臺灣博碩士論文加值系統

摘要
金融機構考量承做房貸業務倚賴於借款人未來是否選擇還款，一旦貸出者確定提供貸款後，借款人將面對正常還款或異常還款之不同情況，而異常還款尚可分為逾期、違約或提前清償等方案。過去探討異常還款之因素多集中於個人資料及總體環境指標，藉由二類方案、多類方案或資料模擬等估計型態，期望反映借款人各種選擇之特性，相較於真實借款人多層級離散選擇行為的相關研究，則付之闕如。本文主要探討借款人因個人社會經濟條件差異，及貸款利息與貸款利息對個人所得比等在不同方案之共生變數，評估選擇最終方案的影響。本文利用實際核准之房屋貸款案件，先採用離散選擇模型中條件羅吉特模型與多項羅吉特模型來進行估計，並分別運用豪斯曼檢定偵測兩模型之方案間是否具獨立無相關性(IIA)，然而兩模型皆未能通過檢定，因此本文嘗試運用巢式羅吉特模型並以充分訊息最大概似法(FIML)進行估計，分析履約選擇及還款選擇對借款人行為之關係。結果發現借款人性別、座落地區、職稱、抵押品類型、貸款金額、貸款成數、貸款利息及現職年資對於履約選擇及還款選擇分別有重要的影響。最後，放寬IIA假設並投入服從不同連續分配之隨機參數，誤差項仍然維持分配具獨立且一致性(IID)，建構出混合羅吉特模型，實證結果發現貸款利息對個人所得比之隨機參數，可顯著解釋離散選擇模型之異質性，並有助於提高模型之配適度。

ABSTRACT
The financial institutions consider transacting business of mortgage loans, which depends on whether the borrowers repay loans in the further. If one lender decides to offer the loans, consequently, it has to deal with different abnormal repayment in the future. And abnormal repayment could be attributed to varied projects, including past-due, delinquent or prepayment. In the past, the literatures discussing on abnormal repayment almost focus on personal data and macroeconomics by various estimated pattern,
namely binary projects, multiple projects or data simulation, which expect to demonstrate varied choices
of borrowers simultaneously. Comparing with the hierarchical choosing behavior of actual borrowers, it
seems too hard to find out related researches. The purpose of this paper is applying the individual difference of social economics background, loan interest expenditure and loan interest expenditure to personal income ratio assessment for varied projects to estimate the impacts on final choices of repayment projects. In this paper, we apply the discrete choice model to estimate the actual cases of housing loans. Specifically, both the conditional logit model and the multinomial logit model are estimated initially and the Hausman test is used to detect the existence of independence from irrelative alternatives (IIA) in different projects, but the IIA hypothesis could not hold exactly. This paper is an attempt to analyze the
causality between performance choice, repayment choices and borrower behaviors applying a nested logit model and full information maximum likelihood (FIML) method. The result demonstrates gender, location, position, type of collateral, amount of loan, loan to value ratio, loan interest and year of occupation play important roles on both performance and repayment choice. The feature of hierarchical choosing behavior can be exhibited precisely by the application of a nested logit model. Finally, we build the mixed logit model by relaxing the hypothesis of IIA and fitting various continuous distributions of
random parameters, in addition, the error terms are still independent and identically distributed(IID). The empirical results show that the heteroscedasticity of discrete choice model could be explained significantly by the random parameter defined as loan interest expenditure to personal income ratio, and which improve the goodness of fit.

