Probabilistic and statistical modeling of fixed income assets
Abstract/Contents
- Abstract
- Fix income market is a very dynamic field in the eyes of finance modelers. There have been many models in the extant literatures trying to describe the dynamics of the short rate and default intensity as realistically as possible so that some of the most important credit assets can be better priced and have their risk better understood. Here we are going to propose first of all two Monte Carlo algorithms for simulating the default times of the financial entities in a certain portfolio. The first algorithm is unbiased but more computationally expensive than the second one, which introduces some bias as tradeoff. We also show that the bias introduced in the second algorithm can be controlled by a prespecified small constant. Moreover, we present a method based on measure change to solve the pricing and risk management of these credit assets that can accommodate many different model settings, and at the same time extend the computational tractability of some well understood models to more complicated ones. In particular, by applying our measure change one can allow the company defaults to be self- and cross-excited, as well as correlated with interest rate and recovery rate. These features have been observed in empirical studies and they are quite essential in pricing multi-name credit portfolios. Another part of this thesis work focuses on predicting the trade prices of corporate bonds with benchmark prices coming from some probabilistic models given. The discrepancy between the actual trade prices and theoretical benchmarks is determined more by the market microstructures trade information so a statistical approach might be more useful here. We have tried some models based on supervised learning techniques on a certain dataset and compared their performance in bond trade price prediction.
Description
| Type of resource | text |
|---|---|
| Form | electronic; electronic resource; remote |
| Extent | 1 online resource. |
| Publication date | 2012 |
| Issuance | monographic |
| Language | English |
Creators/Contributors
| Associated with | Zhu, Shilin, Mr |
|---|---|
| Associated with | Stanford University, Department of Statistics |
| Primary advisor | Giesecke, Kay |
| Primary advisor | Lai, T. L |
| Thesis advisor | Giesecke, Kay |
| Thesis advisor | Lai, T. L |
| Thesis advisor | Dembo, Amir |
| Advisor | Dembo, Amir |
Subjects
| Genre | Theses |
|---|
Bibliographic information
| Statement of responsibility | Shilin Zhu. |
|---|---|
| Note | Submitted to the Department of Statistics. |
| Thesis | Thesis (Ph.D.)--Stanford University, 2012. |
| Location | electronic resource |
Access conditions
- Copyright
- © 2012 by Shilin Zhu
Also listed in
Loading usage metrics...