Tracing the Effects of Real-Time Data Revisions in Exclusions-from-Core Measures of Inflation

Through the use of conditional, local nonparametric estimation, this paper tracks the effects that data revisions have on core and total inflation as measured by Personal Consumption Expenditures and the Consumer Price Index. The purpose of this paper is two-fold. The first is to investigate whether data revisions of PCE does have an impact on total inflation in regards to the exclusions-from-core measures of inflation over a five-period in-sample forecast horizon of one, two, four, eight, and twelve quarts. Previous work has found that the effect of data revisions is difficult to determine when a recursive framework is used since both new data as well as revised data is used in each new vintage of real-time data. Using the same techniques, the second purpose is to examine whether the Consumer Price Index is better able to capture the overall trend of inflation, which is one of the uses of core inflation that could also have policy ramifications as well.