Technical Note

This release presents labor force and unemployment data for census
regions and divisions and states from the Local Area Unemployment 
Statistics (LAUS) program. The LAUS program is a federal-state 
cooperative endeavor.
  
  
Concepts

Definitions.  The labor force and unemployment data are based on
the same concepts and definitions as those used for the official
national estimates obtained from the Current Population Survey 
(CPS), a sample survey of households that is conducted for the 
Bureau of Labor Statistics (BLS) by the U.S. Census Bureau. The 
LAUS program measures employment and unemployment on a place-of-
residence basis. The universe for each is the civilian noninstitu-
tional population 16 years of age and over. Employed persons are 
those who did any work at all for pay or profit in the reference 
week (the week including the 12th of the month) or worked 15 hours 
or more without pay in a family business or farm, plus those not 
working who had a job from which they were temporarily absent, 
whether or not paid, for such reasons as labor-management dispute, 
illness, or vacation. Unemployed persons are those who were not 
employed during the reference week (based on the definition above), 
had actively looked for a job sometime in the 4-week period ending 
with the reference week, and were currently available for work; per-
sons on layoff expecting recall need not be looking for work to be 
counted as unemployed. The labor force is the sum of employed and 
unemployed persons. The unemployment rate is the number of unem-
ployed expressed as a percent of the labor force. The employment-
population ratio is the proportion of the civilian noninstitutional 
population 16 years of age and over that is employed.

Method of estimation.  Estimates for 48 of the 50 states, the Dis-
trict of Columbia, the Los Angeles-Long Beach-Glendale metropolitan 
division, New York City, and the balances of California and New York
State are produced using estimating equations based on regression
techniques. This method, which underwent substantial enhancement at
the beginning of 2005, utilizes data from several sources, including
the CPS, the Current Employment Statistics (CES) survey of nonfarm
payroll employment, and state unemployment insurance (UI) programs.
Estimates for the State of California are derived by summing the
estimates for the Los Angeles-Long Beach-Glendale metropolitan divi-
sion and the balance of California. Similarly, estimates for New 
York State are derived by summing the estimates for New York City 
and the balance of New York State. Estimates for all nine census 
divisions are based on a similar regression approach that does not 
incorporate CES or UI data. Estimates for census regions are ob-
tained by summing the model-based estimates for the component divi-
sions and then calculating the unemployment rate. Each month, cen-
sus division estimates are controlled to national totals; state es-
timates are then controlled to their respective division totals. Es-
timates for Puerto Rico are derived from a monthly household survey 
similar to the CPS. A detailed description of the estimation proce-
dures is available from BLS upon request.

Annual revisions.  Labor force and unemployment data for prior years 
reflect adjustments made at the end of each year. The adjusted esti-
mates reflect updated population data from the U.S. Census Bureau, 
any revisions in the other data sources, and model reestimation. In 
most years, historical data for the most recent 5 years (both season-
ally adjusted and not seasonally adjusted) are revised near the be-
ginning of each calendar year, prior to the release of January esti-
mates. Though the labor force estimates are changed for only 5 years, 
the population estimates--and, thus, employment-population ratios--are 
adjusted back to the decennial estimates base, currently April 2000.
 

Reliability of the estimates

The estimates presented in this release are based on sample surveys, 
administrative data, and modeling and, thus, are subject to sampling 
and other types of errors. Sampling error is a measure of sampling 
variability--that is, variation that occurs by chance because a sample 
rather than the entire population is surveyed. Survey data also are 
subject to nonsampling errors, such as those which can be introduc-
ed into the data collection and processing operations. Estimates not 
directly derived from sample surveys are subject to additional errors 
resulting from the specific estimation processes used. In table 1, le-
vel estimates for states may not sum to level estimates for regions 
and divisions because of rounding. Unemployment rates and employment-
population ratios are computed from unrounded levels and thus may dif-
fer slightly from rates and ratios computed using the rounded level 
estimates displayed in table 1.

Use of error measures. In 2005, the LAUS program introduced several 
improvements to its methodology. Among these was the development of 
model-based error measures for the monthly estimates and the estimates 
of over-the-month changes. Annual average model-based error measures 
became available for the first time after 2006. The introductory sec-
tion of this release preserves the long-time practice of highlighting 
the direction of the movements in regional and state unemployment rates 
and employment-population ratios regardless of their statistical signi-
ficance. The remainder of the analysis in the release--other than his-
torical highs and lows--takes statistical significance into considera-
tion. Model-based error measures are available online at 
www.bls.gov/lau/lastderr.htm. BLS uses 90-percent confidence levels in 
determining whether changes in LAUS unemployment rates or 
employment-population ratios are statistically significant. The average
magnitude of the over-the-year change in an annual state unemployment
rate that is required in order to be statistically significant at the 
90-percent confidence level is about 0.5 percentage point. The average 
magnitude of the over-the-year change in an annual state 
employment-population ratio that is required in order to be statistically
significant at the 90-percent confidence level is about 0.6 percentage point.
More details can be found on the Web site. Measures of nonsampling error 
are not available, but additional information on the subject is pro-
vided in Employment & Earnings Online, available on the BLS Web site 
at www.bls.gov/opub/ee/home.htm.

Additional information

More complete information on the technical procedures used to develop 
these estimates and additional data appear in Employment & Earnings 
Online.

Information in this release will be made available to sensory impaired 
individuals upon request. Voice phone: (202) 691-5200; Federal Relay 
Service: (800) 877-8339.