2020年持續整年最引人注目的議題為新冠肺炎(COVID-19)，也被稱為第二次世界大戰以來全球面臨最嚴峻的危機，對眾多產業帶來衝擊，造成市場氣氛惡化而國際金融市場更是大幅震盪。
本文研究主要為探討，台灣加權股價指數、上海綜合指數股價指數、中國深圳成分股指數、日經225指數、韓國綜合指數、美國紐約道瓊工業平均指數、那斯達克100指數、美國紐約S&P500股價指數等指數，在極端事件下的風險值，將多個市場針對新型冠狀病毒的風險影響，並將極值理論加入GARCH家族模型，形成GARCH-EVT、E-GARCH-EVT、GJR-GARCH-EVT模型進行比較做分析，同時觀察新冠肺炎(COVID-19)疫情前和後疫情時期風險值的之變化，並根據回測結果討論何種模型將能產生較佳結果。
本研究實證結果顯示，使用GARCH模型與加入極值的GARCH模型結果中，多數國家均顯示COVID-19後期風險值有降低的現象。最後再透過概似比檢定比較各模型間的評估績效。綜合而言，在本研究樣本下，GARCH家族模型比加入極值理論後所計算的風險值，表現並未較佳。

The most notable issue that will continue throughout the year in 2020 is the new crown pneumonia (COVID-19), also known as the most severe crisis the world has faced since the Second World War, which has impacted many industries and caused a deterioration in market sentiment. The financial market fluctuates sharply. 

This research mainly discusses the Value at Risk of Taiwan Capitalization Weighted Stock Index, Shanghai Composite Index stock price index, China Shenzhen constituent stock index, Nikkei 225 Index, Korea Composite Index, New York Dow Jones Industrial Average, Nasdaq 100 Index, New York S&P500 Indices such as stock price index, the value of risk under extreme events, the risk impact of multiple markets against the new coronavirus, and the extreme value theory is added to the GARCH family model, Form GARCH-EVT, E-GARCH-EVT, GJR-GARCH-EVT models for comparison and analysis. At the same time, observe the changes in the risk value of the new coronary pneumonia (COVID-19) before and after the epidemic, and discuss what to do based on the backtest results This model will produce better results.

Form GARCH-EVT, E-GARCH-EVT, GJR-GARCH-EVT models for comparison and analysis. At the same time, observe the changes in the risk value of the new coronary pneumonia (COVID-19) before and after the epidemic, and discuss what to do based on the backtest results This model will produce better results.

目錄
目錄IV
表目錄VI
圖目錄VII
第一章　緒論1
第一節 研究背景與動機1
第二節 研究目的2
第三節 研究架構與流程4
第二章　理論與相關文獻6
第一節 風險值的相關文獻6
第二節 GARCH模型的相關文獻9
第三節 極值理論的相關文獻11
第三章　研究方法14
第一節 研究資料定義與來源14
第二節 簡述GARCH、E-GARCH、GJR-GARCH模型定義15
第三節 簡述GARCH-EVT、E-GARCH-EVT 與 GJR-GARCH-EVT 模型18
第四節 風險值模型19
第五節 概似比檢定21
第四章　實證結果與分析22
第一節 敘述統計量分析22
第二節 單根檢定31
第三節 GARCH、E-GARCH 與 GJR-GARCH模型風險值估計32
第四節 GARCH-EVT、E-GARCH-EVT 與 GJR-GARCH-EVT模型風險值估計35
第五節 績效評估結果38
第五章　結論與建議46
第一節 結論46
第二節 建議47
參考文獻48

