Using sectioning to construct confidence intervals for quantiles when applying importance sampling

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Scopus citations

Abstract

Quantiles, which are known as values-at-risk in finance, are often used to measure risk. Confidence intervals provide a way of assessing the error of quantile estimators. When estimating extreme quantiles using crude Monte Carlo, the confidence intervals may have large half-widths, thus motivating the use of variance-reduction techniques (VRTs). This paper develops methods for constructing confidence intervals for quantiles when applying the VRT importance sampling. The confidence intervals, which are asymptotically valid as the number of samples grows large, are based on a technique known as sectioning. Empirical results seem to indicate that sectioning can lead to confidence intervals having better coverage than other existing methods.

Original languageEnglish (US)
Title of host publicationProceedings of the 2012 Winter Simulation Conference, WSC 2012
DOIs
StatePublished - 2012
Event2012 Winter Simulation Conference, WSC 2012 - Berlin, Germany
Duration: Dec 9 2012Dec 12 2012

Publication series

NameProceedings - Winter Simulation Conference
ISSN (Print)0891-7736

Other

Other2012 Winter Simulation Conference, WSC 2012
CountryGermany
CityBerlin
Period12/9/1212/12/12

All Science Journal Classification (ASJC) codes

  • Software
  • Modeling and Simulation
  • Computer Science Applications

Fingerprint Dive into the research topics of 'Using sectioning to construct confidence intervals for quantiles when applying importance sampling'. Together they form a unique fingerprint.

Cite this