Do seasonal adjustments induce noncausal dynamics in inflation rates?

Alain Hecq, Sean Telg, Lenard Lieb

Research output: Contribution to JournalArticleAcademicpeer-review

Abstract

This paper investigates the effect of seasonal adjustment filters on the identification of mixed causal-noncausal autoregressive models. By means of Monte Carlo simulations, we find that standard seasonal filters induce spurious autoregressive dynamics on white noise series, a phenomenon already documented in the literature. Using a symmetric argument, we show that those filters also generate a spurious noncausal component in the seasonally adjusted series, but preserve (although amplify) the existence of causal and noncausal relationships. This result has has important implications for modelling economic time series driven by expectation relationships. We consider inflation data on the G7 countries to illustrate these results.

Original languageEnglish
Article number48
JournalEconometrics
Volume5
Issue number4
DOIs
Publication statusPublished - 1 Dec 2017
Externally publishedYes

Fingerprint

Filter
Inflation rate
Seasonal adjustment
G-7 countries
Autoregressive model
Monte Carlo simulation
Inflation
Economic modelling

Keywords

  • Inflation
  • Mixed causal-noncausal models
  • Seasonal adjustment filters

Cite this

@article{de72804b8b6e4ab295e2a69f1027f44a,
title = "Do seasonal adjustments induce noncausal dynamics in inflation rates?",
abstract = "This paper investigates the effect of seasonal adjustment filters on the identification of mixed causal-noncausal autoregressive models. By means of Monte Carlo simulations, we find that standard seasonal filters induce spurious autoregressive dynamics on white noise series, a phenomenon already documented in the literature. Using a symmetric argument, we show that those filters also generate a spurious noncausal component in the seasonally adjusted series, but preserve (although amplify) the existence of causal and noncausal relationships. This result has has important implications for modelling economic time series driven by expectation relationships. We consider inflation data on the G7 countries to illustrate these results.",
keywords = "Inflation, Mixed causal-noncausal models, Seasonal adjustment filters",
author = "Alain Hecq and Sean Telg and Lenard Lieb",
year = "2017",
month = "12",
day = "1",
doi = "10.3390/econometrics5040048",
language = "English",
volume = "5",
journal = "Econometrics",
issn = "2225-1146",
publisher = "MDPI",
number = "4",

}

Do seasonal adjustments induce noncausal dynamics in inflation rates? / Hecq, Alain; Telg, Sean; Lieb, Lenard.

In: Econometrics, Vol. 5, No. 4, 48, 01.12.2017.

Research output: Contribution to JournalArticleAcademicpeer-review

TY - JOUR

T1 - Do seasonal adjustments induce noncausal dynamics in inflation rates?

AU - Hecq, Alain

AU - Telg, Sean

AU - Lieb, Lenard

PY - 2017/12/1

Y1 - 2017/12/1

N2 - This paper investigates the effect of seasonal adjustment filters on the identification of mixed causal-noncausal autoregressive models. By means of Monte Carlo simulations, we find that standard seasonal filters induce spurious autoregressive dynamics on white noise series, a phenomenon already documented in the literature. Using a symmetric argument, we show that those filters also generate a spurious noncausal component in the seasonally adjusted series, but preserve (although amplify) the existence of causal and noncausal relationships. This result has has important implications for modelling economic time series driven by expectation relationships. We consider inflation data on the G7 countries to illustrate these results.

AB - This paper investigates the effect of seasonal adjustment filters on the identification of mixed causal-noncausal autoregressive models. By means of Monte Carlo simulations, we find that standard seasonal filters induce spurious autoregressive dynamics on white noise series, a phenomenon already documented in the literature. Using a symmetric argument, we show that those filters also generate a spurious noncausal component in the seasonally adjusted series, but preserve (although amplify) the existence of causal and noncausal relationships. This result has has important implications for modelling economic time series driven by expectation relationships. We consider inflation data on the G7 countries to illustrate these results.

KW - Inflation

KW - Mixed causal-noncausal models

KW - Seasonal adjustment filters

UR - http://www.scopus.com/inward/record.url?scp=85063837789&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063837789&partnerID=8YFLogxK

U2 - 10.3390/econometrics5040048

DO - 10.3390/econometrics5040048

M3 - Article

VL - 5

JO - Econometrics

JF - Econometrics

SN - 2225-1146

IS - 4

M1 - 48

ER -