Is There Statistical Insignificance In The Jobs Report?
Posted on July 6, 2007
Filed under Non-Farm Payrolls
Read the complete post
Thanks for visiting The Mortgage Reports. To stay absolutely current on mortgage markets and important guideline changes, be sure to take my free daily email alerts.
According to the Bureau of Labor and Statistics' press release today, the following is true (but subject to revision in August and September):
- 132,000 new jobs were created in June versus expectations of 120,000
- 33,000 more jobs were created in May than previously measured
- 42,000 more jobs were created in April than previously measured
So, in total, today's overall "surprise" was 87,000, measured against the total number of employed people (also in the BLS release) of 146,100,000. In percentage terms, that's just 0.059548% of the overall workforce.
The revisions are statistically insignificant, especially considering that government press releases don't go beyond tenths with respect to decimal places. If revision percentages were included in a government release, it would read something like this:
"Revisions to non-farm payroll jobs from months prior added 0.0% to the total number of employed persons".
Want to put 0.059548% in mathematical perspective?
- It's adding one more square foot to Zaremba's Harbor Walk Townhomes in Colorado
- It's adding one more seat to Krenzler Stadium in Cleveland
- It's adding one more pixel of width to this handsome guy's photograph
And yet, mortgage rates are higher today and economists are out chirping about ongoing economic strength.
To economists and traders, the "adding one more" makes an important difference so maybe we should all look at this as just one more example of how investor psychology can sometimes be more important that logical data analysis.
Dan Green is an active loan officer. Email or call 513-443-2020. Dan is on Twitter at @mortgagereports.

I use Scribe to improve my blog SEO








