Together with our method in this thesis, the best AR-GARCH models can be thus automatically chosen.

參考文獻


Engle, R.F., Lilien, D.M. and Robins, R.P. (1987), ”Estimating Time Varying
applications. Biometrika”,97-109.
Akaike, H. (1969), ”Fitting Autoregressive Models for Prediction,” Annals of the
Institute of Statistical Mathematics 21, 243-247.
Akaike, H.(1973), ”Information Theory and an Extension of the Maximum Likelihood

被引用紀錄


黃韋勝(2013)。型一區間設限韋伯分配資料之WinBUGS貝氏分析〔碩士論文,中原大學〕。華藝線上圖書館。https://doi.org/10.6840/cycu201300563
張志賢(2013)。型一區間設限廣義指數分配資料之WinBUGS貝氏分析〔碩士論文,中原大學〕。華藝線上圖書館。https://doi.org/10.6840/cycu201300562
褚思暐(2011)。廣義伽瑪分配逐步型一區間設限資料之貝氏分析〔碩士論文,中原大學〕。華藝線上圖書館。https://doi.org/10.6840/cycu201100982
許文志(2010)。逐步型I區間設限資料的貝氏分析〔碩士論文,中原大學〕。華藝線上圖書館。https://doi.org/10.6840/cycu201000543
謝明軒(2009)。ARMA-GARCH 模型之貝氏分析〔碩士論文,中原大學〕。華藝線上圖書館。https://doi.org/10.6840/cycu200901028

延伸閱讀