 
表目錄
表 1 研究對象基本資料14
表 2 疫情前期股票指數報酬率之基本敘述統計量22
表 3 疫情後期股票指數報酬率之基本敘述統計量26
表 4 報酬率單根檢定結果31
表 5 八個標的在疫情前後的GARCH風險值32
表 6 八個標的在疫情前後的E-GARCH風險值33
表 7 八個標的在疫情前後的GJR-GARCH風險值34
表 8 八個標的在疫情前後的GARCH-EVT風險值35
表 9 八個標的在疫情前後的E-GARCH-EVT風險值36
表 10 八個標的在疫情前後的GJR-GARCH-EVT風險值37
表 11 台灣加權指數之穿透次數與穿透率38
表 12 上證指數之穿透率與穿透次數39
表 13 深圳指數之穿透次數與穿透率40
表 14 日經225指數之穿透次數與穿透率41
表 15 韓國綜合指數之穿透次數與穿透率41
表 16 道瓊指數之穿透次數與穿透率42
表 17 那斯達克100指數之穿透次數與穿透率43
表 18 S&P500指數之穿透次數與穿透率44
表 19 八個標的在疫情前後的穿透次數模型比較45


 
圖目錄
圖 1 研究架構流程圖5
圖 2 疫情前期之台灣加權每日報酬率時間序列圖23
圖 3 疫情前期之上證、深圳每日報酬率時間序列圖23
圖 4 疫情前期之日經225、韓國綜合每日報酬率時間序列圖24
圖 5 疫情前期之道瓊、那斯達克100、S&P500每日報酬率時間序列圖24
圖 6 疫情前期之8個研究對象報酬率之常態檢定各圖形26
圖 7 疫情後期之台灣加權每日報酬率時間序列圖27
圖 8 疫情後期之上證、深圳每日報酬率時間序列圖28
圖 9 疫情後期之日經225、韓國綜合每日報酬率時間序列圖28
圖 10 疫情後期之道瓊、那斯達克100、S&P500每日報酬率時間序列圖28
圖 11 疫情後期之八個研究對象報酬率之常態檢定各圖形30

參考文獻
一、中文文獻
1.毛臆菱(2020)，美國、中國與台灣股票指數極端風險值的績效之影響，淡江大學財務金融學系碩士班碩士論文。
2.王藝臻(2018)，探討影響台灣地區銀行系統性風險的影響因素: CoVaR風險值的應用與實證分析，南華大學管理學院財務金融學系碩士班碩士論文。
3.江厚德(2016)，不同計算風險值的方法的實例比較，國立中央大學統計學系碩士班碩士論文。
4.許和鈞、盧陽正、李儀坤、王麗惠、李忠榮和王牲(2003)，利用風險值(VaR at Risk)內部模型法提昇證券商衍生性商品業務之風險控管效能，台灣證券交易所委託研究報告。
5.陳典煜(2019)，以風險值(VaR)建構投資決策模型-以台灣五十成分股及台指期為例，國立雲林科技大學財務金融學系碩士班碩士論文。
6.陳庭昱(2019)，以Copula-GARCH模型及其他傳統方法估計比特幣投資組合之風險值，國立清華大學計量財務金融學系碩士班碩士論文。
7.劉彥伶(2018)，台灣指數期貨盤後交易開放之風險值評估台灣指數風險價值評估，東吳大學國際經營與貿易學系碩士班碩士論文。

