臺灣博碩士論文加值系統

本文利用高斯混合模型，參考Fraley and Raftery (2002) 將共變異數矩陣分為十種不同的模型假設，以此十個模型作為分群模型的基準。變數方面參考Altman (1968)、Shumway (2001)、Duffie (2007)、及Campbell (2008)等學者的論文，再參考財經相關書籍，提出22種變數。本研究從這22種變數中找出最好的5個，應用高斯混合模型的十個模型假設，發現VEI模型在選定的變數組合下，有著很好的表現。最後將本研究表現最好的分群結果，與台灣經濟新報(TEJ)的台灣企業信用風險指標分類(TCRI)做比較，結果顯示本研究耗費成本低但也有優秀的分群結果。

This paper used the Gaussian mixture model to find credit risk. The author referred to Fraley and Raftery (2002), used the covariance that parameterized by eigenvalue decomposition and got ten models. As for the variables, the author extracted 22 variables from Altman (1968), Shumway (2001), Duffie (2007), Compbell (2008), and several financial related books. The author selected five variables and collocated with the ten Gaussian mixture models. The result indicated that the VEI model performed well combined with the variables that the author found. Compared with the classification of TEJ TCRI, the empirical result indicated that the author’s classification result had better classified result.

壹、緒論 ................................................ 1
一、研究動機與背景 ...................................... 1
二、研究架構 ............................................ 3
貳、文獻回顧............................................. 5
參、研究方法與設計 ...................................... 7
一、混合模型 ............................................ 7
二、期望-最大化演算法 ................................... 9
三、分群依據 ........................................... 13
(一) 脆弱模型........................................... 13
(二) 型I 型II 誤差 ..................................... 14
四、集群分析 ........................................... 14
(一) 基於模型階層式分群 ..................................................... 15
(二) 結合階層式分群、最大期望演算法和脆弱模型 .......... 15
肆、實證設計.............................................17
一、研究樣本 ..................................................... 17
(一) 資料來源...................................................... 17
(二) 台灣企業信用風險指標 .............................. 17
(三) 危機的定義 ........................................ 19
二、研究變數 ........................................... 21
伍、實證結果.............................................27
陸、結論 ................................................45
參考文獻 ................................................46

Altman, E. I. (1968), “Financial Ratios, Discriminant Analysis, and the Prediction of
Corporate Bankruptcy,” Journal of Finance, 23, 589-609.
Banfield, J. D. and Rafter, A. E. (1993), “Model-Based Gaussian and Non-Gaussian
Clustering,” Biometrics, 49, 803-821.
Bensmail, H. and Celeux, G. (1996), “Regularized Gaussian Discriminant Analysis
Through Eigenvalue Decomposition,” Journal of the American Statistical
Association, 91, 1743-1748.
Bharath, S. T. and Shumway, T. (2008), “Forecasting Default with the Merton
Distance to Default Model,” Review of Financial Studies, 21, 1339-1369.
Campbell, J.Y., Hilscher, J. and Szilagyi, J. (2008), “In search of distress risk,”
Journal of Finance, 63, 2899-2939.
Chava, S., Stefanescu, C., and Turnbull S. (2008), “Modeling the loss distribution,”
(http://faculty.london.edu/cstefanescu/research.html)
Cox, D. R. (1972), “Regression models and life-tables,” Journal of Royal Statistical
Society, Series B (Methodological), 34, 187-220.
Duffie, D., Saita, L. and Wang, K. (2007), “Multi-period corporate default prediction
with stochastic covariates,” Journal of Financial Economics, 83, 635–665.
Farley, C. and Raftery, A. E. (2002), “Model-Based Clustering, Discriminant Analysis,
and Density Estimation,” Journal of the American Statistical Association, 97,
611-631.
Fraley C. and Raftery A. E. (2006), “MCLUST Version 3 for R: Normal mixture
modeling and model-based clustering,” Technical Report No. 504, Department
of Statistics University of Washington, Seattle, USA.
Johnson, R. A. and Wichern, D. W. (2007), Applied Multivariate Statistical Analysis
(6th ed.), Pearson Prentice Hall, Upper Saddle River, New Jersey.
Kaplan, R. S. and Urwitz, G. (1979), “Statistical models of bond ratings: A
methodological inquiry,” Journal of Business, 52, 231-261.
Lando, D. and Skodeberg, Torben M. (2002), “Analyzing ratings transitions and rating
drift with continuous observations,” Journal of Banking and Finance, 26,423-444.
Lau, A. H. L. (1987), “A Five-State Financial Distress Predication Model”, Journal of
Accounting Research, 25, 127-138.
McLachlan, G. J. and Basford, K. E. (1988), Mixture Models: Inference and
Applications to Clustering, New York, Marcel Dekker.
Ohlson, J. (1980), “Financial ratios and the probabilistic prediction of bankruptcy,”
Journal of Accounting Research, 18, 109-131.
Shumway, T. (2001), “Forecasting bankruptcy more accurately: A simple hazard
model,” Journal of Business, 74, 101-124.
Wolfe, J. H. (1970), “Pattern Clustering by Multivariate Mixture Analysis,”
Multivariate Behavioral Research, 5, 329-350.
Zmijewski, M. E. (1984), “Methodological issues related to the estimation of financial
distress prediction models,” Supplement to Journal of Accounting Research, 22,
59-82.
黃瑞卿、蕭兆祥、鐘惠民 (2009), ”自我相關結構信用評等之預測,” Review of
Securities & Futures Markets, 21, 43-70