CERTIFICATION
NGUYEN VIET DUC
ACKNOWLEDGEMENT
TABLES AND FIGURES
CHAPTER 1 - INTRODUCTION
1.1. Problem statement
1.2. Research objectives and research questions
1.3. Scope of the study
1.4. Contributions and Implications
Figure 2 - Credit risk management techniques in banking management
1.5. Organization of the thesis
CHAPTER 2 – LITTERATURE REVIEW
2.1. Concepts of credit rating
Figure 3- sample of a loan’s life
2.2. Worldwide approaches for credit rating
Table 1-Sample of credit risk assessment ranking by Moody in US 2015
2.3. Empirical studies on credit rating
CHAPTER 3 – RESEARCH METHODOLOGY
3.1. Analytical framework and hypotheses
Figure 4 – Conceptual Framework
Table 2 – Variables
3.2. Estimation methods
3.2.1. Binominal logistic regression
3.2.2. Multinomial logistic regressions
3.2.3. Linear regression quick reviews
3.3. Model specification
3.4. Data sources and data treatment
3.4.1. The Data Set
3.4.2. Data treatments
3.4.3. Variable Selection
Figure 5: Dependent variables distribution
Table 3 – A Sample of variable selection by Altman
Table 4-Variables used by Altman2
Table 5- Variables used by Moody
3.4.3.2.1. Independent variables selecion
Table 6 – Dropped variables due to unfull filled or meaningless
3.4.3.2.2-Independent variables transformation
Table 7-Appropriated indicators with value type and transformation
Table 8 – Independent Variables Expected Signs in the Relationship
CHAPTER 4 – EMPERICAL RESULTS
4.1. Descriptive statistics
Table 10-Independent variables descriptive statistic
4.2. Regression results
4.2.1. The first model with Dependent variable is Default01
Table 11-Default statistic frequency
Table 12-Explanation of independent, statistical sample
Table 13-Summary of full model for binominal Default01 logistic functions
Model 1.2 interpreting
Model 1.3-4 interpretation
Table 15-Example of checking the power of qualitative variables’ classifying
4.2.1.3.1-Qualitative marginal effects
Table 16-Example of qualitative marginal effects on credit rating
4.2.1.3.2-Initiative for automatic tool
Table 17-Example of an automatic default predicting tool
4.2.2. The second model with Dependent variable is F2-loan group
Table 18-Loan group distribution frequency
Table 19-Summary of full model for Ologit loan group logistic functions
- Organization and procedures,
Model 2.2 interpretation
Model 2.3 interpretation
Table 21-Margin testing
Table 22-Predicting loan group sample
Table 23-Client’ probability of future loan group
4.2.3. The third model with Dependent variable is F2n-day of late payment
Table 24-Number of day in late payment distribution frequency
Table 25-Summary of full model for linear day of late
Model 3.2 interpretation
Model 3.3 interpretation
Table 27-Client with expected number of late days in payment
4.3. Test for any other limitation
4.3.1. Checking for Multicollinearity
Table 28- Correlation of dummy variables.
Table 29- Test for multicollinearity.
4.3.2. Checking for Homoscedasticity
Table 30- Test for homoscedasticity
4.4. Comparing results of some models
4.4.1. Logit functions back test
Table 31-Compare model 1.2 and 1.3-4 (both in predicting default risk), between risk lover, risk neutral and risk adverse
Figure 6: Distribution comparing (at 10% cut value)
4.4.2. Ologit functions back test
Figure 7: Ologit back test
4.4.3. Linear functions back test
CHAPTER 5 – CONCLUSION AND IMPLICATIONS
5.1. Main findings
5.2. Limitations of the study
5.3. Implications
5.4. Suggestion for further studies
References
Appendix 1-Variable Descriptive Statistic
5. Independent variables-Margin
Appendix 2-Full model for Logit functions Model 1.1a
Model 1.3-4
Appendix 4-Full model for Linear functions Model 3.1a
Model 3.1b
Appendix 5-Testing of Multicollinearity
Appendix 6-Testing of Homoscedasticity
Appendix 7-Terminations