Estimating U.S. output growth with vintage data in a state-space framework

Abstract

This study uses a state-space model to estimate the "true" unobserved measure of total output in the U.S. economy. The analysis uses the entire history (i.e., all vintages) of selected real-time data series to compute revisions and corresponding statistics for those series. The revision statistics, along with the most recent data vintage, are used in a state-space model to extract filtered estimates of the "true" series. Under certain assumptions, Monte Carlo simulations suggest this framework can improve published estimates by as much as 30 percent, lasting an average of 11 periods. Realtime experiments using a measure of real gross domestic product show improvement closer to 10 percent, lasting for 1 to 2 quarters. © 2009, The Federal Reserve Bank of St. Louis.