Asymptotics for LS, GLS, and feasible GLS statistics in an AR(1) model with conditional heteroskedasticity

Donald W.K. Andrews, Patrik Guggenberger

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

We consider a first-order autoregressive model with conditionally heteroskedastic innovations. The asymptotic distributions of least squares (LS), infeasible generalized least squares (GLS), and feasible GLS estimators and t statistics are determined. The GLS procedures allow for misspecification of the form of the conditional heteroskedasticity and, hence, are referred to as quasi-GLS procedures. The asymptotic results are established for drifting sequences of the autoregressive parameter ρn and the distribution of the time series of innovations. In particular, we consider the full range of cases in which ρn satisfies n(1- ρn)→∞ and n(1- ρn)→ h1∈[0,∞) as n→∞, where n is the sample size. Results of this type are needed to establish the uniform asymptotic properties of the LS and quasi-GLS statistics.

Original languageEnglish (US)
Pages (from-to)196-210
Number of pages15
JournalJournal of Econometrics
Volume169
Issue number2
DOIs
StatePublished - Aug 1 2012

Fingerprint

Conditional Heteroskedasticity
Generalized Least Squares
Least Squares
Innovation
Statistics
Time series
Generalized Least Squares Estimator
Uniform Asymptotics
Misspecification
Autoregressive Model
Model
Asymptotic distribution
Asymptotic Properties
Sample Size
First-order
Conditional heteroskedasticity
Least squares
Generalized least squares
Heteroskedasticity
Range of data

All Science Journal Classification (ASJC) codes

  • Economics and Econometrics

Cite this

@article{f4282d7d42de4d868f3f52476d3c7adf,
title = "Asymptotics for LS, GLS, and feasible GLS statistics in an AR(1) model with conditional heteroskedasticity",
abstract = "We consider a first-order autoregressive model with conditionally heteroskedastic innovations. The asymptotic distributions of least squares (LS), infeasible generalized least squares (GLS), and feasible GLS estimators and t statistics are determined. The GLS procedures allow for misspecification of the form of the conditional heteroskedasticity and, hence, are referred to as quasi-GLS procedures. The asymptotic results are established for drifting sequences of the autoregressive parameter ρn and the distribution of the time series of innovations. In particular, we consider the full range of cases in which ρn satisfies n(1- ρn)→∞ and n(1- ρn)→ h1∈[0,∞) as n→∞, where n is the sample size. Results of this type are needed to establish the uniform asymptotic properties of the LS and quasi-GLS statistics.",
author = "Andrews, {Donald W.K.} and Patrik Guggenberger",
year = "2012",
month = "8",
day = "1",
doi = "10.1016/j.jeconom.2012.01.017",
language = "English (US)",
volume = "169",
pages = "196--210",
journal = "Journal of Econometrics",
issn = "0304-4076",
publisher = "Elsevier BV",
number = "2",

}

Asymptotics for LS, GLS, and feasible GLS statistics in an AR(1) model with conditional heteroskedasticity. / Andrews, Donald W.K.; Guggenberger, Patrik.

In: Journal of Econometrics, Vol. 169, No. 2, 01.08.2012, p. 196-210.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Asymptotics for LS, GLS, and feasible GLS statistics in an AR(1) model with conditional heteroskedasticity

AU - Andrews, Donald W.K.

AU - Guggenberger, Patrik

PY - 2012/8/1

Y1 - 2012/8/1

N2 - We consider a first-order autoregressive model with conditionally heteroskedastic innovations. The asymptotic distributions of least squares (LS), infeasible generalized least squares (GLS), and feasible GLS estimators and t statistics are determined. The GLS procedures allow for misspecification of the form of the conditional heteroskedasticity and, hence, are referred to as quasi-GLS procedures. The asymptotic results are established for drifting sequences of the autoregressive parameter ρn and the distribution of the time series of innovations. In particular, we consider the full range of cases in which ρn satisfies n(1- ρn)→∞ and n(1- ρn)→ h1∈[0,∞) as n→∞, where n is the sample size. Results of this type are needed to establish the uniform asymptotic properties of the LS and quasi-GLS statistics.

AB - We consider a first-order autoregressive model with conditionally heteroskedastic innovations. The asymptotic distributions of least squares (LS), infeasible generalized least squares (GLS), and feasible GLS estimators and t statistics are determined. The GLS procedures allow for misspecification of the form of the conditional heteroskedasticity and, hence, are referred to as quasi-GLS procedures. The asymptotic results are established for drifting sequences of the autoregressive parameter ρn and the distribution of the time series of innovations. In particular, we consider the full range of cases in which ρn satisfies n(1- ρn)→∞ and n(1- ρn)→ h1∈[0,∞) as n→∞, where n is the sample size. Results of this type are needed to establish the uniform asymptotic properties of the LS and quasi-GLS statistics.

UR - http://www.scopus.com/inward/record.url?scp=84862701351&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84862701351&partnerID=8YFLogxK

U2 - 10.1016/j.jeconom.2012.01.017

DO - 10.1016/j.jeconom.2012.01.017

M3 - Article

AN - SCOPUS:84862701351

VL - 169

SP - 196

EP - 210

JO - Journal of Econometrics

JF - Journal of Econometrics

SN - 0304-4076

IS - 2

ER -