Inference for Local Autocorrelations in Locally Stationary Models

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

For nonstationary processes, the time-varying correlation structure provides useful insights into the underlying model dynamics. We study estimation and inferences for local autocorrelation process in locally stationary time series. Our constructed simultaneous confidence band can be used to address important hypothesis testing problems, such as whether the local autocorrelation process is indeed time-varying and whether the local autocorrelation is zero. In particular, our result provides an important generalization of the R function acf()to locally stationary Gaussian processes. Simulation studies and two empirical applications are developed. For the global temperature series, we find that the local autocorrelations are time-varying and have a “V” shape during 1910–1960. For the S&P 500 index, we conclude that the returns satisfy the efficient-market hypothesis whereas the magnitudes of returns show significant local autocorrelations.

Original languageEnglish (US)
Pages (from-to)296-306
Number of pages11
JournalJournal of Business and Economic Statistics
Volume33
Issue number2
DOIs
StatePublished - Apr 3 2015

Fingerprint

Autocorrelation
Time-varying
Efficient Market Hypothesis
hypothesis testing
Simultaneous Confidence Bands
Stationary Gaussian Process
Stationary Time Series
Nonstationary Processes
Model
Correlation Structure
time series
Hypothesis Testing
confidence
simulation
Inference
Simulation Study
market
Series
time
Zero

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Social Sciences (miscellaneous)
  • Economics and Econometrics
  • Statistics, Probability and Uncertainty

Cite this

@article{6db4c78e8f044bd0b4239be71bc18ce1,
title = "Inference for Local Autocorrelations in Locally Stationary Models",
abstract = "For nonstationary processes, the time-varying correlation structure provides useful insights into the underlying model dynamics. We study estimation and inferences for local autocorrelation process in locally stationary time series. Our constructed simultaneous confidence band can be used to address important hypothesis testing problems, such as whether the local autocorrelation process is indeed time-varying and whether the local autocorrelation is zero. In particular, our result provides an important generalization of the R function acf()to locally stationary Gaussian processes. Simulation studies and two empirical applications are developed. For the global temperature series, we find that the local autocorrelations are time-varying and have a “V” shape during 1910–1960. For the S&P 500 index, we conclude that the returns satisfy the efficient-market hypothesis whereas the magnitudes of returns show significant local autocorrelations.",
author = "Zhibiao Zhao",
year = "2015",
month = "4",
day = "3",
doi = "10.1080/07350015.2014.948177",
language = "English (US)",
volume = "33",
pages = "296--306",
journal = "Journal of Business and Economic Statistics",
issn = "0735-0015",
publisher = "American Statistical Association",
number = "2",

}

Inference for Local Autocorrelations in Locally Stationary Models. / Zhao, Zhibiao.

In: Journal of Business and Economic Statistics, Vol. 33, No. 2, 03.04.2015, p. 296-306.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Inference for Local Autocorrelations in Locally Stationary Models

AU - Zhao, Zhibiao

PY - 2015/4/3

Y1 - 2015/4/3

N2 - For nonstationary processes, the time-varying correlation structure provides useful insights into the underlying model dynamics. We study estimation and inferences for local autocorrelation process in locally stationary time series. Our constructed simultaneous confidence band can be used to address important hypothesis testing problems, such as whether the local autocorrelation process is indeed time-varying and whether the local autocorrelation is zero. In particular, our result provides an important generalization of the R function acf()to locally stationary Gaussian processes. Simulation studies and two empirical applications are developed. For the global temperature series, we find that the local autocorrelations are time-varying and have a “V” shape during 1910–1960. For the S&P 500 index, we conclude that the returns satisfy the efficient-market hypothesis whereas the magnitudes of returns show significant local autocorrelations.

AB - For nonstationary processes, the time-varying correlation structure provides useful insights into the underlying model dynamics. We study estimation and inferences for local autocorrelation process in locally stationary time series. Our constructed simultaneous confidence band can be used to address important hypothesis testing problems, such as whether the local autocorrelation process is indeed time-varying and whether the local autocorrelation is zero. In particular, our result provides an important generalization of the R function acf()to locally stationary Gaussian processes. Simulation studies and two empirical applications are developed. For the global temperature series, we find that the local autocorrelations are time-varying and have a “V” shape during 1910–1960. For the S&P 500 index, we conclude that the returns satisfy the efficient-market hypothesis whereas the magnitudes of returns show significant local autocorrelations.

UR - http://www.scopus.com/inward/record.url?scp=84928264490&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84928264490&partnerID=8YFLogxK

U2 - 10.1080/07350015.2014.948177

DO - 10.1080/07350015.2014.948177

M3 - Article

AN - SCOPUS:84928264490

VL - 33

SP - 296

EP - 306

JO - Journal of Business and Economic Statistics

JF - Journal of Business and Economic Statistics

SN - 0735-0015

IS - 2

ER -