Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Fuh, Cheng-Der, Jia, Yanwei, Kou, Steven
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2311.12330
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912642832007168
author Fuh, Cheng-Der
Jia, Yanwei
Kou, Steven
author_facet Fuh, Cheng-Der
Jia, Yanwei
Kou, Steven
contents Although stochastic models driven by latent Markov processes are widely used, the classical importance sampling methods based on the exponential tilting for these models suffers from the difficulties in computing the eigenvalues and associated eigenfunctions and the plausibility of the indirect asymptotic large deviation regime for the variance of the estimator. We propose a general importance sampling framework that twists the observable and latent processes separately using a link function that directly minimizes the estimator's variance. An optimal choice of the link function is chosen within the locally asymptotically normal family. We show the logarithmic efficiency of the proposed estimator. As applications, we estimate an overflow probability under a pandemic model and the CoVaR, a measurement of the co-dependent financial systemic risk. Both applications are beyond the scope of traditional importance sampling methods due to their nonlinear features.
format Preprint
id arxiv_https___arxiv_org_abs_2311_12330
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle A General Framework for Importance Sampling with Markov Random Walks
Fuh, Cheng-Der
Jia, Yanwei
Kou, Steven
Computation
Computational Finance
Risk Management
Although stochastic models driven by latent Markov processes are widely used, the classical importance sampling methods based on the exponential tilting for these models suffers from the difficulties in computing the eigenvalues and associated eigenfunctions and the plausibility of the indirect asymptotic large deviation regime for the variance of the estimator. We propose a general importance sampling framework that twists the observable and latent processes separately using a link function that directly minimizes the estimator's variance. An optimal choice of the link function is chosen within the locally asymptotically normal family. We show the logarithmic efficiency of the proposed estimator. As applications, we estimate an overflow probability under a pandemic model and the CoVaR, a measurement of the co-dependent financial systemic risk. Both applications are beyond the scope of traditional importance sampling methods due to their nonlinear features.
title A General Framework for Importance Sampling with Markov Random Walks
topic Computation
Computational Finance
Risk Management
url https://arxiv.org/abs/2311.12330