二、英文文獻
1.Balkema, A. A. and L. de Haan (1994), “Residual Life Time at Great Age,” Annals of Probability, Vol.2, No.5, pp.792-804. 
2.Chinhamu, K, C. K. Huang, C.S. Huang, and D. Chikobvu, (2015), “Extreme Risk, Value-At-Risk and Expected Shortfall in the Gold Market,” International Business & Economics Research Journal, Vol.14,No.1, pp.107-122.
3.Echaust, K. and M. Just, (2020), “Value at Risk Estimation Using the GARCH-EVT Approach with Optimal,” Tail Selection. Mathematics, Vol.8,No.114, pp. 1-22.
4.Engle, R. F. (1982), “Autoregressive Conditional Heteroscedasticity with Estimates of the Variance of United Kingdom Inflation,” Econometrica, Vol.50, No.4, pp. 987-1008. 
5.Engle, R. F. (1990), “Discussion: Stock Market Volatility and the Crash of ’87.” Review of Financial Studies, Vol.3, No.1, pp.103-106.
6.Gencay, R. and F. Selcuk, (2004), “Extreme Value theory and Value-at-Risk: Relative Performance in Emerging Markets,” International Journal of Forecasting, Vol.20, pp.287-303. 
7.Glosten, L.R., R. Jagannathan and D. Runkle, (1993), “On the Relation between the Expected Value and the Volatility of the Nominal Excess Return on Stocks,” Journal of Finance, Vol.48, pp.1779-1801.
8.Hsu ,C.P., C. W. Huang and W.J.P. Chiou, (2012), “Effectiveness of Copula-Extreme Value Theory in Estimating Value-at-Risk: Empirical Evidence from Asian Emerging Markets,” Review of Quantitative Finance and Accounting, Vol.39, pp.447–468.
9.Jammazi, R. and D. K. Nguyen, (2017), “Estimating and Forecasting Portfolio’s Value-At-Risk With Wavelet-Based Extreme Value Theory: Evidence From Crude Oil Prices And US Exchange Rates,” Journal Of the Operational Research Society, Vol. 68, pp.1352-1362.
10.Kim, H. L.(2008), “Extreme Returns and Value at Risk in International Securitized Real Estate Markets,” Journal of Property Investment & Finance, Vol.26,No.5, pp.418-446.
11.Kjellson, B. (2013), “Forecasting Expected Shortfall: An Extreme Value Approach,” Mathematical Statistics, No.1, pp.1-36.
12.Kupiec, P. H. (1995), “Techniques for Verifying the Accuracy of Risk Measurement Models,” The Journal of Derivatives Winter, Vol.3,No.2, pp.73-84. 
13.Li, L. (2017), “A Comparative Study of GARCH and EVT Model in Modeling Value-at-Risk,” Journal of Applied Business and Economics, Vol.19,No.7, pp.27-48.
14.Maghyereh, A. I., and H. A. Ai-Zoubi, (2006), “Value‐at‐Risk Under Extreme Values: The Relative Performance in MENA Emerging Stock Markets,” International journal of managerial finance, Vol.2,No.2, pp.154-172.
15.Mögel, B. and B. R. Auer (2018), “How accurate are modern Value-at-Risk estimators derived from extreme value theory?” Review of Quantitative Finance and Accounting, Vol.50,No.4, pp.979-1030.
16.Nelson, D. B. (1991),”Conditional Heteroskedasticity in Asset Returns: A New Approach,” Econometrica, Vol.59,No.2, pp.347-370. 
17.Nguyen, S. P. and T.L.D. Huynh, (2019), “Portfolio Optimization from A Copulas-GJRGARCH-EVT-CVAR Model: Empirical Evidence from ASEAN Stock Indexes,” Quantitative Finance and Economics, Vol.3, No.3, pp.562-585.
18.Ozun, A., C. Atilla and S. Yılmazer, (2010), “Filtered Extreme-Value Theory For Value-At-Risk Estimation: Evidence From Turkey,” The Journal of Risk Finance, Vol.11, No.2, pp.164-179.
19.Pickands, J. (1995), “Statistical Inference Using Extreme Order Statistics,” The Annals of Statistics, Vol.3, pp.119-131. 
20.Radivojevic, N., C. Milena and S. Stepanov, (2016), “The New Hybrid Value at Risk Approach Based on The Extreme Value Theory,” Estudios de economía , Vol.43, No.1, pp.29-52.
21.Singh, A.K., D. E. Allen., and R.J. Powell, (2011), “Value At Risk Estimation Using Extreme Value Theory,” 19th International Congress on Modelling and Simulation, pp.1478-1484.
22.Soltane, H.B., A. Karaa, and M. Bellalah, (2012), “Conditional VaR using GARCH-EVT Approach: Forecasting Volatility in Tunisian Financial Market,” Journal of Computations & Modelling, Vol.2,No.2, pp.95-115.
23.Vee, D.A.N.N.C., P. N. Gonpot, and N.U.H. Sookia, (2014), “Forecasting Value-At-Risk For Frontier Stock Market Indexes Using GARCH-type Models And Extreme Value Theory: Model Validation For Dynamic Models,” The Journal of Risk Model Validation, Vol. 8, No.4, pp.47-67.
24.Wang ,M. (2017), “Estimation of Extreme Risk Models: GARCH-EVT and SV-EVT Approaches,” Amsterdam School of Economics, master’s thesis,pp.1-37.