On covariance estimation of non-synchronously observed diffusion processes

Takaki Hayashi, Nakahiro Yoshida

Research output: Contribution to journalArticle

186 Citations (Scopus)

Abstract

We consider the problem of estimating the covariance of two diffusion processes when they are observed only at discrete times in a non-synchronous manner. The modern, popular approach in the literature, the realized covariance estimator, which is based on (regularly spaced) synchronous data, is problematic because the choice of regular interval size and data interpolation scheme may lead to unreliable estimation. We propose a new estimator which is free of any 'synchronization' processing of the original data, hence free of bias or other problems caused by it.

Original languageEnglish
Pages (from-to)359-379
Number of pages21
JournalBernoulli
Volume11
Issue number2
DOIs
Publication statusPublished - 2005 Apr
Externally publishedYes

Fingerprint

Covariance Estimation
Diffusion Process
Estimator
Synchronization
Interpolate
Interval

Keywords

  • Diffusions
  • Discrete-time observations
  • High-frequency data
  • Mathematical finance
  • Non-synchronous trading
  • Quadratic variation
  • Realized volatility

ASJC Scopus subject areas

  • Statistics and Probability

Cite this

On covariance estimation of non-synchronously observed diffusion processes. / Hayashi, Takaki; Yoshida, Nakahiro.

In: Bernoulli, Vol. 11, No. 2, 04.2005, p. 359-379.

Research output: Contribution to journalArticle

Hayashi, Takaki ; Yoshida, Nakahiro. / On covariance estimation of non-synchronously observed diffusion processes. In: Bernoulli. 2005 ; Vol. 11, No. 2. pp. 359-379.
@article{fe4ec2aa22cf44489ba22b488f910a14,
title = "On covariance estimation of non-synchronously observed diffusion processes",
abstract = "We consider the problem of estimating the covariance of two diffusion processes when they are observed only at discrete times in a non-synchronous manner. The modern, popular approach in the literature, the realized covariance estimator, which is based on (regularly spaced) synchronous data, is problematic because the choice of regular interval size and data interpolation scheme may lead to unreliable estimation. We propose a new estimator which is free of any 'synchronization' processing of the original data, hence free of bias or other problems caused by it.",
keywords = "Diffusions, Discrete-time observations, High-frequency data, Mathematical finance, Non-synchronous trading, Quadratic variation, Realized volatility",
author = "Takaki Hayashi and Nakahiro Yoshida",
year = "2005",
month = "4",
doi = "10.3150/bj/1116340299",
language = "English",
volume = "11",
pages = "359--379",
journal = "Bernoulli",
issn = "1350-7265",
publisher = "International Statistical Institute",
number = "2",

}

TY - JOUR

T1 - On covariance estimation of non-synchronously observed diffusion processes

AU - Hayashi, Takaki

AU - Yoshida, Nakahiro

PY - 2005/4

Y1 - 2005/4

N2 - We consider the problem of estimating the covariance of two diffusion processes when they are observed only at discrete times in a non-synchronous manner. The modern, popular approach in the literature, the realized covariance estimator, which is based on (regularly spaced) synchronous data, is problematic because the choice of regular interval size and data interpolation scheme may lead to unreliable estimation. We propose a new estimator which is free of any 'synchronization' processing of the original data, hence free of bias or other problems caused by it.

AB - We consider the problem of estimating the covariance of two diffusion processes when they are observed only at discrete times in a non-synchronous manner. The modern, popular approach in the literature, the realized covariance estimator, which is based on (regularly spaced) synchronous data, is problematic because the choice of regular interval size and data interpolation scheme may lead to unreliable estimation. We propose a new estimator which is free of any 'synchronization' processing of the original data, hence free of bias or other problems caused by it.

KW - Diffusions

KW - Discrete-time observations

KW - High-frequency data

KW - Mathematical finance

KW - Non-synchronous trading

KW - Quadratic variation

KW - Realized volatility

UR - http://www.scopus.com/inward/record.url?scp=33646536672&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33646536672&partnerID=8YFLogxK

U2 - 10.3150/bj/1116340299

DO - 10.3150/bj/1116340299

M3 - Article

AN - SCOPUS:33646536672

VL - 11

SP - 359

EP - 379

JO - Bernoulli

JF - Bernoulli

SN - 1350-7265

IS - 2

ER -