臺灣博碩士論文加值系統

風險值為現今主要風險管理下之衡量工具，但在傳統的風險值模型中，並不重視流動性風險，使得風險值無法提供投資者真實的資訊，另外可能因錯估風險值，而造成更大的損失。流動性風險是指資產在市場所揭露的價格與實際上的買賣價格不一致，而所產生的問題。本研究利用Bangia et al.（1999）所提出考慮價差因子下的流動性風險之衡量方法；加入Erwan（2001）所提出的內生性流動性風險衡量方法；另外對於GARCH模型加入流動性因子以衡量流動性風險，希望能夠有效預估流動性風險所產生的損失。同時利用歷史模擬法來進行風險值估計，觀察衡量流動性模型與傳統模型之間的差異性。透過風險值的檢定方法對風險值表現予以比較，以觀察衡量流動性風險模型的預測能力是否準確。本文挑選40家公司股票作為研究標的，再區分成交量高低為兩類組。實證結果上發現，在信賴水準99%下所做的失敗率檢定於各模型之表現並無顯著差距，透過概似比檢定結果各模型之p-value大都大於0.1，表示各模型的預測能力都相當高，透過成交量分群的結果則顯示出，並不因成交量之區分，而在檢定結果上有顯著差異。對信賴水準95%下之失敗率檢定結果，各模型之失敗率顯著偏低，表示各模型普遍高估風險，因此信賴水準95%下各模型所估計出風險值較為保守，在概似比率檢定結果，預測能力並無顯著提升，說明考慮流動性風險之模型較能有效預測極端事件。

Value at Risk（VaR） was main tool of market risk management but traditional VaR did not appreciate liquidity risk to make that VaR did not give correct information and was misvalue VaR to lead a large number of damages. Generally speaking liquidity risk was that asset which was disclosed price at market was different with actual bid-ask price to make problem. Bangia et al.（1999） propose to account spread to produce measure exogenous liquidity risk model and other Erwan（2001）propose to measure endogenous liquidity risk model and the other GARCH model which added liquidity factor came to measure liquidity risk that those models by calculated hoped get liquidity adjust VaR to make actual loss. We simultaneity used Historical Simulation to compare traditional VaR and liquidity adjusted VaR. Using ULR test（Uncovered Loss Ratio）and LR test（Likelihood Ratio Test） to cognizance performance of the models if forecasted ability of the models had been accurately. We examined the forty individual stocks which were random and they differentiate larger volume group and lower volume group. We found the key results as follow: In 99% confidence level those models did not signally different at ULR test and their p-value were 0.1 at LR test therefore they forecast well and then differentiate volume the answers did not different. In 95% confidence level those models performed poor at ULR test and they did not help forecast VaR more accurately at LR test. Therefore we could think that liquidity adjusted VaR would forecast extreme event.

目次

第一章 緒論 1
第一節 研究動機 1
第二節 研究目的 2
第三節 論文架構 2
第四節 研究流程 4
第二章 文獻回顧 5
第一節 風險值 5
第二節 流動性 7
第三節 流動性風險 11
第四節 價差對流動性的衡量 13
第三章 研究方法 15
第一節 歷史模擬法 15
第二節 外生性流動性風險衡量 15
第三節 內生性流動性風險衡量 17
第四節 流動性GARCH模型 19
第五節 風險值模型檢定方法 22
一、回溯測試（Back Test） 22
二、失敗率檢定（Uncovered Loss Ratio, ULR） 22
三、概似比率檢定法（Likelihood Ratio Test） 23
第四章 實證分析 24
第一節 資料敘述與統計分析 24
第二節 風險值的估計 26
一、99%的風險值 27
二、95%的風險值 28
三、小結 28
第五章 結論與建議 30
參考文獻 32

表目錄


表2.1各風險值模型比較 7
表4.1.成交量高公司的報酬下的基本統計量 34
表4.2 成交量低公司的報酬下的基本統計量 35
表4.3 成交量高的公司在99%下的各模型實證結果 36
表4.4 成交量低的公司在99%下的各模型實證結果 37
表4.5 成交量高的公司在95%下的各模型實證結果 38
表4.6 成交量低的公司在95%下的各模型實證結果 39

