>No, he plays to the suspicions of people that anything put out by the
>Executive branch under Bush is likely to be a self-serving lie. You happen
>to believe that the Bureau of Labor Statistics has maintained its
>impeccable independence under Bush.
Would they have announced last month's 112k, this month's 32k, and significant downward revisions of the back months, if they were in W's pocket? You're not really arguing that, are you?
> >They're better than they ever were. Recent benchmark revisions, which
>>are based on near=100% coverage of the employment universe (through
>>unemployment insurance records) have been very small, much smaller
>>compared to those of 10 years ago, when the BLS used a different
>>method of estimating business startups and failures.
>
>I'm not even sure what you mean that unemployment insurance gives you proof
>of accuracy. Large numbers of people laid off never qualify for or apply
>for unemployment insurance, including the self-employed and a range of
>other folks. So if that is the benchmark for double-checking the BLS
>numbers, that hardly restores my confidence.
Wow, you really don't know much about all this, do you? The UI records cover nearly the entire employment universe.
<http://stats.bls.gov/ces/cesbmkqa.htm>
>II. Background Information
>
>(1) What is the establishment payroll survey?
>
>The establishment payroll survey, also known as the Current
>Employment Statistics (CES) survey, is a monthly sample survey which
>includes 400,000 individual business and government agency worksites
>drawn from a sampling frame of Unemployment Insurance tax accounts.
>The primary statistics derived from the survey are monthly estimates
>of employment, hours, and earnings for the nation, states, and major
>metropolitan areas. Preliminary national estimates for a given
>reference month typically are published on the first Friday of the
>following month, in conjunction with data derived from a separate
>survey of households, the Current Population Survey (CPS). The CPS
>is the source of statistics on the activities of the labor force,
>including the nation's unemployment rate.
>
>(2) What is the UI universe count?
>
>The Bureau's UI universe count is a quarterly tabulation, from
>administrative records, of the number of employees covered by
>unemployment insurance laws. UI universe counts, available on a
>lagged basis, contain individual employer records for over 8 million
>establishments and cover over 97 percent of total nonfarm
>employment; they thus provide a benchmark for the sample-based
>estimates. For the small segment of the population not covered by
>UI, BLS develops employment benchmarks from several alternative
>sources.
>
>(3) Why are the payroll survey estimates benchmarked to UI universe counts?
>
>The CES survey, like many other surveys, establishes benchmarks on a
>periodic basis in order to adjust its sample-based estimates to
>complete population counts available from administrative records.
>
>Because of their much smaller size, sample surveys offer an ability
>to produce very timely estimates along with a greater ability to
>control the quality of the data contained in individual reports.
>There is a need, however, to recalibrate sample estimates
>periodically against full population counts. The use of a population
>count, or benchmark, allows the results of the sample survey
>estimation process to be adjusted for new birth units in the
>population frame, and for sampling and non-sampling errors
>I'm not actually arguing-- and neither was Crudele -- that the overall jobs
>survey numbers are inaccurate over time, just that the swings month to
>month may be distorted by these statistical adjustements. Maybe he's wrong
>and maybe he's right-- but he's done a better job of predicting both the
>rise and fall in the job numbers in the last year based on his analysis of
>this problem that most mainstream forecasters.
I find that hard to believe. You have a record of his predictions over the last year?
Doug