Document Search
Add To My Bookshelf Sign in or Register Save And Annotate
Keywords:

operational risk sign in to follow this
loss data sign in to follow this
finite mixtures sign in to follow this
scaling models sign in to follow this
loss distribution sign in to follow this
bank sign in to follow this
Categories:

VaR Uses sign in to follow this
--Operational Risk sign in to follow this
Half-Life:
Impact:
Discuss This Paper
Sign in to follow this page
Recent Comments
  more
A Scaling Model for Severity of Operational Losses Using Generalized Additive Models for Location Scale And Shape (GAMLSS)
Year Of Publication: 2010
Month Of Publication: October
Pages: 34
Download Count: 15
View Count: 1775
Comment Num: 0
Language: English
Source: working paper
Who Can Read: Free
Date: 4-17-2011
Publisher: Administrator
Summary
Lack of internal data is one of the main challenges in quantifying operational risk for banks. In this paper we develop a scaling model that can simulate losses for a bank given readily available explanatory variables such as bank's assets, business lines, and event types. The model is based on a finite mixture distribution and uses the recently introduced ‘generalized additive models for location scale and shape’ (GAMLSS) framework. The model allows different scaling mechanisms for operational loss clusters and is able to capture different shapes and scales of the loss distributions for different business lines and event types. We calibrate the model using data from the US banking industry and simulate losses for two banks in the US. Contrary to existing knowledge, the model estimates reveal that the size of a bank is an important determinant of the severity of operational losses.
Author(s)
Evans, John Sign in to follow this author
Ganegoda, Amandha Sign in to follow this author
This document's citation network:
Similar Documents:
Close window
Sign up in one step, no personal information required. Already a Member?



Email:
Repeat Email:
User Name:
Password:
Confirm Password:

Sign Up


Welcome to GloriaMundi!
Thanks for singning up



continue or edit your profile