Testing for multiple-period predictability between serially dependent time series

Research output: Contribution to journalArticleResearchpeer-review

Abstract

This paper reports the results of a simulation study that considers the finite-sample performances of a range of approaches for testing multiple-period predictability between two potentially serially correlated time series. In many empirically relevant situations, but not all, most of the test statistics considered are significantly oversized. In contrast, both an analytical approach proposed in this paper and a bootstrap are found to have accurate empirical sizes. In a small number of cases, the bootstrap is found to have a superior power. The test procedures considered are applied to an empirical analysis of the predictive power of a Phillips curve model during the 'great moderation' period, which illustrates the practical importance of using test statistics with accurate empirical sizes.

LanguageEnglish
Pages587-597
Number of pages11
JournalInternational Journal of Forecasting
Volume31
Issue number3
DOIs
Publication statusPublished - 1 Jul 2015

Fingerprint

Test statistic
Bootstrap
Testing
Predictability
Great moderation
Finite sample
Predictive power
Simulation study
Empirical analysis
Phillips curve

Cite this

@article{0c5ef86790b64bec905007a232386875,
title = "Testing for multiple-period predictability between serially dependent time series",
abstract = "This paper reports the results of a simulation study that considers the finite-sample performances of a range of approaches for testing multiple-period predictability between two potentially serially correlated time series. In many empirically relevant situations, but not all, most of the test statistics considered are significantly oversized. In contrast, both an analytical approach proposed in this paper and a bootstrap are found to have accurate empirical sizes. In a small number of cases, the bootstrap is found to have a superior power. The test procedures considered are applied to an empirical analysis of the predictive power of a Phillips curve model during the 'great moderation' period, which illustrates the practical importance of using test statistics with accurate empirical sizes.",
author = "Chris Heaton",
year = "2015",
month = "7",
day = "1",
doi = "10.1016/j.ijforecast.2014.09.004",
language = "English",
volume = "31",
pages = "587--597",
journal = "International Journal of Forecasting",
issn = "0169-2070",
publisher = "Elsevier",
number = "3",

}

Testing for multiple-period predictability between serially dependent time series. / Heaton, Chris.

In: International Journal of Forecasting, Vol. 31, No. 3, 01.07.2015, p. 587-597.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Testing for multiple-period predictability between serially dependent time series

AU - Heaton, Chris

PY - 2015/7/1

Y1 - 2015/7/1

N2 - This paper reports the results of a simulation study that considers the finite-sample performances of a range of approaches for testing multiple-period predictability between two potentially serially correlated time series. In many empirically relevant situations, but not all, most of the test statistics considered are significantly oversized. In contrast, both an analytical approach proposed in this paper and a bootstrap are found to have accurate empirical sizes. In a small number of cases, the bootstrap is found to have a superior power. The test procedures considered are applied to an empirical analysis of the predictive power of a Phillips curve model during the 'great moderation' period, which illustrates the practical importance of using test statistics with accurate empirical sizes.

AB - This paper reports the results of a simulation study that considers the finite-sample performances of a range of approaches for testing multiple-period predictability between two potentially serially correlated time series. In many empirically relevant situations, but not all, most of the test statistics considered are significantly oversized. In contrast, both an analytical approach proposed in this paper and a bootstrap are found to have accurate empirical sizes. In a small number of cases, the bootstrap is found to have a superior power. The test procedures considered are applied to an empirical analysis of the predictive power of a Phillips curve model during the 'great moderation' period, which illustrates the practical importance of using test statistics with accurate empirical sizes.

UR - http://www.scopus.com/inward/record.url?scp=84946174965&partnerID=8YFLogxK

U2 - 10.1016/j.ijforecast.2014.09.004

DO - 10.1016/j.ijforecast.2014.09.004

M3 - Article

VL - 31

SP - 587

EP - 597

JO - International Journal of Forecasting

T2 - International Journal of Forecasting

JF - International Journal of Forecasting

SN - 0169-2070

IS - 3

ER -