655

Why forecasting goes wrong so often

Why forecasting goes wrong so often
Comment E-mail Print Share
First Published: Tue, Jul 08 2008. 09 52 PM IST
Updated: Tue, Jul 08 2008. 09 52 PM IST
It’s yet another bad season for economic forecasters. The problem isn’t merely seasonal, though. Too much of the profession’s standard operating procedure naturally leads to missing the truly disruptive turning points.
Forecasts have changed since December. Then the average prediction of 2008 US gross domestic product was 2.1%, according to Consensus Economics. In June, that had fallen to 1.5%. The drop in UK growth projections has been less severe, from 1.9% to 1.7%. The 2008 inflation forecast for the euro zone has moved from 2.3% to 3.3%. In the US the jump is from 2.6% to 4%. Don’t even ask about oil price forecasts.
As anyone doing a tarot reading should suspect, accuracy isn’t the real goal of fortune-telling.
The appeal comes from claiming some knowledge, however imperfect, of the unknowable. Still, economists have some special problems. To start, there is groupthink. It’s much easier to be wrong with the crowd than to take the risk of being wrong all alone. The forecasters mostly use similar models, so they naturally come out with similar results.
Their main flaw, though, is that they predict the past rather than the future. The models are supposed to identify relevant historical patterns, which are too often assumed to continue indefinitely.
Unfortunately, the past is an imperfect guide. All in all, it might just make sense to replace the forecasters’ sophisticated models with a nice tarot deck.
Comment E-mail Print Share
First Published: Tue, Jul 08 2008. 09 52 PM IST
blog comments powered by Disqus
  • Wed, Apr 16 2014. 06 11 PM
  • Wed, Apr 09 2014. 05 19 PM
ALSO READ close

Making sense of China’s GDP slowdown

Subscribe |  Contact Us  |  mint Code  |  Privacy policy  |  Terms of Use  |  Advertising  |  Mint Apps  |  About HT Media  |  Jobs
Contact Us
Copyright © 2014 HT Media All Rights Reserved