Measuring business cycles with structural breaks and outliers: Applications to international data

Pierre Perron, Tatsuma Wada

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

This paper first generalizes the trend-cycle decomposition framework of Perron and Wada (2009) based on unobserved components models with innovations having a mixture of normals distribution, which is able to handle sudden level and slope changes to the trend function as well as outliers. We investigate how important are the differences in the implied trend and cycle compared to the popular decomposition based on the Hodrick and Prescott (HP) (1997) filter. Our results show important qualitative and quantitative differences in the implied cycles for both real GDP and consumption series for the G7 countries. Most of the differences can be ascribed to the fact that the HP filter does not handle well slope changes, level shifts and outliers, while our method does so. Then, we reassess how such different cycles affect some so-called "stylized facts" about the relative variability of consumption and output across countries.

Original languageEnglish
JournalResearch in Economics
DOIs
Publication statusAccepted/In press - 2015 Nov 2

Fingerprint

Structural breaks
Outliers
Business cycles
Filter
Stylized facts
Trend-cycle decomposition
Decomposition
Normal distribution
G-7 countries
Level shift
Real GDP
Unobserved components model
Innovation

Keywords

  • International business cycle
  • Non-Gaussian filter
  • Trend-cycle decomposition
  • Unobserved components model

ASJC Scopus subject areas

  • Economics and Econometrics

Cite this

@article{3817fb881923478b9934353c1fc3d0fe,
title = "Measuring business cycles with structural breaks and outliers: Applications to international data",
abstract = "This paper first generalizes the trend-cycle decomposition framework of Perron and Wada (2009) based on unobserved components models with innovations having a mixture of normals distribution, which is able to handle sudden level and slope changes to the trend function as well as outliers. We investigate how important are the differences in the implied trend and cycle compared to the popular decomposition based on the Hodrick and Prescott (HP) (1997) filter. Our results show important qualitative and quantitative differences in the implied cycles for both real GDP and consumption series for the G7 countries. Most of the differences can be ascribed to the fact that the HP filter does not handle well slope changes, level shifts and outliers, while our method does so. Then, we reassess how such different cycles affect some so-called {"}stylized facts{"} about the relative variability of consumption and output across countries.",
keywords = "International business cycle, Non-Gaussian filter, Trend-cycle decomposition, Unobserved components model",
author = "Pierre Perron and Tatsuma Wada",
year = "2015",
month = "11",
day = "2",
doi = "10.1016/j.rie.2015.12.001",
language = "English",
journal = "Research in Economics",
issn = "1090-9443",
publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - Measuring business cycles with structural breaks and outliers

T2 - Applications to international data

AU - Perron, Pierre

AU - Wada, Tatsuma

PY - 2015/11/2

Y1 - 2015/11/2

N2 - This paper first generalizes the trend-cycle decomposition framework of Perron and Wada (2009) based on unobserved components models with innovations having a mixture of normals distribution, which is able to handle sudden level and slope changes to the trend function as well as outliers. We investigate how important are the differences in the implied trend and cycle compared to the popular decomposition based on the Hodrick and Prescott (HP) (1997) filter. Our results show important qualitative and quantitative differences in the implied cycles for both real GDP and consumption series for the G7 countries. Most of the differences can be ascribed to the fact that the HP filter does not handle well slope changes, level shifts and outliers, while our method does so. Then, we reassess how such different cycles affect some so-called "stylized facts" about the relative variability of consumption and output across countries.

AB - This paper first generalizes the trend-cycle decomposition framework of Perron and Wada (2009) based on unobserved components models with innovations having a mixture of normals distribution, which is able to handle sudden level and slope changes to the trend function as well as outliers. We investigate how important are the differences in the implied trend and cycle compared to the popular decomposition based on the Hodrick and Prescott (HP) (1997) filter. Our results show important qualitative and quantitative differences in the implied cycles for both real GDP and consumption series for the G7 countries. Most of the differences can be ascribed to the fact that the HP filter does not handle well slope changes, level shifts and outliers, while our method does so. Then, we reassess how such different cycles affect some so-called "stylized facts" about the relative variability of consumption and output across countries.

KW - International business cycle

KW - Non-Gaussian filter

KW - Trend-cycle decomposition

KW - Unobserved components model

UR - http://www.scopus.com/inward/record.url?scp=84952361080&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84952361080&partnerID=8YFLogxK

U2 - 10.1016/j.rie.2015.12.001

DO - 10.1016/j.rie.2015.12.001

M3 - Article

AN - SCOPUS:84952361080

JO - Research in Economics

JF - Research in Economics

SN - 1090-9443

ER -