Consistency of Kernel Estimators of Heteroscedastic and Autocorrelated Covariance Matrices

R.M. de Jong, J. Davidson

Research output: Working paperDiscussion paperOther research output

237 Downloads (Pure)

Abstract

Conditions are derived for the consistency of kernel estimators of the covariance matrix of a sum of vectors of dependent heterogeneous random variables, which match those of the currently best-known conditions for the central limit theorem, as required for a unified theory of asymptotic inference. These include finite moments of order no more than 2 + for > 0, trending variances, and variables which are near-epoch dependent on a mixing process, but not necessarily mixing. The results are also proved for the case of sample-dependent bandwidths.
Original languageEnglish
Place of PublicationTilburg
PublisherEconometrics
Number of pages21
Volume1996-52
Publication statusPublished - 1996

Publication series

NameCentER Discussion Paper
Volume1996-52

Fingerprint

Kernel Estimator
Covariance matrix
Dependent
Asymptotic Inference
Mixing Processes
Central limit theorem
Random variable
Bandwidth
Moment

Keywords

  • kernel estimator
  • matrices

Cite this

de Jong, R. M., & Davidson, J. (1996). Consistency of Kernel Estimators of Heteroscedastic and Autocorrelated Covariance Matrices. (CentER Discussion Paper; Vol. 1996-52). Tilburg: Econometrics.
de Jong, R.M. ; Davidson, J. / Consistency of Kernel Estimators of Heteroscedastic and Autocorrelated Covariance Matrices. Tilburg : Econometrics, 1996. (CentER Discussion Paper).
@techreport{482efe9537384a9fb833eb728c9119f9,
title = "Consistency of Kernel Estimators of Heteroscedastic and Autocorrelated Covariance Matrices",
abstract = "Conditions are derived for the consistency of kernel estimators of the covariance matrix of a sum of vectors of dependent heterogeneous random variables, which match those of the currently best-known conditions for the central limit theorem, as required for a unified theory of asymptotic inference. These include finite moments of order no more than 2 + for > 0, trending variances, and variables which are near-epoch dependent on a mixing process, but not necessarily mixing. The results are also proved for the case of sample-dependent bandwidths.",
keywords = "kernel estimator, matrices",
author = "{de Jong}, R.M. and J. Davidson",
note = "Pagination: 21",
year = "1996",
language = "English",
volume = "1996-52",
series = "CentER Discussion Paper",
publisher = "Econometrics",
type = "WorkingPaper",
institution = "Econometrics",

}

de Jong, RM & Davidson, J 1996 'Consistency of Kernel Estimators of Heteroscedastic and Autocorrelated Covariance Matrices' CentER Discussion Paper, vol. 1996-52, Econometrics, Tilburg.

Consistency of Kernel Estimators of Heteroscedastic and Autocorrelated Covariance Matrices. / de Jong, R.M.; Davidson, J.

Tilburg : Econometrics, 1996. (CentER Discussion Paper; Vol. 1996-52).

Research output: Working paperDiscussion paperOther research output

TY - UNPB

T1 - Consistency of Kernel Estimators of Heteroscedastic and Autocorrelated Covariance Matrices

AU - de Jong, R.M.

AU - Davidson, J.

N1 - Pagination: 21

PY - 1996

Y1 - 1996

N2 - Conditions are derived for the consistency of kernel estimators of the covariance matrix of a sum of vectors of dependent heterogeneous random variables, which match those of the currently best-known conditions for the central limit theorem, as required for a unified theory of asymptotic inference. These include finite moments of order no more than 2 + for > 0, trending variances, and variables which are near-epoch dependent on a mixing process, but not necessarily mixing. The results are also proved for the case of sample-dependent bandwidths.

AB - Conditions are derived for the consistency of kernel estimators of the covariance matrix of a sum of vectors of dependent heterogeneous random variables, which match those of the currently best-known conditions for the central limit theorem, as required for a unified theory of asymptotic inference. These include finite moments of order no more than 2 + for > 0, trending variances, and variables which are near-epoch dependent on a mixing process, but not necessarily mixing. The results are also proved for the case of sample-dependent bandwidths.

KW - kernel estimator

KW - matrices

M3 - Discussion paper

VL - 1996-52

T3 - CentER Discussion Paper

BT - Consistency of Kernel Estimators of Heteroscedastic and Autocorrelated Covariance Matrices

PB - Econometrics

CY - Tilburg

ER -

de Jong RM, Davidson J. Consistency of Kernel Estimators of Heteroscedastic and Autocorrelated Covariance Matrices. Tilburg: Econometrics. 1996. (CentER Discussion Paper).