News, Noise, and Estimates of the 'True' Unobserved State of the Economy (September 15, 2009)

摘要

For analysts of economic fluctuations, estimating the true state of the economy from imperfectly measured official statistics is an ever-present problem. Since no one statistic is a perfect gauge of the state of the economy, taking some type of weighted average of multiple imperfectly measured statistics seems sensible. Examples include composite indexes of coincident indicators, and averages of the different measures of aggregate output. For the case of U.S. output growth, the NBER Business Cycle Dating Committees announcement of a peak in December 2007 noted marked differences between two different estimates, GDP and GDI, and essentially decided to give each estimate some implicit weight: in examining the behavior of domestic production, we consider not only the conventional product-side GDP estimates, but also the conceptually equivalent income-side GDI estimates. The differences between these two sets of estimates were particularly evident in 2007 and 2008. In this paper, we take the state of the economy to mean the growth rate of output as traditionally defined in the U.S. National Income and Product Accounts (NIPAs), and work out methodologies for reconciling differences between these two estimates.