公司財務危機預測能力之提升：使用修正KMV模型

Using the Modified KMV Model to Promote the Ability of Forecasting Corporate Financial Distress

10.30003/JRM.200912.0003

穆衍東(Yan-Dong Mu)；韓千山(Chien-Shan Han)；林玫伶(Mei-Ling Lin)

修正KMV模型 ； 違約距離 ； Logistic廻歸模型 ； 群內分析法 ； Modified KMV Model ； Distance to Default ； Logistic Regression Model ； Intra-Cohort Analysis

風險管理學報

11卷2期（2009 / 12 / 01）

171 - 195

繁體中文

國內文獻通常KMV模型來預測公司財務危機。KMV模型以資產小於流動負債加二分之一長期負債做為違約點（DPT, default point）。然而本文蒐集了台灣在2001年到2008年共67家違約公司，發現這些公司在發生違約當季的資產並未達到違約點，但卻有過半公司的流動資產小於流動負債。因此本文修正KMV模型，以流動資產小於流動負債時，公司就會發生財務危機。在67家違約公司與132家正常公司配對資料下，檢視發生違約時點前四季的違約距離的變化。根據群內分析法（the intra-cohort analysis）與Logistic廻歸分析，發現本文所發展的修正模型對財務危機預測能力明顯優於KMV。且隨著違約時間點的接近，修正模型的預測效果更佳。

The domestic literatures often used the KMV model to forecast the financial distress. The default occurs when the asset value below the short term debt plus half the long term debt considered by KMV model. However, many literatures documented this methods exhibit poor forecast ability. Moreover, we collect 67 distressed firms in Taiwan from 2001 to 2008, and find the asset values of all distressed firms are still higher than default points defined by KMV. On the contrary, about half of the distressed firms suffer current assets are lower than current liabilities. Using the data of 67 distressed firms to collocate with 132 normal firms, we investigate the variations in the distance to default from four seasons prior to default. According to the intra-cohort analysis and logistic regression, we found that forecast ability of the distance to default defined by current assets and current liabilities is significantly better than the distance to default defined by KMV. Furthermore, when the default time comes closer, the modified KMV forecast ability will become more accurate.

1. 張大成(2003)。違約機率與信用評分模型。台灣金融財務季刊，4(1)
   連結：
2. 陳業寧、王衍智、許鴻英(2004)。台灣企業財務危機之預測：信用評分法與選擇權評價法孰優？。風險管理學報，6(2)，155-179。
   連結：
3. Allen, L.,G. Delong,A. Saunders(2004).Issues in the Credit Risk Modeling of Retail markets.Journal of Banking and Finance,28,727-752.
4. Altman, E. I.(1968).Financial Ratios, Discriminate Analysis and the Prediction of Corporate Bankruptcy.Journal of Finance,23,589-609.
5. Beaver, W. H.(1966).Financial Ratios as Predictor of Failure.Journal of Accounting Selected Studies,44-62.
6. Bin, Z.,J. Zhang(2001).An Empirical Assessment of Asset Correlation Models.KMV Corporation.
7. Crosbie, J. P.(1999).Modeling Default Risk.San Francisco, California, U.S.A.:KMV.
8. Duffie, D.,K. J. Singleton(2003).Credit Risk: Pricing, Measurement, and Management.Princeton, NJ.:Princeton University Press.
9. Jarrow, R. A.,S. M. Turnbull(2000).The Intersection of Market and Credit Risk.Journal of Banking and Finance,24,271-299.
10. Jeffrey, R. B.(1999).Using Marking Data to Value Credit Risky Instruments.KMV Corporation.
11. John, C. H.,I. Nelken,A. White(2004).Merton's Model, Credit Risk and Volatility Skews.Journal of Credit Risk,1(1),3-28.
12. Merton, R.(1974).On the Pricing of Corporate Debt.Journal of Finance,28,449-470.
13. Ohlson, J. A.(1980).Financial Ratios and the Probabilistic Prediction of Bankruptcy.Journal of Accounting Research,18,109-131.
14. Sanjiv, R. D.,L. Freed,G. Geng,N. Kapadia(2003).Correlated Default Risk, EFA 2003 Annual Conference Paper, 928.DC Meetings:AFA 2003 Washington.
15. Saunders, A.,L. Allen(2002).Credit Risk Measurement: New Approaches to Value at Risk and Other Paradigms.New York:John Wiley and Sons.
16. Shumway, T.(2004).Forecasting Bankruptcy More Accurately: A Simple Hazard Model.Journal of Business,74,101-124.
17. Sreedhar, T. B.,T. Shumway(2004).Forecasting Default with the KMV-Merton Model.AFA 2006 Boston Meetings Paper.
18. Stephen, K.,J. R. Bohn(2001).Portfolio Management of Default Risk.San Francisco, California, U.S.A.:KMV.
19. 沈大白、張大成、劉宛鑫(2002)。信用評等模型之簡介。中國商銀月刊，21(11)，1-5。
20. 沈大白、敬永康(2001)。新版巴賽爾資本協定下。貨幣觀測與信用評等，29，111-121。
21. 沈大白、敬永康(2001)。新版巴賽爾資本協定上。貨幣觀測與信用評等，28，113-123。
22. 林妙宜(2002)。國立政治大學金融研究所。
23. 林秀玫(2003)。淡江大學財務金融研究所。
24. 林景春、陳達新、林允永、邱智偉(2000)。銀行授信風險評估：KMV實質選擇權理論的應用。產業金融季刊，108，28-37。
25. 黃明祥、許光華、黃榮彬、陳鈺玲(2005)。KMV模型在台灣金融機構信用風險管理機制有效性之研究。財金論文叢刊，3，29-50。
26. 黃建隆(2003)。文化大學會計研究所。
27. 鄭寶琳(2004)。政治大學經營管理研究所。