目錄
中文摘要…………………………………………………………………ⅰ
英文摘要…………………………………………………………………ⅱ
誌謝………………………………………………………………………ⅲ
目錄………………………………………………………………………iv
表目錄……………………………………………………………………ⅴ
圖目錄……………………………………………………………………ⅵ
壹、緒論…………………………………………………………………1
一、研究背景與動機……………………………………………………1
二、研究目的……………………………………………………………7
三、研究方法與步驟……………………………………………………7
四、研究對象與資料來源………………………………………………10
五、本文架構……………………………………………………………10
貳、理論基礎與相關文獻………………………………………………12
一、房屋抵押貸款定義與風險預警沿革………………………………12
二、離散選擇模型理論(Discrete Choice Model)………………….14
參、研究設計與實證模型………………………………………………18
一、變數敘述性統計分析………………………………………………18
二、計量實證模型建構…………………………………………………23
(一)、離散選擇模型之基本假設與效用函數組成……………………23
(二)、多項式羅吉特模型及條件式羅吉特模型………………………25
(三)、解決方案間存有相似性模型……………………………………30
(四)、解決方案間存有相似性及異質性模型…………………………34
(五)、模型檢定統計量…………………………………………………42
肆、實證結果……………………………………………………………45
一、條件式羅吉特模型估計結果………………………………………45
二、多項式羅吉特模型估計結果………………………………………47
三、巢式羅吉特模型估計結果…………………………………………50
四、隨機參數羅吉特模型估計結果……........................54
伍、結論與建議…………………………………………………………58
一、結論…………………………………………………………………58
二、建議與未來研究方向………………………………………………59
參考文獻…………………………………………………………………61
附錄一：變數占方案百分比表、變數相關矩陣表……………………68

一、中文部分
1. 李桐豪與呂美慧， 2000， "金融機構房貸客戶授信評量模式分析－Logistic 迴歸之應用"，台灣金融財務季刊，第1 卷，第1 期，頁1-20。
2. 李沃牆與黃程偉，2006，"房屋抵押貸款授信之風險評估"，台灣經濟金融月刊，第42 卷，頁15-33。
3. 吳至中，2005，檢視住宅選擇行為中的異質性與相似性─以台灣地區都市層級選擇為例，國立成功大學，碩士論文。
4. 林左裕與劉長寬，2003， "應用Logit 模型於銀行授信違約行為之研究"，中華民國住宅學會第十二屆學術論文研討會，中華民國住宅學會與台北大學，頁92-119，台北。
5. 林左裕，2004，"A Study on the Termination Behavior of Residential Mortgages in Taiwan"，Journal of Agricultural Economics，第76 卷，頁209-235。
6. 林祖嘉與陳建良，2005，"租買選擇、貸款選擇、與世代組成：巢式logit 模型之應用"，住宅學報，第14 卷，第1 期，頁1-20。
7. 周建新、于鴻福與陳進財，2004， "銀行業房貸授信風險評估因素之選擇"，中華管理評論，第7 卷，第2 期，頁77-103。
8. 周百隆、姚振華與林文琴，2007， "以樣本配對觀點探討國內壽險業抵押貸款違約風險之實證分析"，保險專刊，第23 卷，第2期，頁115-128。
9. 周榮昌、劉祐興與王唯全，2007， "國際航線低價航空公司及般航空公司選擇行為之研究─以臺北─新加坡航線為例"，運輸計劃季刊，第36 卷，第3 期，頁307-332。
10. 邱靜淑，2004，都市通勤者運具選擇行為之研究，國立暨南國際大學，碩士論文。
11. 范哲銘、林英星，2009，"銀行體系與行銷體系信用貸款授信模式的研究"，商學學報，第17 期，頁161-188。
12. 徐明洸，1994， "銀行經營風險分析－以授信風險為例",台灣土地銀行研究報告，台北。
13. 袁淑湄，2003，應用混合 Logit 模型探討台灣家戶住宅選擇之研究，國立成功大學，碩士論文。
14. 高博祥，2008，我國銀行業房屋貸款違約風險潛在因子之研究─以S 銀行為例，國立高雄第一科技大學，碩士論文。
15. 莊瑞珠與陳穆貞，2006，"金融機構住宅房屋貸款信用評分系統之建構研究"，住宅學報，第 15 卷，第 2 期，頁65-90。
16. 陳彥仲與吳京玲，1998，"家戶住宅區位選擇與地方化財政理論之實證研究"，都市與計畫，第25 卷，第2 期，頁223-238。
17. 陳彥仲，1997，"住宅選擇之程序性決策模式"，住宅學報，第5 卷，頁37-49。
