For immediate release: December 29, 2006
Careless Use of Preliminary Economic Data Misleading, Says Dallas Fed’s Economic Letter
DALLAS—The careless use of preliminary economic data by monetary policymakers and others could lead to poor decisions, according to the December issue of the Federal Reserve Bank of Dallas’ Economic Letter.
In “Through a Glass, Darkly: How Data Revisions Complicate Monetary Policy,” vice president and senior economist Evan F. Koenig notes that many early economic statistical releases are inaccurate. Scores of analysts use the government’s initial estimates in their forecasts, which can lead to trouble, according to Koenig.
“Seriously misleading conclusions and subpar forecasting results are likely when analysts and policymakers treat heavily revised and first-release data as if they are interchangeable,” Koenig writes.
As an example, he cites the use of profit-margin data by analysts to predict inflation. While revised profit-margin estimates may help forecasters understand inflation after the fact, the data available in real time show no correlation to inflation.
Koenig also argues that annual, comprehensive and benchmark revisions to government statistical estimates have more impact than seasonal and monthly revisions.
“The revisions in a month or two immediately after the government’s initial releases and revisions due to reestimation of seasonal factors contribute relatively little new information,” Koenig writes. An implication is that it may easily be a year or more after their initial release before government estimates can be taken at face value.
The December 2006 issue of Economic Letter can be found at www.dallasfed.org.
Phone: (214) 922-5307