Fast smoothing in switching approximations of non-linear and non-Gaussian models

Ivan Gorynin; Stéphane Derrode; Emmanuel Monfrini; Wojciech Pieczynski

doi:10.1016/j.csda.2017.04.007

Fast smoothing in switching approximations of non-linear and non-Gaussian models

Ivan Gorynin
, Stéphane Derrode
, Emmanuel Monfrini
, Wojciech Pieczynski

Université Paris-Saclay
Université de Lyon

Research output: Contribution to journal › Article › peer-review

Abstract

Statistical smoothing in general non-linear non-Gaussian systems is a challenging problem. A new smoothing method based on approximating the original system by a recent switching model has been introduced. Such switching model allows fast and optimal smoothing. The new algorithm is validated through an application on stochastic volatility and dynamic beta models. Simulation experiments indicate its remarkable performances and low processing cost. In practice, the proposed approach can overcome the limitations of particle smoothing methods and may apply where their usage is discarded.

Original language	English
Pages (from-to)	38-46
Number of pages	9
Journal	Computational Statistics and Data Analysis
Volume	114
DOIs	https://doi.org/10.1016/j.csda.2017.04.007
Publication status	Published - 1 Oct 2017
Externally published	Yes

Keywords

Conditionally Gaussian linear state-space models
Conditionally Markov switching hidden linear models
Optimal statistical smoother
Smoothing in non-linear systems
Stochastic volatility

Access to Document

10.1016/j.csda.2017.04.007

Cite this

@article{3c71b4a36aed4edfb191e80d4846a314,

title = "Fast smoothing in switching approximations of non-linear and non-Gaussian models",

abstract = "Statistical smoothing in general non-linear non-Gaussian systems is a challenging problem. A new smoothing method based on approximating the original system by a recent switching model has been introduced. Such switching model allows fast and optimal smoothing. The new algorithm is validated through an application on stochastic volatility and dynamic beta models. Simulation experiments indicate its remarkable performances and low processing cost. In practice, the proposed approach can overcome the limitations of particle smoothing methods and may apply where their usage is discarded.",

keywords = "Conditionally Gaussian linear state-space models, Conditionally Markov switching hidden linear models, Optimal statistical smoother, Smoothing in non-linear systems, Stochastic volatility",

author = "Ivan Gorynin and St{\'e}phane Derrode and Emmanuel Monfrini and Wojciech Pieczynski",

note = "Publisher Copyright: {\textcopyright} 2017 Elsevier B.V.",

year = "2017",

month = oct,

day = "1",

doi = "10.1016/j.csda.2017.04.007",

language = "English",

volume = "114",

pages = "38--46",

journal = "Computational Statistics and Data Analysis",

issn = "0167-9473",

}

TY - JOUR

T1 - Fast smoothing in switching approximations of non-linear and non-Gaussian models

AU - Gorynin, Ivan

AU - Derrode, Stéphane

AU - Monfrini, Emmanuel

AU - Pieczynski, Wojciech

PY - 2017/10/1

Y1 - 2017/10/1

N2 - Statistical smoothing in general non-linear non-Gaussian systems is a challenging problem. A new smoothing method based on approximating the original system by a recent switching model has been introduced. Such switching model allows fast and optimal smoothing. The new algorithm is validated through an application on stochastic volatility and dynamic beta models. Simulation experiments indicate its remarkable performances and low processing cost. In practice, the proposed approach can overcome the limitations of particle smoothing methods and may apply where their usage is discarded.

AB - Statistical smoothing in general non-linear non-Gaussian systems is a challenging problem. A new smoothing method based on approximating the original system by a recent switching model has been introduced. Such switching model allows fast and optimal smoothing. The new algorithm is validated through an application on stochastic volatility and dynamic beta models. Simulation experiments indicate its remarkable performances and low processing cost. In practice, the proposed approach can overcome the limitations of particle smoothing methods and may apply where their usage is discarded.

KW - Conditionally Gaussian linear state-space models

KW - Conditionally Markov switching hidden linear models

KW - Optimal statistical smoother

KW - Smoothing in non-linear systems

KW - Stochastic volatility

U2 - 10.1016/j.csda.2017.04.007

DO - 10.1016/j.csda.2017.04.007

M3 - Article

AN - SCOPUS:85020434352

SN - 0167-9473

VL - 114

SP - 38

EP - 46

JO - Computational Statistics and Data Analysis

JF - Computational Statistics and Data Analysis

ER -

Fast smoothing in switching approximations of non-linear and non-Gaussian models

Abstract

Keywords

Access to Document

Fingerprint

Cite this