Measuring Core Inflation in Australia with Disaggregate Ensembles

Shaun P. Vahey, Melbourne Business School
Francesco Ravazzolo, Norges Bank

Abstract

We construct ensemble predictives for inflation in Australia based on the out of sample forecast performance of many component models, where each component model uses a particular disaggregate inflation series. Following Ravazzolo and Vahey (2009), the disaggregate ensemble can be interpreted as a measure of core inflation. We demonstrate that the ensemble forecast densities for measured inflation using disaggregate information by city and by sector are well calibrated. The resulting density forecasts outperform considerably those from a benchmark autoregressive model. And the point forecasts are competitive. From a structural perspective, the disaggregate ensemble core inflation measure suggests that the more traditional weighted median and trimmed mean measures periodically understate and overstate inflationary pressures in Australia.