18. 陳彥仲，1998，"對多項Logit 模型參數指定方式之比較分析"，交大管理學報，第18 卷，第2 期，頁171-185。
19. 陳綿村、許通安與林蔓蓁，1996，"銀行授信客戶違約風險之預測"，管理科學學報，第13 卷，頁173-195。
20. 張瑞元與林金賢，2005，"建構銀行危機預警模型─訊號法與Panel Logit 之結合"，會計與公司治理，第1 卷，第2 期，頁9-32。
21. 黃嘉興、謝永明與劉宗哲，2005，"房屋抵押貸款客戶違約預測模式之比較研究"，東吳經濟商學學報，第48 期，頁103-126。
22. 黃文啟，2002，以LOGIT 模型研究借款人特性與不動產抵押貸款提前償還之關係，政治大學，碩士論文。
23. 曾勝雄、曾國雄與張德儀，1997，"旅行業組織購買選擇行為之研究—羅吉特模式之應用"，管理與系統，第4 卷，第2 期，頁127-146。
24. 曾偉君與黃俊燁，2006，"選項集合在隨機效用模型應用之關鍵性—以沿海溼地遊憩價值之評估為例"，經濟論文叢刊，第34 卷，第2 期，頁209-243。
25. 楊顯爵、林左裕與陳宗豪，2008，"住宅抵押貸款違約之研究—影響因素之顯著性分析"，台灣土地研究，第 11 卷，第 2 期，頁1-36。
26. 溫傑華、葉文雅、賴珊靖與蕭秀姮，2009， "國際線航空公司品牌定位之研究－以臺北東京航線為例"，運輸學刊，第 21 卷，第 3 期，頁251- 278。
27. 劉展宏與張金鶚，2001，"購屋貸款提前清償行為之研究"，住宅學報，第10卷，第1 期，頁29-49。
28. 蔡碩倉，2000，"運用類神經網路建構台灣地區農會信用部金融預警系統"，農業經濟半年刊，第68 卷，頁117-156。
29. 賴文泰與呂錦隆，2008，"應用涉入理論於運具選擇行為之研究"，運輸計劃季刊，第37 卷，第2 期，頁237-262。
30. 儲蓉，2004，金融資產證券化理論與案例分析，臺灣金融研訓院，台北。
二、英文部分
1. Albaladejo-Pina, I. P. and M. T. Dı’az-Delfa, 2009, "Tourist preferences for rural house stays: Evidence from discrete choice modelling in Spain," Tourism management, Vol. 30, No. 6, pp.805-811.
2. An, X., J. C. Clapp and Y. Deng, 2008, "Omitted Mobility Characteristics and Property Market Dynamics: Application to Mortgage termination," Journal of Real Estate Finance and Economics, Vol. 7, pp.1-27.
3. Anas, A. and C. Chu, 1984, "Discrete Choice Models and the Housing Price and Travel to work Elasticities of Location Demand," Journal of Urban Economics, Vol. 15, No. 1, pp.107-123.
4. Anderson, D. R. and M. Weinrobe, 1986, "Mortgage Default Risks and the 1971 San Fernando Earthquake," AREUEA Journal, Vol. 14, No. 1, pp.100-135.
5. Archer, W., D. Ling and G. McGill, 1996, "The Effect of Income and Collateral Constraints on Residential Mortgage Terminations," Regional Science and Urban Economic, Vol. 26, No. 3-4, pp.235-261.
6. Ben-Akiva, M. E. and S. Lerman, 1985, Discrete Choice Analysis: Theory and Application to Travel Demand, MIT Press, Cambridge, Massachusetts.
7. Berkson, J., 1944, "Application of the Logistic Function to Bio-assay," Journal of American Statistical Association, Vol.39, pp.357-365.
8. Bhat, C., 1995, "A Heteroscedastic Extreme Value Model of Intercity Mode Choice," Transportation Research B, Vol. 29, No. 6, pp.471-483.
