Giorgio Canarella and Stephen M. Miller both (Economics and Center for Business and Economic Research) published their paper, in Studies in Nonlinear Dynamics and Econometrics with coauthors Heni Boubaker, Rabat Business School, and Rangan Gupta, University of Pretoria. This paper reports the results of applying several long-memory models to the historical monthly U.S. inflation rate series and analyzes their out-of-sample forecasting performance over different horizons. The paper finds that the time-varying approach to estimating inflation persistence outperforms the models that assume a constant long-memory process. In addition, the paper examines the link between inflation persistence and exchange rate regimes. The results support the hypothesis that floating exchange rates associate with increased inflation persistence. This finding, however, is less pronounced during the era of the Great Moderation and the Federal Reserve System’s commitment to inflation targeting.