圖目錄

圖1.1 研究流程 4
圖4.1 99%失敗率測試 40
圖4.2 99%概似比率檢定p-value 41
圖4.3 95%失敗率測試 42
圖4.4 95%概似比率檢定p-value 43

中文文獻
1.陳嘉平，（2000），「流動性風險、漲跌幅限制與風險衡量」，台灣大學財務金融學系碩士論文。
2.黃于珍，（2002），「流動性風險衡量」，中國文化大學商學院會計學系碩士論文。
3.彭裕嘉，（2003），「分量迴歸在流動性風險上的運用」，中正大學企業管理學系碩士論文 。
4.詹場、胡星陽，（2000），「流動性衡量方法之綜合評論」，國家科學委員會研究彙刊，第11卷第3期，205-221。
英文文獻
1.Amihud, Y. and H. Mendelson（1989）. “The effect of computer base trading on volatility and liquidity.” In: H.C. Lucas & R.A. Schwartz（Eds.）, The challenge of information technology for the securitites markets, liquidity, volatility, and global trading”. Homewood, IL: Dow Jones & Company, Inc. 59-85
2.Andersen, T. G. and T. Bollerslev, （1997）, “Intraday periodicity and volatility persistence in financial markets.”Journal of Empirical Finance 4, 115-158.
3.Aitken, Michael and Carole Comerton-Forde（2003）. “How Should Liquidity Be Measured?”Pacific-Basin Finance Journal, 45-59.
4.Huang, R. D and H. S Stoll（1996）. “Dealer versus auction markets: A paired comparison of execution costs on NASDAQ and the NYSE.”Journal of Financial Economics, 41, 313-357
5.Bangia, A., F. x. Diebold, T. Shuermann and J. D. Stroughair（1999）. “Modeling Liquidity Risk, with Implication for Traditional Market Risk Measurement and Management.” Working Paper.
6.Berkowitz, J.（2000）. “Incorporating Liquidity Risk into Value-at-Risk Models.” Working Paper.
7.Bollersler, T.（1986）“Generalized Autoregressive Conditional Heteroscedasticity.” Journal of Econometrics, 31, 307-327.
8.Dowd, K.（1998）“Beyond Value at Risk: the New Science of Risk Management. ” John Wiley and Son.
9.Erwan, L. S.（2001）. “Incorporating Liquidity Risk on VaR Models.” Working paper.
10.Giot, P. and G. Joachim（2003）. “How large is liquidity risk in an automated auction market.” Working paper.
11.Glosten, L. R and L. E. Harris （1988）. “Estimating the component of the bid/ask spread.” The Journal of Financial Economics, 21, 123-142.
12.Hendricks, D（1996）“Evaluation of Value-at-Risk Models using Historical Data.”Federal Reserve Bank of New York Economic Policy Review 2, 39-69.
13.Jorion, P.（1996）. Value at Risk, McGraw-Hill.
14.Jorion, P.（2000）. Value at Risk, McGraw-Hill.
15.Jorion, P. （2000）. “Risk Management Lessons from Long-Term Capital Management.” European Financial Management, 6, 277-300.
16.Kyle, A.S. （1985）. “Continuous auctions and insider trading.” Econometrica, 53, 1315-1335.
17.Lawrence, C and G. Robinson （1998）. “Liquidity, Dynamic Hedging and Value at Risk.” in Risk Management for Financial Institutions, ed. Risk Publications, 63-72..
18.O’Hara, M.（1995）. Market Microstructure Theory. Cambridge: Blackwell Publisher Inc.
19.Roll, R.A. （1984）.“A simple implicit measure of the effective bid-ask spread in an efficient market.” The journal of Finance, 39, 1127-1139.
20.Schwartz, R.A. （1988）. Equity markets: Structure, Trading, and Performance. New York: Harper and Row, Inc.
21.Stoll, H.R. （1989）. “Inferring the components of the bid-ask spread : Theory and empirical test.” The Journal of Finance, 44, 115-134.
22.Upper, C.（2000）. “How Safe was the Safe Haven? Financial Market Liquidity during the 1998 Turbulences.” Discussion paper, Economic Research Group of the Deutsche Bundesbank.