Publications and Research

The author provides a statistical evaluation of various measures of core inflation for Canada. The criteria used to evaluate the measures are lack of bias, low variability relative to total CPI inflation, and ability to forecast actual and trend total CPI inflation. The author uses the same methodology as Hogan, Johnson, and Laflèche (2001) and thus provides updated empirical results. The findings are that most traditional measures of core inflation are unbiased and all continue to be less volatile than total inflation. They nevertheless display some volatility and have limited predictive ability. Overall, CPIW seems to have a slight advantage over the other measures, but the differences across measures are not large. (CPIW uses all components of total CPI but adjusts the weight of each component by a factor that is inversely proportional to the component's variability.) Compared with the results of Hogan, Johnson, and Laflèche, CPIW's relative performance has improved. The distribution of price changes for 54 CPI subcomponents is also examined, and substantial increases in both the skewness and kurtosis of this distribution since 1998 are found.