Saturday, August 12, 2006

Business Cycle Dating

Back in 2004, Michael Mandel of Businessweek gave me grief for saying that the 2001 recession began in late 2000, rather than at the official NBER date of March 2001. My view (and the view of the nonpartisan CEA staff) was that the data were substantially revised after the NBER committee made their call, and the March 2001 date no longer seemed right in light of the revised data. Mandel's view was that I was a Republican stooge.

Recently, a friend emailed me a paper on dating business cycles by the prominent time-series econometrician Jim Hamilton and coauthor Marcelle Chauvet. If you look at their Table 6 (page 53), you can find their estimated date for the start of the recession: September 2000.

They write:

The NBER recession dates and the model-based dates are very close, either exactly coinciding or differing by only one month. The one exception is the 2001 recession, in which the estimated probabilities started increasing in 2000, six months before the recession began as declared by the NBER. Our quarterly GDP-based full-sample inferences reported in Table 2 also suggested that this recession actually began in the fourth quarter of 2000.

I am happy to welcome Jim Hamilton into the Republican Stooge Club.

Update: Hamilton weighs in.