Nonparametric estimation of time varying correlation coefficient

Ji Eun Choi; Dong Wan Shin

doi:10.1007/s42952-020-00073-6

Nonparametric estimation of time varying correlation coefficient

Ji Eun Choi, Dong Wan Shin

Department of Statistics

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

3 Scopus citations

Abstract

We propose a new time varying correlation coefficient, which is a local correlation measure of a pair of time series. The time varying correlation coefficient is locally estimated using a nonparametric kernel method. Asymptotic normality of the estimated time varying correlation is established, which allows us to construct statistical methods of confidence interval and hypothesis tests. Finite sample validity of the proposed methods are demonstrated by a Monte–Carlo study. The proposed time varying correlation coefficient method is well illustrated by an analysis of five sets of world major stock price index returns.

Original language	English
Pages (from-to)	333-353
Number of pages	21
Journal	Journal of the Korean Statistical Society
Volume	50
Issue number	2
DOIs	https://doi.org/10.1007/s42952-020-00073-6
State	Published - Jun 2021

Bibliographical note

Funding Information:
The authors are very thankful of two anonymous referees whose comments improved the paper considerably. This study was supported by a Grant from the National Research Foundation of Korea (2019R1A2C1004679) and by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (2019R1A6A1A11051177).

Publisher Copyright:
© 2020, Korean Statistical Society.

Keywords

Confidence interval
Nonparametric estimation
Statistical test
Time varying correlation coefficient

Access to Document

10.1007/s42952-020-00073-6

Cite this

@article{80cf59799f5b491bad2585bb46e90ed5,

title = "Nonparametric estimation of time varying correlation coefficient",

abstract = "We propose a new time varying correlation coefficient, which is a local correlation measure of a pair of time series. The time varying correlation coefficient is locally estimated using a nonparametric kernel method. Asymptotic normality of the estimated time varying correlation is established, which allows us to construct statistical methods of confidence interval and hypothesis tests. Finite sample validity of the proposed methods are demonstrated by a Monte–Carlo study. The proposed time varying correlation coefficient method is well illustrated by an analysis of five sets of world major stock price index returns.",

keywords = "Confidence interval, Nonparametric estimation, Statistical test, Time varying correlation coefficient",

author = "Choi, {Ji Eun} and Shin, {Dong Wan}",

note = "Funding Information: The authors are very thankful of two anonymous referees whose comments improved the paper considerably. This study was supported by a Grant from the National Research Foundation of Korea (2019R1A2C1004679) and by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (2019R1A6A1A11051177). Publisher Copyright: {\textcopyright} 2020, Korean Statistical Society.",

year = "2021",

month = jun,

doi = "10.1007/s42952-020-00073-6",

language = "English",

volume = "50",

pages = "333--353",

journal = "Journal of the Korean Statistical Society",

issn = "1226-3192",

publisher = "Korean Statistical Society",

number = "2",

}

TY - JOUR

T1 - Nonparametric estimation of time varying correlation coefficient

AU - Choi, Ji Eun

AU - Shin, Dong Wan

N1 - Funding Information: The authors are very thankful of two anonymous referees whose comments improved the paper considerably. This study was supported by a Grant from the National Research Foundation of Korea (2019R1A2C1004679) and by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (2019R1A6A1A11051177). Publisher Copyright: © 2020, Korean Statistical Society.

PY - 2021/6

Y1 - 2021/6

N2 - We propose a new time varying correlation coefficient, which is a local correlation measure of a pair of time series. The time varying correlation coefficient is locally estimated using a nonparametric kernel method. Asymptotic normality of the estimated time varying correlation is established, which allows us to construct statistical methods of confidence interval and hypothesis tests. Finite sample validity of the proposed methods are demonstrated by a Monte–Carlo study. The proposed time varying correlation coefficient method is well illustrated by an analysis of five sets of world major stock price index returns.

AB - We propose a new time varying correlation coefficient, which is a local correlation measure of a pair of time series. The time varying correlation coefficient is locally estimated using a nonparametric kernel method. Asymptotic normality of the estimated time varying correlation is established, which allows us to construct statistical methods of confidence interval and hypothesis tests. Finite sample validity of the proposed methods are demonstrated by a Monte–Carlo study. The proposed time varying correlation coefficient method is well illustrated by an analysis of five sets of world major stock price index returns.

KW - Confidence interval

KW - Nonparametric estimation

KW - Statistical test

KW - Time varying correlation coefficient

UR - http://www.scopus.com/inward/record.url?scp=85086155597&partnerID=8YFLogxK

U2 - 10.1007/s42952-020-00073-6

DO - 10.1007/s42952-020-00073-6

M3 - Article

AN - SCOPUS:85086155597

SN - 1226-3192

VL - 50

SP - 333

EP - 353

JO - Journal of the Korean Statistical Society

JF - Journal of the Korean Statistical Society

IS - 2

ER -

Nonparametric estimation of time varying correlation coefficient

Abstract

Bibliographical note

Keywords

Access to Document

Fingerprint

Cite this