Template-type: ReDIF-Paper 1.0
Author-Name: Canepa, Alessandra 
Author-Email: alessandra.canepa@unito.it 
Author-Workplace-Name: University of Turin
Author-Workplace-Homepage: http://www.est.unito.it/
Title: Ination Dynamics and Time-Varying Persistence: The Importance of the Uncertainty Channel.
Abstract: In this article, we employ a time-varying GARCH-type speci?cation to model in?ation and in-
vestigate the behaviour of its persistence. Speci?cally, by modelling the in?ation series as AR(1)-
APARCH(1,1)-in-mean-level process with breaks, we show that persistence is transmitted from the
conditional variance to the conditional mean. Hence, by studying the conditional mean/variance
independently, one will obtain a biased estimate of the true degree of persistence. Accordingly, we
propose a new measure of time-varying persistence, which not only distinguishes between changes in
the dynamics of in?ation and its volatility but also allows for feedback between the two variables.
Analysing the in?ation series for a number of countries, we ?nd evidence that in?ation uncertainty
plays an important role in shaping expectations, and a higher level of uncertainty increases in?ation
persistence. We also consider a number of unit root tests and present the results of a Monte Carlo
experiment to investigate the size and power properties of these tests in the presence of breaks in the
mean and the variance equation of an AR(1)-APARCH(1,1)-in-mean-level data generating process.
The Monte Carlo experiment reveals that if the model is misspeci?ed, then commonly used unit root
tests will misclassify in?ation as a nonstationary, rather than a stationary process.
Length: pages 32
Creation-Date: 2022-09
File-URL: https://www.est.unito.it/do/home.pl/Download?doc=/allegati/wp2022dip/wp_11_2022.pdf
File-Format: Application/PDF
Handle: RePEc:uto:dipeco:202211