9. Bhat, C. R., 1998, "Accommodating Flexible Substitution Patterns in Multi-dimensional Choice Modeling: Formulation and Application to Travel Mode and Departure Time Choice," Transportation Research B, Vol. 32, No. 7, pp.455-466.
10. Bhat, C. R., 2001, "Quasi-Random Maximum Simulated Likelihood Estimation of the Mixed Multinomial Logit Model," Transportation Research Part B, Vol. 35, No. 7, pp.677-693.
11. Bhat, C. R., 2003, "Simulation Estimation of Mixed Discrete Choice Models Using Randomized and Scrambled Halton Sequences," Transportation Research Part B:
Methodological, Vol. 37, No. 9, pp.837–855.
12. Bhat, C. R. and J. Guo, 2004, "A Mixed Spatially Correlated Logit Model: Formulation and Application to Residential Choice Modeling," Transportation Research Part B, Vol. 38, No. 2, pp.147-168.
13. Boyd, J. and J. Mellman, 1980, "The Effect of Fuel Economy Standards on the U.S. Automotive Market: A Hedonic Demand Analysis," Transportation Research, Vol. 14A, No. 5-6, pp.367-378.
14. Campbell, T. S. and D. J. Kimball, 1983, "The Determinants of Default on Insured Conventional Residential Mortgage Loans," Journal of Finance, Vol. 38, No. 5,
pp.1569-1581.
15. Cardell, N. and F. Dunbar, 1980, "Measuring the Societal Impacts of Automobile Downsizing," Transportation Research, Vol. 14A, No. 5-6, pp.423-434.
16. Caselli, S., S. Gatti and F. Querci, 2008, "The Sensitivity of the Loss Given Default Rate to Systematic Risk: New Empirical Evidence on Bank Loans," Journal of
Financial Services Research, Vol. 34, No. 1, pp.1–34.
17. Clapp, J. M., Y. Deng and X. An, 2006, "Unobserved Heterogeneity in Models of Competing Mortgage Termination Risks," Real Estate Economics, Vol. 34, No. 2, pp.243-273.
18. Currim, I., 1982, "Predictive Testing of Consumer Choice Models Not Subject to Independence of Irrelevant Alternatives," Journal of Marketing Research, Vol. 19,
pp.208-222.
19. Deng, Y. H., J. M. Quigley and R. V. Order, 1996, "Mortgage Default and Low Down payment Loans: The Costs of Public Subsidy," Regional Science and Urban Economics, Vol. 26, No. 3-4, pp.263-285.
20. Deng, Y. H., J. M. Quigley and R. V. Order, 2000, "Mortgage Terminations, Heterogeneity and the Exercise of Mortgage Options," Econometrica, Vol. 68, No. 2, pp.275-307.
21. Denicolo, V., 2000, "Independence of Irrelevant Alternatives and Consistency of Choice," Economic Theory, Vol. 15, pp.221-226.
22. Episcopos, A., Pericli, A. and Hu, J., 1998 "Commercial Mortgage Default: A Comparison of Logit with Radial Basis Function Networks," Journal of Real Estate Finance and Economics, Vol. 17, No. 2, pp.163-178.
23. Epley, D. R., K. Liano and R. Haney, 1996, "Borrower Risk Signaling Using Loan-to-Value Ratios," Journal of Real Estate Research, Vol. 11, No. 1, pp.71-86.
24. Greene, W., 1997, Econometric Analysis, 3rd ed, Prentice-Hall, NJ.
25. Greene, W. H. and D. A. Hensher, 2003, "A Latent Class Model for Discrete Choice Analysis: Contrasts with Mixed Logit," Transportation Research Part B, Vol. 37, No. 8, pp.681–698.
26. Greene, W. H. and D. A. Hensher, 2004, NLOGIT 4: User’s Guide.
27. Greene, W. H., D. A. Hensher and J. Rose, 2006, "Accounting for Heterogeneity in the Variance of Unobserved Effects in Mixed Logit Models," Transportation Research Part B, Vol. 40, No. 1, pp.75–92.
