Fixler, Nalewaik discuss GDP, GDI, and "true" state

Survey of Current Business, August, 2005

Which is a better indicator of the "true" state of the economy: Gross domestic product (GDP) or gross domestic income (GDI)? The best estimate is perhaps a weighted average of the two, but that raises the issue of how to weight each measure.

Dennis Fixler, Chief Statistician at the Bureau of Economic Analysis (BEA), and Jeremy Nalewaik, a BEA economist, discussed their recent study of this topic last month at the National Bureau of Economic Research's Summer Institute 2005 in a workshop on productivity and macroeconomics.

In their study, the authors relaxed the assumption that the difference between the true state of the economy and both GDP and GDI is pure "noise" meaning that the two measures are not correlated with information about the economy's true state. Under this assumption, the measure with the smallest variance is given greater weight when calculating an average.

The authors explored the possibility that the difference could instead be "news" meaning pure information about the true state of the economy. The study suggests that under the news assumption, the measure with the greatest variance should be given additional weight because it is assumed to contain more information about the true state of the economy.

The authors concluded that the news assumption is closer to reality. Therefore, GDP (which has greater variance than GDI) should be accorded greater weight.

The study's working paper is available on BEA's Web site at <www.bea.gov>, by clicking on "Papers and Working Papers."