If it’s a jobs Friday, it must be time for some fact-free spin, probably from both sides. But the right seems to take things just a bit further than the left.
Catching my eye last week was Senator Ron Johnson, who was interviewed by Betty Liu on her In the Loop show.
Paraphrasing Johnson’s first two claims:
Nonfarm payroll growth should average between 200-300K coming out of a recession (we’ll settle on 250K for this exercise). This is at 0:32.
Though the Establishment Survey produced 163K jobs, one should look at the Household Survey, which has a “larger sample size” (0:47).
From trough to peak, the Bush Boom averaged a woeful 155K/month NFP jobs, obviously less if you subtract the government jobs he added which I discussed here. Further still, Bush averaged 250K NFP jobs/month for a rolling 12 month period exactly zero times. Bill Clinton, on the other hand, had 47 – no typo – such 12 month rolling periods.
On to point number two:
The Household Survey is “Monthly sample survey of approximately 60,000 households.” The Establishment Survey is a “Monthly sample survey of about 141,000 businesses and government agencies covering approximately 486,000 establishments.” Do we need to go any further to assess which has a larger sample size? Well, okay, why not:
Both surveys are subject to sampling error. The payroll survey has a much larger sample size than the household survey. The payroll survey’s active sample covers approximately 486,000 business establishments of all sizes representing about one-third of total nonfarm employment. The household survey is much smaller at 60,000 households, covering a very small fraction of total employed persons. Over-the-month changes in household survey employment are therefore subject to larger sampling error, about four times that of the payroll survey on a monthly basis.
Further: “An over-the-month employment change of about 100,000 is statistically significant in the establishment survey, while the threshold for a statistically significant change in the household survey is about 400,000.” Yet Senator Johnson focused on the -195,000 drop in the Household Survey, which BLS tells us is not statistically significant.
This concludes the July edition of Fact-Free NFP Fridays, which perhaps I’ll make a monthly feature.
Find me on the Twitter: @TBPInvictus
What's been said:
Discussions found on the web: