logistic logistic Merton Black - Scholes Black&Cox Merton Longstaff&Schwarlz Jarrow&Turnbull

Transcription

1 29 6 Vol. 29 No Research of Finance and Education Nov logistic logistic A 21 logistic F A Merton Black - Scholes Black&Cox Merton Longstaff&Schwarlz Jarrow&Turnbull Ⅲ III

2 Madan&Unal zhou KMV Bayes Logitistic Logitistic Logistic Logistic 0-1 Logistic Logistic Logistic 1. A 1 A ST 2. ST * ST % ST 40 ST 40 ST ST ST 1 A B H A

3 6 logistic 29 ST ST logistic ST 1 ST Logistic Logistic ε i ε i ε i = α + m β k x ki k = 1 1 P y i = 1 x i = 1 + exp [ - α + m β k x ki ] Logit ln p [ i ] 1 - pi = α + m k = 1 β k k = 1 2 n k β k k β k k α 1 x k β k x ki k = 1 Logistic Logistic ZCFZL LDZCBL GDZCBL QYDFZBL LXBZBS LDFZBL LDBL SDBL YYZJBL YYZJDJZCBL MGSY MGJZC XJLLBL YYSRXJBL YYMLL YYJLL ZCBCL ZZCJLL JZCSYL ZBJLL ZZCZZL

4 SPSS Logistic forward stepwise. Cox & Snell R Square Nagelkerke R Square likelihood Ratio Test Wald 1. 2 Unweighted Cases a N Percent Selected Cases Included in Analysis Missing Cases Total Unselected Cases 0 0 Total a. If weight is in effect see classification table for the total number of cases ST * ST Chi - square df Sig. Step Block Model P Excel CHIINV P Log likelihood Cox & Snell R Square Nagelkerke R Square a a. Estimation terminated at iteration number 6 because parameter estimates changed by less than Log likelihood = Cox & Snell R Square Nagelkerke R Square χ % Cox & Snell R Square Nagelkerke R Square 64. 2% Logistic Cox & Snell R Square Nagelkerke R Square Logistic 2. Classification Table Logistic

5 6 logistic 31 5 Logistic SFWY Observed SFWY Predicted Percentage Correct Overall Percentage Logistic % % % 3. Logistic Wald Wald Sig Wald Sig Wald Wald = b 2 var b Logistic Variables in the Equation B S. E. Wald df Sig. Exp B GDZCBL LDFZBL MGSY ZBJLL Constant Logistic Variables not in the Equation a Score df Sig. LDBL SDBL YYZJBL YYZJDJZCBL ZCFZL LDZCBL QYDFZBL LXBZBS MGJZC XJLLBL YYSRXJBL YYMLL YYJLL ZCBCL ZZCJLL JZCSYL ZZCZZL a. Residual Chi - Squares are not computed because of redundancies. 6-1 GDZCBL LDFZBL MGSY ZBJLL

6 GDZCBL MGSY Sig MGSY Wald GDZCBL Wald ZBJLL Wald LDFZBL Wald MGSY GDZCBL LDFZBL ZBJLL 6-2 5% GDZCBL LDFZBL MGSY ZBJLL 95% ln p ( 1 - p ) = GDZCBL LDFZBL MGSY ZBJLL GDZCBL LDFZBL MGSY ZBJLL GDZCBL GDZCBL LDFZBL MGSY EPS 1 Observed Groups and Predicted Probabilities

7 6 logistic 33 ZBJLL Merton Robert C. On the Pricing of Corporate Debt The Risk Structure of Interest Rates J. Journal of Finance American Finance Association Black F Cox J. C. Valuing corporate securities some effects of bond indenture provision J. Journal of Finance Longstaff F. Schwartz E. A Simple Approach to Valuing Risky Fixed and Floating Rate Debt J. Journal of Finance Jarrow Robert A. and Stuart M. Turnbull. Pricing Derivatives on Financial Securities Subject to Credit Risk J. Journal of Finance Madan D Haluk U. A. Factor Hazard Rate Model for Pricing Risky Debt and the Term Structure of Credit Spreads J. The Journal of Financial and Quantitative Analysis

8 J J Bayes J Logistic Bayes J Logistic J J J The Measurement of the Probability of Default of the Borrowing Enterprises in Commercial Bank based on Logistic Model Take Manufacturing Listed Companies for Example FENG Lei DONG Jigang School of Economics and Management Shandong Agricultural University Tai an Shandong China Abstract With the requirements of the Basel Ⅲ and the gradual completion of the interest rate market the venture management of commercial banks becomes a top priority its main content is to measure the probability of default of the borrower. The thesis used the logistic regression model to compare and analyze the 21 indicators of 80 A - share listed companies in manufacturing industry in China from 2011 to 2014 get the default probability prediction model which had significant impact on variables such as fixed assets ratio current liabilities ratio earnings per share and the capital accumulation rate. This paper is aim to help commercial banks establish a quantitative test and evaluation system for the loan default risk and improve the loan pricing mechanism then put forward the corresponding countermeasures and suggestions. Key words commercial banks probability of default logistic model manufacturing enterprise