Structural VAR approach in estimation of core inflation and an application for Turkish economy

A monetary authority with the primary objective of price stability, needs to have a precise measure of the inflationary pressure in the economy, that it can control. However, measured infation may not be good measure of inflationary pressure for monetary policy, since this measure is reflecting relative price shocks rather than the underlying trend of inflation. As measured inflation is affected by other factors than just monetary policy, many central banks calculate ?core? inflation rate, that reflects long term price movements and excludes transitory relative price shocks.In this paper, after review of various approaches to the measurement of core inflation in the literature, an estimation of core inflation in Turkish Economy is obtained using a structural vector autoregressive (SVAR) approach proposed by Quah and Vahey (1995). This approach which is based on economic theory, tries to derive a measure of core inflation using the long-run neutrality assumption of monetary theory. In this study we have used the monthly data pertaining to 2003:01?2009:07 period; core inflation estimation derived from SVAR approach are tested to see whether it meets certain criteria which are desirable for core inflation rates. The criteria used in order to assess SVAR approach includes unbiasedness, volatility, long-run relationship and causality. The findings are that core inflation is less volatile than CPI (or headline) inflation, unbiased with respect to CPI inflation, cointegrated with the CPI inflation and better predict of CPI inflation than CPI inflation, would itself.