Please use this identifier to cite or link to this item:
https://hdl.handle.net/10316/11758
Title: | Second Order Filter Distribution Approximations for Financial Time Series with Extreme Outliers | Authors: | Smith, J. Q. Santos, António A. F. |
Keywords: | Bayesian inference; Importance sampling; Particle filter; State space model; Stochastic volatility | Issue Date: | 2005 | Publisher: | FEUC. Grupo de Estudos Monetários e Financeiros | Citation: | Estudos do GEMF. 11 (2005) | Abstract: | Particle Filters are now regularly used to obtain the filter distributions associated with state space financial time series. Most commonly used nowadays is the auxiliary particle filter method in conjunction with a first order Taylor expansion of the log-likelihood. We argue in this paper that for series such as stock returns, which exhibit fairly frequent and extreme outliers, filters based on this first order approximation can easily break down. However, an auxiliary particle filter based on the much more rarely used second order approximation appears to perform well in these circumstances. To detach the issue of algorithm design from problems related to model misspecification and parameter estimation, we demonstrate the lack of robustness of the first order approximation and the feasibility of a specific second order approximation using simulated data. | URI: | https://hdl.handle.net/10316/11758 | Rights: | openAccess |
Appears in Collections: | FEUC- Vários |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Second Order Filter Distribution Approximations.pdf | 370.05 kB | Adobe PDF | View/Open |
Page view(s) 50
450
checked on Jul 17, 2024
Download(s)
261
checked on Jul 17, 2024
Google ScholarTM
Check
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.