Core Inflation and Wavelets Core Inflation as Idiosyncratic Persistence: A Wavelet Based Approach to Measuring Core Inflation Richard G. Anderson 1 Fredrik NG Andersson 2 Jane Binner 3 Thomas Elger 4 This draft: 8 May 2007 Preliminary and Incomplete: Please do not quote or cite without the authors’ permission. Abstract This paper uses stochastic index number theory to propose a measure of core inflation based on the idiosyncratic persistence in individual CPI component price series. Our index is closely related to Diewert’s (1995) neo-Edgeworthian stochastic price index. In part, we also seek to provide a core price index useful for to policymakers for measuring inflation while allowing for differing trends in underlying price series, as suggested by Woodford (2003). Our empirical work is based on the maximum overlap discrete wavelet transformation (MODWT) which, essentially, allows us to weight component prices roughly on their ratio of low to high frequency variation while simultaneously allowing for time-variation in the individual series’ DGPs. We provide preliminary results for the U.S., the U.K. and the Euro area. Much additional analysis remains to be done. Keywords: Core Inflation, Wavelet Variance JEL-codes: E31, C82 Paper prepared for the conference “Price Measurement for Monetary Policy,” Federal Reserve Bank of Dallas, May 24-25, 2007. Anderson thanks the Aston Business School, Aston University, Birmingham U.K., and the Research department of the Federal Reserve Bank of Minneapolis for their hospitality during visits at those institutions. 1 Research Division, Federal Reserve Bank of St. Louis. Contact: anderson@stls.frb.org 2 Department of Economics, Lund University, Lund, Sweden 3 Aston Business School, Aston University, Birmingham UK 4 Department of Economics, Lund University, Lund, Sweden