A bounded model of time variation in trend inflation, NAIRU and the Phillips curve

Joshua C. C. Chan, Gary Koop, Simon M. Potter

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

In this paper, we develop a bivariate unobserved components model for in‡ation and unemployment. The unobserved components
are trend in‡ation and the non-accelerating in‡ation rate of unemployment (NAIRU). Our model also incorporates a time-varying Phillips curve and time-varying in‡ation persistence. What sets this paper apart from the existing literature is that we do not use unbounded random walks for the unobserved components, but rather use bounded random walks. For instance, NAIRU is assumed to evolve within bounds. Our empirical work shows the importance of bounding. We …nd that our bounded bivariate model forecasts better than many alternatives, including a version of our model with unbounded unobserved components. Our model also yields sensible estimates
of trend in‡ation, NAIRU, in‡ation persistence and the slope of the Phillips curve.
LanguageEnglish
Pages551-565
Number of pages5
JournalJournal of Applied Econometrics
Volume31
Issue number3
Early online date15 Jan 2015
DOIs
Publication statusPublished - 1 Apr 2016

Fingerprint

Phillips curve
inflation
unemployment
trend
persistence
time
Unemployment
Inflation
Time variation
Persistence
Unobserved components
Time-varying
Random walk

Keywords

  • trend in‡ation
  • non-linear state space model
  • natural rate of unemployment
  • in‡ation targeting
  • Bayesian

Cite this

@article{8fb23a4b6e204d5ebff49f4b8f744361,
title = "A bounded model of time variation in trend inflation, NAIRU and the Phillips curve",
abstract = "In this paper, we develop a bivariate unobserved components model for in‡ation and unemployment. The unobserved componentsare trend in‡ation and the non-accelerating in‡ation rate of unemployment (NAIRU). Our model also incorporates a time-varying Phillips curve and time-varying in‡ation persistence. What sets this paper apart from the existing literature is that we do not use unbounded random walks for the unobserved components, but rather use bounded random walks. For instance, NAIRU is assumed to evolve within bounds. Our empirical work shows the importance of bounding. We …nd that our bounded bivariate model forecasts better than many alternatives, including a version of our model with unbounded unobserved components. Our model also yields sensible estimatesof trend in‡ation, NAIRU, in‡ation persistence and the slope of the Phillips curve.",
keywords = "trend in‡ation, non-linear state space model, natural rate of unemployment, in‡ation targeting, Bayesian",
author = "Chan, {Joshua C. C.} and Gary Koop and Potter, {Simon M.}",
year = "2016",
month = "4",
day = "1",
doi = "10.1002/jae.2442",
language = "English",
volume = "31",
pages = "551--565",
journal = "Journal of Applied Econometrics",
issn = "0883-7252",
number = "3",

}

A bounded model of time variation in trend inflation, NAIRU and the Phillips curve. / Chan, Joshua C. C.; Koop, Gary; Potter, Simon M.

In: Journal of Applied Econometrics, Vol. 31, No. 3, 01.04.2016, p. 551-565.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A bounded model of time variation in trend inflation, NAIRU and the Phillips curve

AU - Chan, Joshua C. C.

AU - Koop, Gary

AU - Potter, Simon M.

PY - 2016/4/1

Y1 - 2016/4/1

N2 - In this paper, we develop a bivariate unobserved components model for in‡ation and unemployment. The unobserved componentsare trend in‡ation and the non-accelerating in‡ation rate of unemployment (NAIRU). Our model also incorporates a time-varying Phillips curve and time-varying in‡ation persistence. What sets this paper apart from the existing literature is that we do not use unbounded random walks for the unobserved components, but rather use bounded random walks. For instance, NAIRU is assumed to evolve within bounds. Our empirical work shows the importance of bounding. We …nd that our bounded bivariate model forecasts better than many alternatives, including a version of our model with unbounded unobserved components. Our model also yields sensible estimatesof trend in‡ation, NAIRU, in‡ation persistence and the slope of the Phillips curve.

AB - In this paper, we develop a bivariate unobserved components model for in‡ation and unemployment. The unobserved componentsare trend in‡ation and the non-accelerating in‡ation rate of unemployment (NAIRU). Our model also incorporates a time-varying Phillips curve and time-varying in‡ation persistence. What sets this paper apart from the existing literature is that we do not use unbounded random walks for the unobserved components, but rather use bounded random walks. For instance, NAIRU is assumed to evolve within bounds. Our empirical work shows the importance of bounding. We …nd that our bounded bivariate model forecasts better than many alternatives, including a version of our model with unbounded unobserved components. Our model also yields sensible estimatesof trend in‡ation, NAIRU, in‡ation persistence and the slope of the Phillips curve.

KW - trend in‡ation

KW - non-linear state space model

KW - natural rate of unemployment

KW - in‡ation targeting

KW - Bayesian

U2 - 10.1002/jae.2442

DO - 10.1002/jae.2442

M3 - Article

VL - 31

SP - 551

EP - 565

JO - Journal of Applied Econometrics

T2 - Journal of Applied Econometrics

JF - Journal of Applied Econometrics

SN - 0883-7252

IS - 3

ER -