Confidence intervals for multivariate value at risk

Goh, Y. L. and Pooi, Ah Hin * (2012) Confidence intervals for multivariate value at risk. In: International Conference on Computer Engineering & Mathematical Sciences, 27 Aug 2012, Kuala Lumpur.

Pooi Ah Hin - Confidence Intervals for Multivariate Value at Risk.pdf - Accepted Version

Download (297kB) | Preview


Confidence intervals for the y-quantile of a linear combination of N non-normal variates with a linear dependence structure would be useful to the financial institutions as the intervals enable the accuracy of the value at risk (VaR) of a portfolio of investments to be quantified. Presently, we construct 100(1-α) % confidence intervals for the y-quantile using the procedures based on bootstrap, normal approximation and hypothesis testing. We show that the method based on hypothesis testing produces confidence interval which is more satisfactory than those found by using bootstrap or normal approximation.

Item Type: Conference or Workshop Item (Paper)
Additional Information: First author with Department of Mathematical and Actuarial Sciences, Universiti Tunku Abdul Rahman; 2nd author with Sunway University Business School.
Uncontrolled Keywords: non-normal variates; multivariate value at risk; y-quantile; confidence interval
Subjects: Q Science > QA Mathematics
Divisions: Others > Non Sunway Academics
Sunway University > School of Mathematical Sciences > Department of Applied Statistics
Depositing User: Ms. Molly Chuah
Date Deposited: 11 Jan 2014 14:47
Last Modified: 03 Jul 2019 08:38

Actions (login required)

View Item View Item