Tracking real-time data revisions in inflation persistence

Regarding the forecasting of real-time data, it is assumed that the third quarter release produces the best forecasts since it includes data from new and revised sources, which this paper finds is not necessarily the case. There seems to be a benchmark effect when estimating the local nonparametric regressions and the forecasts of real-time PCE and core PCE when examining the four benchmark periods beginning in 1996:Q1, 1999:Q4, 2003:Q4, and 2009:Q3. There is a benchmark effect with respect to the estimated local nonparametric slopes with the demarcation being at the 2003:Q4 benchmark, which is also the demarcation for the forecasting results. For the benchmark revisions periods of 1996:Q1 and 1999:Q4, the second quarter real-time data releases produce the smaller RMSE and for the benchmark revisions of 2003:Q4 and 2009:Q3, the third quarter real-time data releases produce forecasts with smaller RMSE approximately 58% and 60% of the time, respectively.Abbreviations: PCE, Personal Consumption Expenditures; KWLS, Kernel Weighted Least Squares; "V_" as a prefix stand for vintage, i.e. V_2003:Q4 is vintage 2003:Q4, which means that the data sample ends in 2003: Q3; IRSC, integrated residual squares criterion; NPISH, Non-Profit Institutions Serving Households; SNA, System of Accounts; RMSE, Root Mean Square Error; MAE, Mean Absolute Error; NAICS, North American Industry Classification System; SIC, Standard Industrial Classification; ARSC, Average Residual Squares Criterion; I-O, Input – Output; EIA, Energy Information Administration; ATM, Automated Teller Machines; BEA, Bureau of Economic Analysis; SNA, System of Accounts