A state space approach to estimating the integrated variance under the existence of market microstructure noise

Daisuke Nagakura, Toshiaki Watanabe

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

This article develops a state space method for estimating the integrated variance under the existence of market microstructure noise (MMN). Our method is based on a state space representation of the noisecontaminated RV (NCRV), namely, the realized variance (RV) calculated with observed prices contaminated by MMNs. The main idea of our method is to filter out the bias component, which we call the microstructure noise (MN) component, from the NCRV using the Kalman filter. We apply the proposed method to yen/dollar exchange rate data.We find that about half of the variation in NCRV is because of the MN component. The proposed method can serve as a convenient way to estimate a general class of continuous-time stochastic volatility models under the existence of MMN.

Original languageEnglish
Pages (from-to)45-82
Number of pages38
JournalJournal of Financial Econometrics
Volume13
Issue number1
DOIs
Publication statusPublished - 2015

Fingerprint

Market microstructure noise
State space
Integrated variance
Realized variance
Microstructure noise
Continuous time
Kalman filter
Stochastic volatility model
Exchange rates
Filter

Keywords

  • Exchange rate
  • Identification
  • Integrated variance
  • Market microstructure noise
  • Realized variance
  • State space

ASJC Scopus subject areas

  • Economics and Econometrics
  • Finance

Cite this

A state space approach to estimating the integrated variance under the existence of market microstructure noise. / Nagakura, Daisuke; Watanabe, Toshiaki.

In: Journal of Financial Econometrics, Vol. 13, No. 1, 2015, p. 45-82.

Research output: Contribution to journalArticle

@article{205279753ee240eaa3fe335001ff4203,
title = "A state space approach to estimating the integrated variance under the existence of market microstructure noise",
abstract = "This article develops a state space method for estimating the integrated variance under the existence of market microstructure noise (MMN). Our method is based on a state space representation of the noisecontaminated RV (NCRV), namely, the realized variance (RV) calculated with observed prices contaminated by MMNs. The main idea of our method is to filter out the bias component, which we call the microstructure noise (MN) component, from the NCRV using the Kalman filter. We apply the proposed method to yen/dollar exchange rate data.We find that about half of the variation in NCRV is because of the MN component. The proposed method can serve as a convenient way to estimate a general class of continuous-time stochastic volatility models under the existence of MMN.",
keywords = "Exchange rate, Identification, Integrated variance, Market microstructure noise, Realized variance, State space",
author = "Daisuke Nagakura and Toshiaki Watanabe",
year = "2015",
doi = "10.1093/jjfinec/nbt015",
language = "English",
volume = "13",
pages = "45--82",
journal = "Journal of Financial Econometrics",
issn = "1479-8409",
publisher = "Oxford University Press",
number = "1",

}

TY - JOUR

T1 - A state space approach to estimating the integrated variance under the existence of market microstructure noise

AU - Nagakura, Daisuke

AU - Watanabe, Toshiaki

PY - 2015

Y1 - 2015

N2 - This article develops a state space method for estimating the integrated variance under the existence of market microstructure noise (MMN). Our method is based on a state space representation of the noisecontaminated RV (NCRV), namely, the realized variance (RV) calculated with observed prices contaminated by MMNs. The main idea of our method is to filter out the bias component, which we call the microstructure noise (MN) component, from the NCRV using the Kalman filter. We apply the proposed method to yen/dollar exchange rate data.We find that about half of the variation in NCRV is because of the MN component. The proposed method can serve as a convenient way to estimate a general class of continuous-time stochastic volatility models under the existence of MMN.

AB - This article develops a state space method for estimating the integrated variance under the existence of market microstructure noise (MMN). Our method is based on a state space representation of the noisecontaminated RV (NCRV), namely, the realized variance (RV) calculated with observed prices contaminated by MMNs. The main idea of our method is to filter out the bias component, which we call the microstructure noise (MN) component, from the NCRV using the Kalman filter. We apply the proposed method to yen/dollar exchange rate data.We find that about half of the variation in NCRV is because of the MN component. The proposed method can serve as a convenient way to estimate a general class of continuous-time stochastic volatility models under the existence of MMN.

KW - Exchange rate

KW - Identification

KW - Integrated variance

KW - Market microstructure noise

KW - Realized variance

KW - State space

UR - http://www.scopus.com/inward/record.url?scp=84942050421&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84942050421&partnerID=8YFLogxK

U2 - 10.1093/jjfinec/nbt015

DO - 10.1093/jjfinec/nbt015

M3 - Article

AN - SCOPUS:84942050421

VL - 13

SP - 45

EP - 82

JO - Journal of Financial Econometrics

JF - Journal of Financial Econometrics

SN - 1479-8409

IS - 1

ER -