### Abstract

integrated or near integrated process but this implication is strongly rejected

using United States data. However, if we assume that inflation is a stationary

process around a shifting mean (due to changes in monetary policy) then any

estimate of long-run relationships will suffer from a ‘small-sample’ problem

as there are too few inflation ‘regimes’ where the data are stationary. We offer

a ‘4-stage’ solution to this problem and applying this solution to United States

data we estimate a significant negative sloping non-linear long-run Phillips

curve.

Original language | English |
---|---|

Place of Publication | Dundee |

Publisher | University of Dundee, Department of Economic Studies |

Number of pages | 31 |

Publication status | Published - 27 Feb 2016 |

### Publication series

Name | Dundee Discussion Papers in Economics |
---|---|

Publisher | University of Dundee, Department of Economic Studies |

No. | 294 |

ISSN (Print) | 1473-236X |

### Fingerprint

### Keywords

- Phillips curve
- Inflation
- Structural breaks
- Non-stationary data
- JEL Classification

### Cite this

*Breaks and the Statistical Process of Inflation: The Case of the 'Modern' Phillips Curve*. (Dundee Discussion Papers in Economics; No. 294). Dundee: University of Dundee, Department of Economic Studies .

}

**Breaks and the Statistical Process of Inflation : The Case of the 'Modern' Phillips Curve.** / Russell, Bill (Lead / Corresponding author); Rambaccussing, Dooruj.

Research output: Working paper

TY - UNPB

T1 - Breaks and the Statistical Process of Inflation

T2 - The Case of the 'Modern' Phillips Curve

AU - Russell, Bill

AU - Rambaccussing, Dooruj

N1 - No funding info

PY - 2016/2/27

Y1 - 2016/2/27

N2 - ‘Modern’ theories of the Phillips curve inadvertently imply that inflation is anintegrated or near integrated process but this implication is strongly rejectedusing United States data. However, if we assume that inflation is a stationaryprocess around a shifting mean (due to changes in monetary policy) then anyestimate of long-run relationships will suffer from a ‘small-sample’ problemas there are too few inflation ‘regimes’ where the data are stationary. We offera ‘4-stage’ solution to this problem and applying this solution to United Statesdata we estimate a significant negative sloping non-linear long-run Phillipscurve.

AB - ‘Modern’ theories of the Phillips curve inadvertently imply that inflation is anintegrated or near integrated process but this implication is strongly rejectedusing United States data. However, if we assume that inflation is a stationaryprocess around a shifting mean (due to changes in monetary policy) then anyestimate of long-run relationships will suffer from a ‘small-sample’ problemas there are too few inflation ‘regimes’ where the data are stationary. We offera ‘4-stage’ solution to this problem and applying this solution to United Statesdata we estimate a significant negative sloping non-linear long-run Phillipscurve.

KW - Phillips curve

KW - Inflation

KW - Structural breaks

KW - Non-stationary data

KW - JEL Classification

UR - https://www.dundee.ac.uk/business/research/discussionpapersseries/

M3 - Working paper

T3 - Dundee Discussion Papers in Economics

BT - Breaks and the Statistical Process of Inflation

PB - University of Dundee, Department of Economic Studies

CY - Dundee

ER -