Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You and Your Team.

Learn More →

Zero‐modified discrete distributions for operational risk modelling

Zero‐modified discrete distributions for operational risk modelling Purpose – The purpose of this paper is to introduce the zero‐modified distributions in the calculation of operational value‐at‐risk. Design/methodology/approach – This kind of distributions is preferred when excess of zeroes is observed. In operational risk, this phenomenon may be due to the scarcity of data, the existence of extreme values and/or the threshold from which banks start to collect losses. In this article, the paper focuses on the analysis of damage to physical assets. Findings – The results show that basic Poisson distribution underestimates the dispersion, and then leads to the underestimation of the capital charge. However, zero‐modified Poisson distributions perform well the frequency. In addition, basic negative binomial and its related zero‐modified distributions, in their turn, offer a good prediction of count events. To choose the distribution that suits better the frequency, the paper uses the Vuong's test. Its results indicate that zero‐modified Poisson distributions, basic negative binomial and its related zero‐modified distributions are equivalent. This conclusion is confirmed by the capital charge calculated since the differences between the six aggregations are not significant except that of basic Poisson distribution. Originality/value – Recently, the zero‐modified formulations are widely used in many fields because of the low frequency of the events. This article aims to describe the frequency of operational risk using zero‐modified distributions. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png The Journal of Risk Finance Emerald Publishing

Zero‐modified discrete distributions for operational risk modelling

The Journal of Risk Finance , Volume 13 (5): 15 – Nov 2, 2012

Loading next page...
 
/lp/emerald-publishing/zero-modified-discrete-distributions-for-operational-risk-modelling-b6xtrE7GEC
Publisher
Emerald Publishing
Copyright
Copyright © 2012 Emerald Group Publishing Limited. All rights reserved.
ISSN
1526-5943
DOI
10.1108/15265941211273768
Publisher site
See Article on Publisher Site

Abstract

Purpose – The purpose of this paper is to introduce the zero‐modified distributions in the calculation of operational value‐at‐risk. Design/methodology/approach – This kind of distributions is preferred when excess of zeroes is observed. In operational risk, this phenomenon may be due to the scarcity of data, the existence of extreme values and/or the threshold from which banks start to collect losses. In this article, the paper focuses on the analysis of damage to physical assets. Findings – The results show that basic Poisson distribution underestimates the dispersion, and then leads to the underestimation of the capital charge. However, zero‐modified Poisson distributions perform well the frequency. In addition, basic negative binomial and its related zero‐modified distributions, in their turn, offer a good prediction of count events. To choose the distribution that suits better the frequency, the paper uses the Vuong's test. Its results indicate that zero‐modified Poisson distributions, basic negative binomial and its related zero‐modified distributions are equivalent. This conclusion is confirmed by the capital charge calculated since the differences between the six aggregations are not significant except that of basic Poisson distribution. Originality/value – Recently, the zero‐modified formulations are widely used in many fields because of the low frequency of the events. This article aims to describe the frequency of operational risk using zero‐modified distributions.

Journal

The Journal of Risk FinanceEmerald Publishing

Published: Nov 2, 2012

Keywords: Operational risk; lda; Poisson distribution; Excess zeroes; Overdispersion; Zero‐inflated distributions; Hurdle distributions; Negative binomial distribution; Capital charge; Basel II accord; Risk management; Binomial distribution

References