A Note on the Efficient Estimation of Inflation in Brazil

Abstract

This paper investigates the use of trimmed-mean estimators and time-series averaging as techniques for improving the signal-to-noise ratio in high-frequency price data. We show that trimmed-mean estimators substantially increase the efficiency of the aggregate estimator compared to the more standard mean-measures. In this way, these estimators also reduce a central bank's need to time-series average the monthly inflation estimates which greatly improves the timeliness of the inflation statistic. In the case of Brazil, we find that asymmetrically trimming 24 percent from the tails of the price-change distribution reduces the RMSE of the monthly inflation statistic as a measure of the inflation trend by 23 percent, making it as accurate as the 3-month average growth rate of the mean retail price measure. We also demonstrate that a 3-month lagged moving average of the optimal (asymmetrically) trimmed mean is as efficient an estimator of the 24-month centered moving-average retail price growth trend as the mean inflation rate averaged over any horizon.