Friday, March 11, 2011

Benchmarking Drops NM Job Totals

Every year the job counters at the state and national level “benchmark” the past estimates.
What that means, basically, is that they go back and clean up the numbers, eliminating (probably not completely) the errors that have crept in over the past year. The error has two sources, actual mistakes and sampling.
The sampling error is in the nature of the beast. The annual benchmark provides the base for the sample. But the further the estimator gets from the base, the shakier the sample becomes.
The federal Bureau of Labor Statistics explains this, nearly understandably.
The revisions moved New Mexico’s reported employment down a half percent for December 2010. That means last year was even worse than we thought.
A sample of the fed’s insight is pasted below along with the URL for the whole thing.
“With the release of the estimates for January 2011, non-farm payroll employment, hours, and earnings data for States and areas were revised to reflect the incorporation of March 2010 benchmarks and the recomputation of seasonal adjustment factors for State estimates. The revisions affect all not seasonally adjusted data from April 2009 forward, all seasonally adjusted data from January 2006 forward, and select series subject to historical revisions.
“The Current Employment Statistics (CES) program, also known as the payroll survey, is a Federal/State cooperative program that provides employment, hours, and earnings estimates… by estimating the number of jobs in the population from a sample of that population. Each month the CES program surveys about 140,000 businesses and government agencies, representing approximately 410,000 individual worksites, in order to provide detailed industry data on employment, hours, and earnings of workers on non-farm payrolls…
“As with data from other sample surveys, CES estimates are subject to both sampling and non-sampling error. Sampling error is an unavoidable byproduct of forming an inference about a population based on a sample. The larger the sample is, relative to the population, the smaller the sampling error. The sample-to-population ratio varies across States and industries. Non-sampling error, by contrast, generally refers to errors in reporting and processing.”

No comments: