According to the Bureau of Labor Statistics, the average difference between the "benchmark revision" numbers Scott Walker has supposedly come up with and the Current Employment Survey is only 0.3% and largest diference they have recorded in the last ten years has been 0.7%.
Walker is claiming to have benchmark revision numbers that would be 2.1% different that CES numbers or seven times the average difference and three times larger than the largest difference ever recorded.
Is it possible that Scott Walker's numbers could be right? Yes. But, it's about as probable as getting struck by lightning.
It's also important to note that the benchmark revision has not yet been certified as correct by the BLS and, even then is subject to error:
The benchmark revision can be more precisely interpreted as the difference between two independently derived employment counts, each subject to its own error sources.
Both the universe counts and the establishment survey estimates are subject to nonsampling errors common to all surveys – coverage, response, and processing errors. The error structures for both the CES monthly survey and the UI universe are complex. Still, the two programs generally produce consistent total employment figures, each validating the other. Over the last decade, annual benchmark revisions at the Total nonfarm level have averaged 0.3 percent (in absolute terms), with an absolute range of 0.1 percent to 0.7 percent.
Here is the bottomline: If there was some sort of historic, earth-shattering sampling error in the CES, it would be statistically improbable that the error would only be in Wisconsin-- all states would be off by roughly 2.1% -- meaning that Wisconsin would still be last in job growth, compared to other states.
