Model selection for Lévy measures in diffusion processes with jumps from discrete observations

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

We deal with parametric inference and selection problems for jump components in discretely observed diffusion processes with jumps. We prepare several competing parametric models for the Lévy measure that might be misspecified, and select the best model from the aspect of information criteria. We construct quasi-information criteria (QIC), which are approximations of the information criteria based on continuous observations.

Original languageEnglish
Pages (from-to)516-532
Number of pages17
JournalJournal of Statistical Planning and Inference
Volume139
Issue number2
DOIs
Publication statusPublished - 2009 Feb 1
Externally publishedYes

Fingerprint

Discrete Observations
Information Criterion
Model Selection
Diffusion Process
Jump
Parametric Inference
Parametric Model
Approximation
Information criterion
Model selection
Diffusion process
Model

Keywords

  • Diffusion processes with jumps
  • Discrete observations
  • Expectation-unbiasedness
  • Lévy measures
  • Model selection
  • Quasi-information criteria

ASJC Scopus subject areas

  • Statistics, Probability and Uncertainty
  • Applied Mathematics
  • Statistics and Probability

Cite this

@article{c1981fb0db09454eaf824f2dc1f7962f,
title = "Model selection for L{\'e}vy measures in diffusion processes with jumps from discrete observations",
abstract = "We deal with parametric inference and selection problems for jump components in discretely observed diffusion processes with jumps. We prepare several competing parametric models for the L{\'e}vy measure that might be misspecified, and select the best model from the aspect of information criteria. We construct quasi-information criteria (QIC), which are approximations of the information criteria based on continuous observations.",
keywords = "Diffusion processes with jumps, Discrete observations, Expectation-unbiasedness, L{\'e}vy measures, Model selection, Quasi-information criteria",
author = "Yasutaka Shimizu",
year = "2009",
month = "2",
day = "1",
doi = "10.1016/j.jspi.2008.05.009",
language = "English",
volume = "139",
pages = "516--532",
journal = "Journal of Statistical Planning and Inference",
issn = "0378-3758",
publisher = "Elsevier",
number = "2",

}

TY - JOUR

T1 - Model selection for Lévy measures in diffusion processes with jumps from discrete observations

AU - Shimizu, Yasutaka

PY - 2009/2/1

Y1 - 2009/2/1

N2 - We deal with parametric inference and selection problems for jump components in discretely observed diffusion processes with jumps. We prepare several competing parametric models for the Lévy measure that might be misspecified, and select the best model from the aspect of information criteria. We construct quasi-information criteria (QIC), which are approximations of the information criteria based on continuous observations.

AB - We deal with parametric inference and selection problems for jump components in discretely observed diffusion processes with jumps. We prepare several competing parametric models for the Lévy measure that might be misspecified, and select the best model from the aspect of information criteria. We construct quasi-information criteria (QIC), which are approximations of the information criteria based on continuous observations.

KW - Diffusion processes with jumps

KW - Discrete observations

KW - Expectation-unbiasedness

KW - Lévy measures

KW - Model selection

KW - Quasi-information criteria

UR - http://www.scopus.com/inward/record.url?scp=55149088339&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=55149088339&partnerID=8YFLogxK

U2 - 10.1016/j.jspi.2008.05.009

DO - 10.1016/j.jspi.2008.05.009

M3 - Article

VL - 139

SP - 516

EP - 532

JO - Journal of Statistical Planning and Inference

JF - Journal of Statistical Planning and Inference

SN - 0378-3758

IS - 2

ER -