28. Greene, W. H. and D. A. Hensher, 2007, "Heteroscedastic Control for Random Coefficients and Error Components in Mixed Logit," Transportation Research Part E, Vol. 43, No. 5, pp.610–623.
29. Hausman, J. and D. McFadden, 1984, "Specification Tests for the Multinomial Logit Model," Econometrica, Vol. 52, No. 5, pp.1219-1240.
30. Hensher, D. A. and W. H. Greene, 2002, "Specification and Estimation of The Nested Logit Model: Alternative Normalizations," Transportation Research Part B:
Methodological, Vol. 36, No. 1, pp.1-17.
31. Hensher, D. A. and W. H. Greene, 2004, "The Mixed Logit model: The State of Practice," Transportation, Vol. 30, No. 2, pp.133-176.
32. Hensher, D. A. and S. A. Jones, 2007, "Forecasting Corporate Bankruptcy: Optimizing the Performance of the Mixed Logit Model," Abacus, Vol. 43, No. 3, pp.241-264.
33. Johnson, N. and S. Kotz, 1970, Distributions in Statistics: Continuous Univariate Distributions, Wiley Press, New York.
34. Jones, S. and D. A. Hensher, 2004, "Predicting Firm Financial Distress: A Mixed Logit Model," Accounting Review, Vol. 79, No. 4, pp.1011-1038.
35. Jung, A. F., 1962, "Terms of Conventional Mortgage Loans on Existing Houses," Journal of Finance, Vol. 17, pp.432-443.
36. Kau, J. B. and D. C. Keenan, 1999, "Patterns of Rational Default," Regional Science and Urban Economics, Vol. 29, No. 6, pp.65-85.
37. Koppelman, F. S. and C. H. Wen, 2000, "The paired combinatorial logit model: properties, estimation and application," Transportation Research B, Vol. 34, pp.75-89.
38. Koppelman, F. S. and C. H. Wen, 2001, "The Generalized Nested Logit Model," Transportation Research Part B, Vol. 35, No. 7, pp.627-641.
39. LaCour-Little, M., 1999, "Another Look at the Role of Borrower Characteristics in Predicting Mortgage Prepayments," Journal of Housing Research, Vol. 10, No. 1,
pp.45-60.
40. Lawrence, E. C., L. D. Smith and R. Rhoades, 1992, "An Analysis of Default Risk in Mobile Home Credit," Journal of Banking and Finance, Vol. 16, No. 2, pp.299-312.
41. Lawrence, E. C., L. D. Smith and R. Rhoades, 1995, "Credit and Banking: A Multinomial Logit Analysis of Problem Loan Resolution Choices in Banking," Journal of Money, Credit & Banking, Vol. 27, pp.202-216.
42. Louviere, J., D. A. Hensher and J. Swait, 2000, Stated Choice Methods: Analysis and Application, Cambridge University Press, Cambridge.
43. Luce, R. D. and P. Suppes, 1965, Preference utility and subjective probability, In Luce, R. D., Bush, R. R. and Galanter, E. (editors) Handbook of Mathematical
Psychology, Vol. III, Wiley Press, New York.
44. Maddala, G. S., 1983, Limited-dependent and qualitative variables, in Frontier in Econometrics, Cambridge University Press, New York.
45. Manski, C. F., 1973, The Analysis of Qualitative Choice, Ph.D. Dissertation, Department of Economics, Massachusetts Institute of Technology, MA.
46. McFadden, D., 1973, Conditional Logit analysis of qualitative choice behavior, in Zarembka, P. (ed.), Frontiers in Econometrics, Academic Press, New York.
47. McFadden, D., 1974, "The Measurement of Urban Travel Demand," Journal of Public Economics, Vol. 3, No. 4, pp.303-328.
48. McFadden, D. and F. Reid, 1975, "Aggregate Travel Demand Forecasting from Disaggregated Behavioral Models," Transportation Research Record: Travel Behavior and Values, 534, pp. 24-37.
