臺灣博碩士論文加值系統

本研究主要是希望能夠將信用評分模型所得出的結果進行評等研究，進以觀察不同信用評分模型是否會對最後的信用評等結果造成影響；在研究中，除了以Logit模型與多元區別分析模型進行比較分析外，還使用兩種資料處理方法，同時比較在不同的資料處理下，是否亦會對信用評等的結果產生影響。
在樣本資料中，主要是用台灣經濟新報中，上市上櫃與曾經上市上櫃公司資料庫，其最後，整理出來的資料結果，共有14125筆公司財務資料可以進行完整的實証分析，違約公司資料有153筆；並將這此公司的財務變數進行線性相關變異數影響因子檢定，並將評分模型所得出的結果進行K–S檢定與ROC驗証，最後再將評分結果進行集區分析以及評等穩定度的檢定，其結果所得出的結果包括下列幾點：
1、經過極端值調整處理過後的資料，對信用評分模型的區別能力有正面的效果，但是這樣的資料處理對評等結果而言，卻不一定能夠增加評等穩定度。
2、Logit模型在原始資料下的表現較多元區別分析模型來得好，而在經過資料處理過後，這樣的結果依然相同。
3、不同信用評分模型以及不同資料處理的評分結果，都會對信用評等的結果造成影響，其中區別能力愈好的模型，其後面的等級違約率差別愈大。
4、在綜合評分模型的區別能力、各等級的違約率以及評等穩定度之後，經過資料調整過後的Logit模型整體表現最好。

The purpose of this paper is mainly in the hope of using different credit scoring models to make cluster, and to observe the impact of credit scoring models on cluster. In this paper, we not only compare the difference between Logit model and Multiple Discriminate Analysis (MDA) model, but also compare the results acquired from two kinds of different data.
In sample data, we use the database of Taiwan Finance Database of Taiwan Economic Journal and collect 14,125 company’s’ finance data which include 153 default company’s’ data to study. We use these financial data to make Variance Inflation Factor (VIF) test, and use the result of credit scoring model to make Kolmogorov–Smirnov (K-S) test and Receiver Operating Characteristic (ROC) check. Finally, the conclusions are listed as following:
1, The ability of credit scoring model can be improved after the sample data was adjusted for extreme value data dealing, but not necessarily improve the stable of cluster.
2, The Logit model is better than MDA model in two kinds of database.
3, Different credit scoring model and data dealing will influence the results of cluster. The better the ability of credit scoring model, the larger the difference between clusters in probability of default.
4, After all of our study and test, we find the Logit model, which was adjusted after extreme value data dealing have the best ability to score and cluster.

第一章：序論...............................................................................................................1
第一節：研究背景與動機...........................................................................................1
第二節：研究目的.......................................................................................................3
第三節：研究流程.......................................................................................................4
第二章：文獻探討.......................................................................................................6
第一節：違約資料設定與極端值處理.......................................................................6
第二節：模型變數之使用及可能之問題...................................................................9
第三節：過去信用風險之研究方法...........................................................................10
第四節：信用評等介紹與集群分析...........................................................................12
第五節：信用評等研究...............................................................................................13
第三章：研究方法.......................................................................................................16
第一節：多元區別分析 (MULTIPLE DISCRIMINANT ANALYSIS，MDA).............16
第二節：LOGIT模型....................................................................................................21
第三節：集群分析介紹(CLUSTER ANALYSIS).........................................................24
第四節：檢定方法介紹...............................................................................................29
第四章：實証分析.......................................................................................................38
第一節：研究資料分析...............................................................................................38
第二節：評分模型分析...............................................................................................42
第三節：集群分析.......................................................................................................46
第四節：矩陣整合分析...............................................................................................50
第五章：結論與建議...................................................................................................52
第一節：結論...............................................................................................................52
第二節：研究貢獻.......................................................................................................54
第三節：研究限制.......................................................................................................55
第四節：未來研究方向建議.......................................................................................56
參考文獻.......................................................................................................................57
中文部份.......................................................................................................................57
英文部份.......................................................................................................................59
附錄A：特性根平均指標的運算概念.........................................................................62

