Formulating hypothetical scenarios in correlation stress testing via a Bayesian framework |
| |
Institution: | 1. Department of Radiography and Radiology, Faculty of Health Sciences, University of Calabar, Calabar, Nigeria;2. Discipline of Medical Radiation Sciences, Faculty of Health Sciences, University of Sydney, Lidcombe, NSW, Australia;1. Department of Surgery, McMaster University, Hamilton, ON, Canada;2. Department of Surgical Oncology, Hamilton Health Sciences and Juravinski Hospital and Cancer Centre, Hamilton, ON, Canada;3. Department of Oncology, Hamilton Health Sciences and Juravinski Hospital and Cancer Centre, Hamilton, ON, Canada;4. Department of Surgery, St. Joseph''s Healthcare, Hamilton, ON, Canada;5. Department of Clinical Epidemiology and Biostatistics, McMaster University and Biostatistics Unit, St. Joseph''s Healthcare, Hamilton, ON, Canada;6. Faculty of Health Sciences, Simon Fraser University, Burnaby, BC, Canada;1. Department of Radiology, Brigham and Women’s Hospital, Boston, Massachusetts;1. Department of Economics, Waikato University, New Zealand;2. Facultad de Economía, Universidad del Rosario, Colombia;3. Department of Economics, University of Macedonia, Greece;1. School of Securities and Futures, Southwestern University of Finance and Economics, Chengdu 611130, China;2. The Wang Yanan Institute for Studies in Economics, Xiamen University, Xiamen, Fujian 361005, China |
| |
Abstract: | Correlation stress testing refers to the correlation matrix adjustment to evaluate potential impact of the changes in correlations under financial crises. There are two categories, sensitivity tests and scenario tests. For a scenario test, the correlation matrix is adjusted to mimic the situation under an underlying stress event. It is only natural that when some correlations are altered, the other correlations (peripheral correlations) should vary as well. However, most existing methods ignore this potential change in peripheral correlations. In this paper, we propose a Bayesian correlation adjustment method to give a new correlation matrix for a scenario test based on the original correlation matrix and views on correlations such that peripheral correlations are altered according to the dependence structure of empirical correlations. The algorithm of posterior simulation is also extended so that two correlations can be updated in one Gibbs sampler step. This greatly enhances the rate of convergence. The proposed method is applied to an international stock portfolio dataset. |
| |
Keywords: | Correlation stress testing Scenario test Bayesian estimation Block Gibbs sampling |
本文献已被 ScienceDirect 等数据库收录! |
|