Estimation of the autoregressive order in the presence of measurement errors

Tai Leung, Terence CHONG, Venus LIEW, Yuanxiu ZHANG, Chi Leung, Adam WONG

Research output: Journal PublicationsJournal Article (refereed)Researchpeer-review

Abstract

Most of the existing autoregressive models presume that the observations are perfectly measured. In empirical studies, the variable of interest is unavoidably measured with various kinds of errors. Thus, misleading conclusions may be yielded due to the inconsistency of the parameter estimates caused by the measurement errors. Thus far, no theoretical result on the direction of bias of the lag order estimate is available in the literature. In this note, we will discuss the estimation an AR model in the presence of measurement errors. It is shown that the inclusion of measurement errors will drastically increase the complexity of the problem. We show that the lag lengths selected by the AIC and BIC are increasing with the sample size at a logarithmic rate.
Original languageEnglish
Pages (from-to)1-10
Number of pages10
JournalEconomics Bulletin
Volume3
Issue number12
Publication statusPublished - 1 May 2006
Externally publishedYes

Fingerprint

Measurement error
Lag
Inclusion
Empirical study
Autoregressive model
Inconsistency
Sample size

Keywords

  • Akaike Information Criterion
  • Autoregressive Process
  • Bayesian Information Criterion
  • Measurement Error

Cite this

CHONG, Tai Leung, Terence ; LIEW, Venus ; ZHANG, Yuanxiu ; WONG, Chi Leung, Adam. / Estimation of the autoregressive order in the presence of measurement errors. In: Economics Bulletin. 2006 ; Vol. 3, No. 12. pp. 1-10.
@article{7743f68ad25d458f822b200089ac67fd,
title = "Estimation of the autoregressive order in the presence of measurement errors",
abstract = "Most of the existing autoregressive models presume that the observations are perfectly measured. In empirical studies, the variable of interest is unavoidably measured with various kinds of errors. Thus, misleading conclusions may be yielded due to the inconsistency of the parameter estimates caused by the measurement errors. Thus far, no theoretical result on the direction of bias of the lag order estimate is available in the literature. In this note, we will discuss the estimation an AR model in the presence of measurement errors. It is shown that the inclusion of measurement errors will drastically increase the complexity of the problem. We show that the lag lengths selected by the AIC and BIC are increasing with the sample size at a logarithmic rate.",
keywords = "Akaike Information Criterion, Autoregressive Process, Bayesian Information Criterion, Measurement Error",
author = "CHONG, {Tai Leung, Terence} and Venus LIEW and Yuanxiu ZHANG and WONG, {Chi Leung, Adam}",
year = "2006",
month = "5",
day = "1",
language = "English",
volume = "3",
pages = "1--10",
journal = "Economics Bulletin",
issn = "1545-2921",
publisher = "Economics Bulletin",
number = "12",

}

Estimation of the autoregressive order in the presence of measurement errors. / CHONG, Tai Leung, Terence; LIEW, Venus; ZHANG, Yuanxiu; WONG, Chi Leung, Adam.

In: Economics Bulletin, Vol. 3, No. 12, 01.05.2006, p. 1-10.

Research output: Journal PublicationsJournal Article (refereed)Researchpeer-review

TY - JOUR

T1 - Estimation of the autoregressive order in the presence of measurement errors

AU - CHONG, Tai Leung, Terence

AU - LIEW, Venus

AU - ZHANG, Yuanxiu

AU - WONG, Chi Leung, Adam

PY - 2006/5/1

Y1 - 2006/5/1

N2 - Most of the existing autoregressive models presume that the observations are perfectly measured. In empirical studies, the variable of interest is unavoidably measured with various kinds of errors. Thus, misleading conclusions may be yielded due to the inconsistency of the parameter estimates caused by the measurement errors. Thus far, no theoretical result on the direction of bias of the lag order estimate is available in the literature. In this note, we will discuss the estimation an AR model in the presence of measurement errors. It is shown that the inclusion of measurement errors will drastically increase the complexity of the problem. We show that the lag lengths selected by the AIC and BIC are increasing with the sample size at a logarithmic rate.

AB - Most of the existing autoregressive models presume that the observations are perfectly measured. In empirical studies, the variable of interest is unavoidably measured with various kinds of errors. Thus, misleading conclusions may be yielded due to the inconsistency of the parameter estimates caused by the measurement errors. Thus far, no theoretical result on the direction of bias of the lag order estimate is available in the literature. In this note, we will discuss the estimation an AR model in the presence of measurement errors. It is shown that the inclusion of measurement errors will drastically increase the complexity of the problem. We show that the lag lengths selected by the AIC and BIC are increasing with the sample size at a logarithmic rate.

KW - Akaike Information Criterion

KW - Autoregressive Process

KW - Bayesian Information Criterion

KW - Measurement Error

UR - http://commons.ln.edu.hk/sw_master/4495

M3 - Journal Article (refereed)

VL - 3

SP - 1

EP - 10

JO - Economics Bulletin

JF - Economics Bulletin

SN - 1545-2921

IS - 12

ER -