表 目 錄
表3-1：類常態轉換方式..............................................................................................19
表4-1：公司違約情況與比例......................................................................................39
表4-2：財務比率變數資料表......................................................................................40
表4-3：各模型經逐步過程所挑選出來的變數..........................................................43
表4-4：各評分模型的K–S與ROC指標......................................................................44
表4-5：各模型評等結果的違約機率分佈..................................................................48
表4-6：各模型之特性根平均指標(Msvd)...................................................................50
附錄表1：原始資料各變數之敘述統計.....................................................................64
附錄表2：百分比調整資料各變數之敘述統計.........................................................66
附錄表3：VIF檢定共線性變數刪除表.......................................................................68
附錄表4：各評分模型分堆結果.................................................................................69
附錄表5：各評分模型之等級轉置矩陣.....................................................................70

圖 目 錄
圖1-1 研究流程圖...........................................................................................................5
圖3-1 百分比調整後的資料分佈情況...........................................................................30
圖4-1 集群分析概念圖...................................................................................................47

一、中文部份
1.王懷德(2003)，KMV模型於國內未上市、未上櫃之公開發行公司之研究，碩士論文，東吳大學會計學系。
2.邱友信(2004)，年度財務預測季分配之研究，碩士論文，朝陽科技大學會計系。
3.杜國靜(2003)，我國政府支出與經濟成長關係之研究，碩士論文，朝陽科技大學財務金融系。
4.阮正治，江景清(2004)，「台灣企業信用評分模型建置與驗證」，財團法人金融聯合徵信中心，金融風險管理季刊，民93，6月號。
5.林素菁(2004)，上市公司退出率與存活期間之計量模型上市公司退出率與存活期間之計量模型–以中國和台灣下市公司為實證，碩士論文，中原大學企業管理研究所。
6.金慧貞(2002)，多變量EWMA財務危機預警模式之應用，碩士論文，朝陽科技大學財務金融系。
7.孫銘誼，王思芳(2004)，「信用評等模型驗證之初探–相關方法與文獻回顧」財團法人金融聯合徵信中心，金融風險管理季刊，民93，第一卷，第一期，pp.111-125。
8.康贊清(2003)，銀行放款評估之知識擷取:類神經網路之應用，碩士論文，中正大學資訊管理學系。
9.施佳華(2001)，產險業信用評等模式之研究-美國產險公司之實證分析，碩士論文，政治大學風險與管理學系。
10.郭淑雲(2001)，消費者特性與網際網路購物意願關係之研究–以生鮮食品為例，碩士論文，國立中興大學行銷學系。
11.陳順宇(2004)，多變量分析，三版。台北：華泰出版。
12.黃燦盛(2001)，產品配合使用介質的可靠度性能數據蒐集規劃與分析之研究，碩士論文，國立高雄第一科技大學機械與自動化工程所。
13.劉志寬(2003)，財務比率分析於金融機構授信決策之研究-個案公司為例，碩士論文，銘傳大學管理學院高階經理碩士學程。
14.鄭采芳(2004)，模糊集群法在IC設計業生產外包之研究，碩士論文，中華大學經營管理研究所。
15.鄭孟育(2002)，台灣農作物颱風損失模式之研究－以水稻為例，碩士論文，國立高雄第一科技大學風險管理與保險系。
16.盧陽正、陳達新、郭哲男、駱茂榮(2001)，「新一代信用風險模型的介紹與應用：CreditPortfolioView 和 CreditRisk+」，台灣期貨市場，第2期，第3卷，3-18頁。
17.顏月珠(1986)，實用無母數統計方法：企管、醫療、環境及社會科學研究適用，台北市：陳昭明出版。

