Structural changes in inflation dynamics: Multiple breaks at different dates for different parameters

Research output: Contribution to journalArticlepeer-review

10 Citations (Scopus)


I consider complicated patterns of structural breaks in postwar quarterly US inflation rates based on the CPI and the GDP deflator over the period from 1953:Q1 to 2013:Q4. Bayesian model selection procedures suggest that the two inflation measures had distinct structural changes in different parameters as well as at different dates. CPI inflation experienced a dramatic drop in persistence around the early 1980s, but GDP deflator inflation remains persistent throughout the postwar sample period. The residual variance for both inflation measures switched from a low volatility regime to a high volatility regime in the early 1970s, but returned to another low volatility regime at different dates: the early 1980s for GDP deflator inflation and the early 1990s for CPI inflation. The residual variance for CPI inflation has increased again since the early 2000s, while GDP deflator inflation has remained less volatile. I do not find evidence of a structural shift in the unconditional mean of either measure of inflation. When reviewing the recent literature, considerable controversy exists over the structural break in inflation persistence around the early 1980s but this appears to be dependent on the measures of inflation, as highlighted by the empirical findings in this paper.

Original languageEnglish
Pages (from-to)211-231
Number of pages21
JournalStudies in Nonlinear Dynamics and Econometrics
Issue number3
Publication statusPublished - 2016 Jun 1
Externally publishedYes

Bibliographical note

Publisher Copyright:
© 2016 by De Gruyter.


  • Bayesian analysis
  • inflation dynamics
  • multiple-group changepoint
  • persistence
  • structural breaks
  • UC-SV model

ASJC Scopus subject areas

  • Analysis
  • Social Sciences (miscellaneous)
  • Economics and Econometrics


Dive into the research topics of 'Structural changes in inflation dynamics: Multiple breaks at different dates for different parameters'. Together they form a unique fingerprint.

Cite this