A hypothesis test using bias-adjusted AR estimators for classifying time series in small samples

Research output: Contribution to journalArticleResearchpeer-review

Abstract

A new test of hypothesis for classifying stationary time series based on the bias-adjusted estimators of the fitted autoregressive model is proposed. It is shown theoretically that the proposed test has desirable properties. Simulation results show that when time series are short, the size and power estimates of the proposed test are reasonably good, and thus this test is reliable in discriminating between short-length time series. As the length of the time series increases, the performance of the proposed test improves, but the benefit of bias-adjustment reduces. The proposed hypothesis test is applied to two real data sets: the annual real GDP per capita of six European countries, and quarterly real GDP per capita of five European countries. The application results demonstrate that the proposed test displays reasonably good performance in classifying relatively short time series.
Original languageEnglish
Pages (from-to)32 - 49
Number of pages18
JournalComputational Statistics and Data Analysis
Volume60
DOIs
Publication statusPublished - 2013

Cite this

@article{5330e30ca62c49f3853f14154376e7a0,
title = "A hypothesis test using bias-adjusted AR estimators for classifying time series in small samples",
abstract = "A new test of hypothesis for classifying stationary time series based on the bias-adjusted estimators of the fitted autoregressive model is proposed. It is shown theoretically that the proposed test has desirable properties. Simulation results show that when time series are short, the size and power estimates of the proposed test are reasonably good, and thus this test is reliable in discriminating between short-length time series. As the length of the time series increases, the performance of the proposed test improves, but the benefit of bias-adjustment reduces. The proposed hypothesis test is applied to two real data sets: the annual real GDP per capita of six European countries, and quarterly real GDP per capita of five European countries. The application results demonstrate that the proposed test displays reasonably good performance in classifying relatively short time series.",
author = "Shen Liu and Maharaj, {Elizabeth Ann}",
year = "2013",
doi = "10.1016/j.csda.2012.11.014",
language = "English",
volume = "60",
pages = "32 -- 49",
journal = "Computational Statistics and Data Analysis",
issn = "0167-9473",
publisher = "Elsevier",

}

A hypothesis test using bias-adjusted AR estimators for classifying time series in small samples. / Liu, Shen; Maharaj, Elizabeth Ann.

In: Computational Statistics and Data Analysis, Vol. 60, 2013, p. 32 - 49.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - A hypothesis test using bias-adjusted AR estimators for classifying time series in small samples

AU - Liu, Shen

AU - Maharaj, Elizabeth Ann

PY - 2013

Y1 - 2013

N2 - A new test of hypothesis for classifying stationary time series based on the bias-adjusted estimators of the fitted autoregressive model is proposed. It is shown theoretically that the proposed test has desirable properties. Simulation results show that when time series are short, the size and power estimates of the proposed test are reasonably good, and thus this test is reliable in discriminating between short-length time series. As the length of the time series increases, the performance of the proposed test improves, but the benefit of bias-adjustment reduces. The proposed hypothesis test is applied to two real data sets: the annual real GDP per capita of six European countries, and quarterly real GDP per capita of five European countries. The application results demonstrate that the proposed test displays reasonably good performance in classifying relatively short time series.

AB - A new test of hypothesis for classifying stationary time series based on the bias-adjusted estimators of the fitted autoregressive model is proposed. It is shown theoretically that the proposed test has desirable properties. Simulation results show that when time series are short, the size and power estimates of the proposed test are reasonably good, and thus this test is reliable in discriminating between short-length time series. As the length of the time series increases, the performance of the proposed test improves, but the benefit of bias-adjustment reduces. The proposed hypothesis test is applied to two real data sets: the annual real GDP per capita of six European countries, and quarterly real GDP per capita of five European countries. The application results demonstrate that the proposed test displays reasonably good performance in classifying relatively short time series.

U2 - 10.1016/j.csda.2012.11.014

DO - 10.1016/j.csda.2012.11.014

M3 - Article

VL - 60

SP - 32

EP - 49

JO - Computational Statistics and Data Analysis

JF - Computational Statistics and Data Analysis

SN - 0167-9473

ER -