The application of statistical classification to predict sovereign default
- Authors: Vele, Rendani
- Date: 2023-10-13
- Subjects: Statistical classification , Neural networks (Computer science) , Regression analysis , Logits , Probits , Multiple imputation (Statistics) , Markov chain Monte Carlo , Debts, Public
- Language: English
- Type: Academic theses , Master's theses , text
- Identifier: http://hdl.handle.net/10962/424563 , vital:72164
- Description: When considering sovereign loans, it is imperative for a financial institution to have a good understanding of the sovereign they are transacting with. Defaults can occur if proper evaluation steps are not considered. To aid in the prediction of potential sovereign defaults, financial institutions, together with grading companies, quantify the risk associated with issuing a loan to a sovereign by developing sovereign default early warning systems (EWS). Various classification models are considered in this study to develop sovereign default EWS. These models are the binary logit, probit, Bayesian additive regression trees, and artificial neural networks. This study investigates the predictive performance of the various classification techniques. Sovereign information is not readily available, so missing data techniques are considered in order to counter the data availability issue. Sovereign defaults are rare, which results in an imbalance in the distribution of the binary dependent variable. To assess data sets with such characteristics, metrics for imbalanced data are considered for model performance comparison. From the findings, the Bayesian additive regression technique generated better results than the other techniques when considering a basic data analysis. Moreover when cross-validation was considered, the neural network technique performed best. In addition, regional models had better results than the global model when considering model predictive capability. The significance of this study is to develop sovereign default prediction models using various classification techniques focused on enhancing previous literature and analysis through the application of Bayesian additive regression trees. , Thesis (MSc) -- Faculty of Science, Statistics, 2023
- Full Text:
- Date Issued: 2023-10-13
- Authors: Vele, Rendani
- Date: 2023-10-13
- Subjects: Statistical classification , Neural networks (Computer science) , Regression analysis , Logits , Probits , Multiple imputation (Statistics) , Markov chain Monte Carlo , Debts, Public
- Language: English
- Type: Academic theses , Master's theses , text
- Identifier: http://hdl.handle.net/10962/424563 , vital:72164
- Description: When considering sovereign loans, it is imperative for a financial institution to have a good understanding of the sovereign they are transacting with. Defaults can occur if proper evaluation steps are not considered. To aid in the prediction of potential sovereign defaults, financial institutions, together with grading companies, quantify the risk associated with issuing a loan to a sovereign by developing sovereign default early warning systems (EWS). Various classification models are considered in this study to develop sovereign default EWS. These models are the binary logit, probit, Bayesian additive regression trees, and artificial neural networks. This study investigates the predictive performance of the various classification techniques. Sovereign information is not readily available, so missing data techniques are considered in order to counter the data availability issue. Sovereign defaults are rare, which results in an imbalance in the distribution of the binary dependent variable. To assess data sets with such characteristics, metrics for imbalanced data are considered for model performance comparison. From the findings, the Bayesian additive regression technique generated better results than the other techniques when considering a basic data analysis. Moreover when cross-validation was considered, the neural network technique performed best. In addition, regional models had better results than the global model when considering model predictive capability. The significance of this study is to develop sovereign default prediction models using various classification techniques focused on enhancing previous literature and analysis through the application of Bayesian additive regression trees. , Thesis (MSc) -- Faculty of Science, Statistics, 2023
- Full Text:
- Date Issued: 2023-10-13
The predictive ability of the yield spread in timing the stock exchange: a South African case
- Authors: Cook, Jenna
- Date: 2020
- Subjects: Stocks -- Mathematical models , Probits , Johannesburg Stock Exchange
- Language: English
- Type: Thesis , Masters , MCom
- Identifier: http://hdl.handle.net/10962/147025 , vital:38586
- Description: The use of the yield curve in forecasting economic recessions is well established in the literature. A new avenue of use for the yield curve has emerged in the form of using it to forecast bull and bear stock markets. This has the potential to change how investors manage portfolios. A dynamic market-timing strategy would allow investors to shift out of or in to stock markets based on the probability of bear stock market in the future. The relationship between the yield curve and the stock market is tested using an adapted probit model. This has proven positive with encouraging results for the US, India and Spain. This is tested for South Africa using the adapted probit model and the SA yield spread. Bear stock markets are identified on the JSE and forms part of the probit modelling process. Bear markets are identified using a six- and four-month criteria. As South Africa is a small, open and developing economy, the probit is also modelled using the US yield spread. The three probit models do not appear to track bear markets well. This is substantiated through the Henriksson-Merton parametric model test which tests for market timing ability. The results for the SA yield spread using both bear market criteria do not show market timing ability, however, the SA and US yield spread model does show potential market timing ability.
- Full Text:
- Date Issued: 2020
- Authors: Cook, Jenna
- Date: 2020
- Subjects: Stocks -- Mathematical models , Probits , Johannesburg Stock Exchange
- Language: English
- Type: Thesis , Masters , MCom
- Identifier: http://hdl.handle.net/10962/147025 , vital:38586
- Description: The use of the yield curve in forecasting economic recessions is well established in the literature. A new avenue of use for the yield curve has emerged in the form of using it to forecast bull and bear stock markets. This has the potential to change how investors manage portfolios. A dynamic market-timing strategy would allow investors to shift out of or in to stock markets based on the probability of bear stock market in the future. The relationship between the yield curve and the stock market is tested using an adapted probit model. This has proven positive with encouraging results for the US, India and Spain. This is tested for South Africa using the adapted probit model and the SA yield spread. Bear stock markets are identified on the JSE and forms part of the probit modelling process. Bear markets are identified using a six- and four-month criteria. As South Africa is a small, open and developing economy, the probit is also modelled using the US yield spread. The three probit models do not appear to track bear markets well. This is substantiated through the Henriksson-Merton parametric model test which tests for market timing ability. The results for the SA yield spread using both bear market criteria do not show market timing ability, however, the SA and US yield spread model does show potential market timing ability.
- Full Text:
- Date Issued: 2020
- «
- ‹
- 1
- ›
- »