Friday, December 02, 2011

New rule: if you are going to call yourself an economist, you need to know the meaning of a confidence interval

I was listening to NPR on the drive in to work this morning, and a heard a man who was labeled "an economist," say that the job growth numbers were disappointing, because measured job growth in November was 120,000, whereas the consensus forecast for job growth was 130,000.

The Bureau of Labor Statistics puts the 90 percent confidence interval of the monthly job growth estimate for the estalishment survey at 100,000.  This means the standard error of the estimate is about 56,000, so the difference between the BLS estimate and the consensus forecast number was less than .2 standard errors, which is essentially zero.  I suppose Mr. Economist would be happy had the number come in at 140,000, which would have been above expectations.

One needn't have a Ph.D. in economics to understand confidence intervals--one undergraduate course in statatistics will do the trick.  Yet week after week, I hear people who call themselves economists yammering on about small movements in numbers that are as likely noise as anything else. 


David Barker said...

It depends on how the numbers are to be used. If the Federal Reserve is deciding whether to launch QE3, or a voter is deciding whether to support an incumbent president, I agree that a blip like this is inconsequential. But if an investor is deciding whether a stock is overvalued, the difference between 120,000 and 130,000 jobs created can be important.

No matter how large the standard error, the reported job growth number still represents the expected value of job growth. Stock prices represent the discounted value of expected profit. If a company's profits depend on job growth (office building construction, for example) then 1.1% annual growth (the reported number) versus 1.2% annual growth (the expected number) represents an 8% drop in the expected growth rate, and therefore in expected profit over the next several months. (assuming that job growth is serially correlated, which it appears to be) It is not at all unreasonable to adjust a company's valuation by, say, 1% if profits over the next several months are likely to be 8% below expectations. The degree to which company profits depend on job growth varies, but for many companies the relationship is significant.

A 1% drop in value is a big deal, particularly for leveraged buyers, option traders, or anyone expecting to cash out in the near future.

It's OK to "call yourself an economist" and say that the numbers were disappointing, even though the change was within the confidence interval, as long as your advice is directed toward these kinds of investors, rather than policy makers or long-term strategic planners.

Brad Pit said...

Wow this such a great article and the tips are very comprehensive. For sure many entrepreneurs with small and big businesses are going to benefit from this. Keep it up!
Real estate orange county

Mohd_ummed said...

there are a very valuable information here for the real estate i observe it very nice
for Revanta Raheja

webmaster said...

Hello dear.You have written a great post. Going to share with my followers on twitter. Thanks for sharing.

Rio flat