二、英文部份
1.Altman E.I. and H.A. Rijken, (2004),“How rating agencies achieve rating stability,”Journal of Banking & Finance 28, pp.2679-2714
2.Ariyawardana A. and W.C. Bailey, (2003),“Investigation of Strategic Group Formation using Cluster Analysis,”Sri Lankan Journal of Applied Statistics - Volume 4.
3.Barbro Back, Teija Laitinen, Kaisa Sere, and Michiel van Wezel. (1996),“Choosing bankruptcy predictors using discriminant analysis, Logit analysis, and genetic algorithms,”Technical Report TUCS-TR-40, Turku Centre for Computer Science, Finland, September 16.
4.Begley, J., Ming, J., and S. Watts, (1997),“Bankruptcy Classification Errors in the 1980s: An Empirical Analysis of Altman's and Ohlson's Models,”Review of Accounting Studies, March, Vol 1, No 4, pp.267-284.
5.Chava Sudheer, and Robert A. Jarrow, (2004),“Bankruptcy prediction with industry effects,”Johnson Graduate School of Management Working Paper, Cornell University.
6.Coenders, G. and M. Saez, (2000),“Collinearity, heteroscedasticity and outlier diagnostics in regression. do they always offer what they claim?,”New approaches in applied statistics, Metodološki Zvezki, 16, Ljubljana: FDV, pp.79-94.
7.Edward I. Altman, (1968),“Financial Ratio Discriminant Analysis and the Prediction of Corporate Bankruptcy,”Journal of Finance, Vol.23, No.4, pp589-609.
8.Elizabeth Mays, (2001), Handbook of Credit Scoring, New York:AMACOM
9.Evelyn Hayden (2003), “Are Credit Scoring Models Sensitive With Respect to Default Definitions? Evidence from the Austrian Market”, Department of Business Administration Working Paper, University of Vienna.
10.Fox J. and G. Monette, (1992),“Generalized collinearity diagnostics,”Journal of the American Statistical Association 87, pp.176-183.
11.Girish P. and David W. Stewart, (1983),“Cluster analysis in marketing research: Review and Suggestions for application, ”Journal of Marketing Research, Vol. 20 No. 2, pp. 134-148.
12.Gilbert Strang, (1988), Linear Algebra and its Applications, 3rd Ed., Saunders HBJ.
13.Hendrickx J. and B. Pelzer, (2004),“Collinearity involving ordered and unordered categorical variables,”Paper presented at the RC33 conference in Amsterdam, August.
14.Hillegeist S., Keating E., Cram D., and K. Lundstedt, (2004),“Assessing the Probability of Bankruptcy,”Review of Accounting Studies, vol. 9, No. 1 (March 2004), pp. 5-34.
15.Honghu Liu and Tongtong Wu, (2003),“Estimating the Area under a Receiver Operating Characteristic Curve For Repeated Measures Design,”Journal of Statistical Software, 2003 - Volume: 8 - Issue: 12.
16.Huei-Ming Chai (2003)at School of Physical Therapy, National Taiwan University, Taipei.：http://www.pt.ntu.edu.tw/hmchai/SAS03/SASproc/SASnormal.htm.
17.Jafry, Y. and T. Schuermann, (2003a),“Measurement and Estimation of Credit Migration Matrices,”Wharton Financial Institutions Working Paper #03-08.
18.Jafry, Y. and T. Schuermann, (2003b),“Metrics for Comparing Credit Migration Matrices,”Wharton Financial Institutions Working Paper #03-09.
19.Jafry, Y. and T. Schuermann, (2004),“Measurement, Estimation and Comparison of Credit Migration Matrices,”Til Schuermann of the Federal Reserve Bank of New York, March 5.
20.James A. Ohlson, (1980),“Financial Ratios and the Probabilistic Prediction of Bankruptcy,” Journal of Accounting Research, Vol.18, No.1, pp109-131.
21.Ketchen, D. J. JR. and C. L. Shook, (1996),“The application of cluster analysis in strategic management research: an analysis and critique,”Strategic Management Journal,17, pp.441-458.
22.Lando, David, and Torben M. Skødeberg (2002),“Analyzing Rating Transitions and Rating Drift with Continuous Observations,”Journal of Banking and Finance, Vol. 26,No. 2-3, pp. 423-444.
23.Loretta J. Mester, (1997),“What is the Point of Credit Scoring?,”Federal Reserve Bank of Philadelphia Business Review, pp.3-16.
24.Malhotra, Davinder K. and Malhotra, Rashmi, (2003),“Evaluating consumer loans using neural networks,”The International Journal of Management Science, 31, pp.83-96.
25.Mona L. Toms, Mark A. Cummings-Hill, David G. Curry and Scott M. Cone, (2001), “Using Cluster Analysis for Deriving Menu Structures for Automotive Mobile Multimedia Applications,”SAE Technical Papers, Document Number: 2001-01-0359.
26.Tyler Shumway, (2001),“Forecasting Bankruptcy more Accurately: A Simple Hazard Model,” Journal of Business, Vol. 74, pp.101-124.
27.Stepanova M. and L. C. Thomas, (2002),“Survival analysis methods for personal loan data,”Operations Research, 50(2), pp.277–289.