A general importance sampling algorithm for estimating portfolio loss probabilities in linear factor models

This paper develops a novel importance sampling algorithm for estimating the probability of large portfolio losses in the conditional independence framework. We apply exponential tilts to (i) the distribution of the natural sufficient statistics of the systematic risk factors and (ii) conditional de...

Full description

Saved in:
Bibliographic Details
Published in:Insurance, mathematics & economics Vol. 64; pp. 279 - 293
Main Authors: Scott, Alexandre, Metzler, Adam
Format: Journal Article
Language:English
Published: Amsterdam Elsevier B.V 01.09.2015
Elsevier Sequoia S.A
Subjects:
[formula omitted] copula
Algorithms
Copulas
Cross-entropy method
Exponential tilts
Gaussian copula
Importance sampling
Kullback–Leibler divergence
Mathematical models
Monte Carlo
Parameter estimation
Portfolio loss
Portfolio performance
Portfolios
Probability
Risk factors
Sampling
Statistics
Studies
Values
Kullback–Leibler divergence
t copula
Monte Carlo
Cross-entropy method
Portfolio loss
Gaussian copula
Importance sampling
Exponential tilts
ISSN:0167-6687, 1873-5959
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper develops a novel importance sampling algorithm for estimating the probability of large portfolio losses in the conditional independence framework. We apply exponential tilts to (i) the distribution of the natural sufficient statistics of the systematic risk factors and (ii) conditional default probabilities, given the simulated values of the systematic risk factors, and select parameter values by minimizing the Kullback–Leibler divergence of the resulting parametric family from the ideal (zero-variance) importance density. Optimal parameter values are shown to satisfy intuitive moment-matching conditions, and the asymptotic behaviour of large portfolios is used to approximate the requisite moments. In a sense we generalize the algorithm of Glasserman and Li (2005) so that it can be applied in a wider variety of models. We show how to implement our algorithm in the t copula model and compare its performance there to the algorithm developed by Chan and Kroese (2010). We find that our algorithm requires substantially less computational time (especially for large portfolios) but is slightly less accurate. Our algorithm can also be used to estimate more general risk measures, such as conditional tail expectations, whereas Chan and Kroese (2010) is specifically designed to estimate loss probabilities.
Bibliography:SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ISSN:0167-6687
1873-5959
DOI:10.1016/j.insmatheco.2015.06.001