脆弱相關違約模型－台灣上市櫃公司實證研究

Frailty Correlated Default Model: An Empirical Study for Taiwan Companies

10.29973/JCSA.201109.0002

黃瑞卿(Ruey-Ching Hwang)；諶自強(Zih-Ciang Chen)

脆弱因子 ； 強度函數 ； 馬可夫鏈蒙地卡羅 ； 蒙地卡羅期望－最大化演算法 ； 危機預測家數 ； 預測區間 ； frailty factor ； intensity function ； Markov Chain Monte Carlo ； Monte Carlo expectation-maximization algorithm ； predicted number of distresses ； predictive interval

中國統計學報

49卷3期（2011 / 09 / 01）

98 - 122

繁體中文

本文應用Duffie et al.(2009)所提議的脆弱相關違約模型(frailty correlated default model)預測台灣上市櫃公司的財務危機機率。該模型爲在違約強度模型(default intensity model; Duffie et al. 2007)中加入脆弱因子(frailty factor)，以解釋台灣潛在總體動態因子(latent macroeconomic dynamic factor)。本文收集Altman變數(Altman1968)、Campbell變數(Campbell et al. 2008)、Duffie變數(Duffieet al. 2007)、與Shumway變數(Shumway 2001)等四組解釋變數資料，並將4組解釋變數資料分別應用在脆弱相關違約模型與違約強度模型中，因此總共有8種解釋變數與模型的組合。實證結果顯示，脆弱相關違約模型比違約強度模型，提供較多公司發生財務危機的訊息，以及產生較正確的樣本外(out-of-sample)財務危機機率預測值；在這8種解釋變數與模型的組合中，以Campbell變數與脆弱相關違約模型的組合，具有最好的樣本外表現。

In this paper, the frailty correlated default model (Duffie et al. 2009) is suggested to predict the financial distress probabilities for Taiwan companies. It is built by applying the frailty factor to the default intensity model (Duffie et al. 2007). The frailty factor is used to explain the latent macroeconomic dynamic factor. To build the frailty correlated default model for Taiwan corporations, we collect time-varying predictor values for each set of Altman's predictors (Altman 1968), Campbell's predictors (Campbell et al. 2008), Duffie's predictors (Duffie et al. 2007), and Shumway's predictors (Shumway 2001). The empirical results indicate that, for each panel dataset, the frailty correlated default model is better than the default intensity model, in the sense of yielding more information about financial distresses, and more accurate firm-by-firm financial distress probabilities in out-of-sample analysis. Also, the frailty correlated default model using Campbell's predictors has the best out-of-sample performance.

1. Duan, J. C. (2010). Clustered Defaults. National University of Singapore. Working paper.
2. Altman, E. I.(1968).Financial ratios, discriminant analysis, and the prediction of corporate bankruptcy.The Journal of Finance,23,589-609.
3. Bharath, S. T.,Shumway, T.(2008).Forecasting default with the KMV-Merton model.Review of Financial Studies,21,1339-1369.
4. Campbell, J. Y.,Hilscher, J.,Szilagyi, J.(2008).In search of distress risk.The Journal of Finance,62,2899-2939.
5. Cohen, R. B.,Polk, C.,Vuolteenaho, T.(2003).The value spread.The Journal of Finance,58,609-641.
6. Davis, J. L.,Fama, E. F.,French, K. R.(2000).Characteristics, covariances, and average returns: 1929 to 1997.The Journal of Finance,55,389-406.
7. Duffie, D.,Eckner, A.,Horel, G.,Saita, L.(2009).Frailty correlated default.The Journal of Finance,64,2089-2123.
8. Duffie, D.,Saita, L.,Wang, K.(2007).Multi-Period corporate default prediction with stochastic covariates.Journal of Financial Economics,83,635-665.
9. Hillegeist, S. A.,Keating, E. K.,Cram, D. P.,Lundstedt, K. G.(2004).Assessing the probability of bankruptcy.Review of Accounting Studies,9,5-34.
10. Ohlson, J.(1980).Financial ratios and the probabilistic prediction of bankruptcy.Journal of Accounting Research,18,109-131.
11. Shumway, T.(2001).Forecasting bankruptcy more accurately: A simple hazard model.The Journal of Business,74,101-124.
12. Wei, G. C. G.,Tanner, M. A.(1990).A Monte Carlo implementation of the EM algorithm and the poor man's data augmentation algorithm.Journal of The American Statistical Association,85,699-704.
13. Zmijewski, M. E.(1984).Methodological issues related to the estimation of financial distress prediction models.Supplement to Journal of Accounting Research,22,59-82.

1. 陳美源、林庚諭(2016)。台灣上市公司違約群聚性的再探討：產業及時間脆弱因子觀點。中國統計學報，54(1)，1-25。