49. McFadden, D. and K. Train, 1977, "An Application of Diagnostic Test for the Independence from Irrelevant Alternatives Property of the Multinomial Logit Model," Transportation Research Record, 637, pp.39-46.
50. McFadden, D., 1978, "Modelling the Choice of Residential Location," in Spatial Interaction Theory and Residential Location.ed. A. Karlquist et al. Institute of
Transportation Studies, University of California, 477, pp.75-96.
51. McFadden, D. and C. Manski, 1981, Structural Analysis of Discrete Choice with Econometric Applications, MIT Press, Cambridge, Massachusetts.
52. McFadden, D. and K. Train, 2000, "Mixed MNL Models for Discrete Response," Journal of Applied Econometrics, Vol. 15, No. 5, pp.447-470.
53. McKinley, B. and T. Vermilyea, 2007, "The Role of Information Externalities and Scale Economies in Home Mortgage Lending Decisions," Journal of Urban Economics, Vol. 61, No. 1, pp.71–85.
54. Page, A. N., 1964, "The Variation of Mortgage Interest Rates," Journal of Business, Vol. 37, pp.280-294.
55. Pinder, J., 1996, "Decision Analysis Using Multinomial Logit Models: Mortgage Portfolio Valuation," Vol. 48, pp.67-77.
56. Revelt, D. and K. Train, 1998, "Mixed Logit with Repeated Choices: Households Choices of Appliance Efficiency Level," Review of Economics and Statistics, Vol.
80, No. 4, pp.647-657.
57. Rose, M. J., 2008, "Predatory lending practices and subprime foreclosures: Distinguishing impacts by loan category," Journal of Economics and Business, Vol. 60, No.1-2, pp.13-32.
58. Shin, S., 2008, "An Empirical Study on the Choice of Residential Mortgage Lender by Korean Household," 3rd International Conference on Asia-Pacific Financial
Markets, Konkuk University, Seoul, Korea.
59. Srinivasan, K. K. and H. S. Mahmassani, 2003, "Analyzing Heterogeneity and Unobserved Structural Effects in Route-Switching Behavior under ATIS: A Dynamic Kernel Logit Formulation," Transportation Research B, Vol. 37,
pp.793-814.
60. Talvitie, A., 1972, "Comparison of Probabilistic Modal-Choice Models," Highway Research Board Record, 392, pp.111-120.
61. Tiwari, P., 2000, "Housing Demand in Tokyo," International Real Estate Review, Vol. 3, No. 1, pp.65–92.
62. Train, K. E., 1998, "Recreation Demand Models with Taste Differences Over People," Land Economics, Vol.74, No.2, pp.230-239.
63. Train, K., 2003, Mixed Logit and Bayesian Procedures, in Discrete Choice Methods with Simulation, Cambridge University Press.
64. Von Furstenberg, G. M., 1969, "Default Risk on FHA-Insured Home Mortgages as a Function of the Terms of Financing: A Quantitative Analysis," Journal of Finance,
Vol. 24, No. 3, pp.459-477.
65. Vovsha, P., 1997, "Application of a Cross-Nested Logit Model to Mode Choice in Tel Aviv, Israel, Metropolitan Area," Transportation Research Record, 1607, pp. 6-15.
66. Westin, R., 1974, "Predictions from Binary Choice Models," Journal of Econometrics, Vol. 2, No. 1, pp.1-16.
67. Westin, R. and D. Gillen, 1978, "Parking Location and Transit Demand: A Case Study of Endogenous Attributes in Disaggregate Mode Choice Models," Journal of Econometrics, Vol. 8, No. 1, pp.75-101.
68. Yang, Z., M. Platt and H. Platt, 1999, "Probabilistic Neural Network in Bankruptcy Prediction," Journal of business Research, Vol. 44, pp.67-74.
69. Zhang, G., M. Hu, B. Patuwo and D. Indro, 1999, "Artificial Neural Networks in Bankruptcy Prediction: General Framework and Cross-Validation Analysis,"
European Journal of Operational Research, 116, pp.16-32.