In Thursday’s class, I mentioned that the “advanced estimate” (or the first estimate) by the BEA for annualized growth in the fourth quarter of last year was 0.6%. [Take a look at the original BEA News Release]. Last week’s Economist has a great article on how (in)accurate these estimates are (emphasis added):
…[what] statistics…reveal is suggestive, but what they conceal is vital. America’s advance GDP figures…hide as much as they show… Fourth-quarter numbers, showing an annualised growth rate of 0.6% (or less than 0.2% in quarterly terms), suggested that America’s economy was barely growing at the end of last year.
A large fall in inventories subtracted 1.25 percentage points from fourth-quarter growth, making a far bigger dent than usual in the figures. Changes in inventories, however, are often subject to large revisions. They might well be adjusted upwards later.
The first estimate of America’s GDP is notoriously imprecise, and is probably more so during times of wrenching economic change. According to the Bureau of Economic Analysis, which computes the GDP figures, around 25% of the required source data are not available for the first estimate and only partial information (for example two out of three months’ data) is on hand for a further 30% of sources. [link]
This certainly ties in the stuff on GDP components from Chapter 2 (how and where do inventories figure into the measuring of real GDP?). It also certainly has to do with my blog-post on GDP components (now updated). In that post, I quote heavily from a post at The Street Light, and if you actually went and read the quoted post, you’d realize something else about the “advanced estimates” of the BEA:
First of all, let me give the appropriate qualifier: this is a very early estimate, and subject to substantial revision. For the fourth quarter of 2006 the advance estimate was 3.5% growth, the preliminary estimate was 2.2% growth, and the final number was 2.5%. [link]
But also, it ties into something else that Prof. Kash Mansori was saying – in the forecasting handout posted for our 1/29 class. Here’s a quote from that handout (emphasis added):
In October 2005 the Congressional Budget Office published “The CBO’s Economic Forecasting Record5,” in which they took at look at the track record of both the CBO and “Blue Chip consensus” forecasts for various macroeconomic variables. Doing a quick check on the accuracy of the Blue Chip consensus forecast for GDP growth shows that, on
average, the consensus forecast was off by 1% (in absolute value). Forecast errors were particularly large during large changes in GDP. In other words, economists are particularly bad at identifying turns in the business cycle.
Now, I’m not sure whether this average error of 1% is larger or smaller than I would have expected, compared to an average GDP growth rate of 3.1%. But I am quite sure that it’s disappointing to see that a forecast that simply extrapolated last year’s GDP growth into next year’s GDP growth would have had a slightly smaller average error. In other words, the average of our best macroeconomic models does no better at predicting GDP growth than a person who simply always guesses that next year’s GDP growth will be the same as this year’s! [link]
Here we have two clear examples of how inaccurate measures of real GDP are, and how bad economists are at identifying when we have just crossed a peak and/or a trough in the business cycle. This is not such a big deal when things are going well, but certainly when the economy is beginning to reach a trough (as it seems to be doing right now), these critiques come into the spotlight, and rightly so.
It is important to understand these problems with estimating the GDP, as well as the problems with forecasting GDP – both of which have to do with the statistical modeling techniques that are used. These tools are all we have today and, while imprecise, they do provide some insights into how the economy is doing.