05-1336. Notice of Decision To Revise Method for Estimation of Monthly Labor Force Statistics for Certain Subnational Areas

AGENCY:

Bureau of Labor Statistics, Labor.

ACTION:

Statement of policy.

SUMMARY:

The Department of Labor, through the Bureau of Labor Statistics (BLS), is responsible for the development and publication of local area labor force statistics. In the Local Area Unemployment Statistics (LAUS) program, monthly estimates of the labor force, employment, unemployment, and the unemployment rate for more than 7,000 areas in the Nation are developed and issued monthly. With data for January 2005, to be published in March 2005, the monthly labor force estimates prepared in the LAUS program will be based on methodological improvements that resulted from the completion of a number of projects to improve the statistical basis of the estimates. In addition, the LAUS estimates will reflect updated geography and other techniques that are based on 2000 Census data.

EFFECTIVE DATE:

These changes will be effective with January 2005 LAUS estimates issued in March 2005.

FOR FURTHER INFORMATION CONTACT:

Sharon P. Brown, Chief, Division of Local Area Unemployment Statistics, Bureau of Labor Statistics, Telephone [phone].

SUPPLEMENTARY INFORMATION:

I. Summary of Comments

The BLS received one comment in response to the request for comments on the Proposal to Revise the Method for Estimation of Monthly Labor Force Statistics for Certain Subnational Areas. That commenter was opposed to the use of model based estimation for the Miami metropolitan division. In BLS's judgment the statistical modeling methodology is superior to the existing method for Miami because it directly utilizes Current Population Survey (CPS) estimates of employment and unemployment, allows for the development of seasonally adjusted estimates, and provides measures of error on the data. The commenter also opposed the implementation of a method for adjusting place-of-work employment to place-of-residence using decennial census-based ratios for areas outside the area of estimation with known commutation. Based on research and simulations, the BLS feels that this dynamic approach will result in better estimation of resident employed in the intercensal period.

II. Additional Information

Since the BLS was given responsibility for the LAUS program in 1972, a hierarchy of estimation methods has been used to produce the State and area labor force estimates, based in large part on the availability and quality of data from the CPS, the official measure of the labor force for the nation. The BLS has continuously advanced the statistical basis of the LAUS estimates by researching and implementing improved statistically sound methodology, updating the methodology with decennial census data, and reflecting the latest decennial identification of geographic areas.

Estimates for States, the District of Columbia, New York City, Los Angles-Long Beach-Glendale Metropolitan Division. From 1996 on, the estimates for States, the District of Columbia, New York City, Los Angeles metropolitan area, and the balances of New York State and California were developed using signal-plus-noise models. These models relied heavily on monthly CPS data, as well as current wage and salary employment estimates and unemployment insurance statistics. The State CPS annual averages of employment and unemployment were used as benchmarks to the model-based estimates at the end of the year. In general, this method of model estimation and annual benchmarking resulted in an overestimate of employment and an underestimate of unemployment and the unemployment rate in States as compared to the national CPS estimates. The annual benchmarking approach reintroduced sampling error into the series and resulted in significant end-of-year revisions in a large number of States, caused economic anomalies that were an artifact of the benchmarking approach, distorted seasonality in the previous year so that analysis is impaired, and often missed shocks to the economy.

The improved model-based approach to estimation with real-time benchmarking addresses these issues. The models are signal-plus-noise models, where the signal is a bivariate model of the employment or unemployment level. Seasonal adjustment occurs within the model structure. Real-time benchmarking ensures that State estimates add to the national estimates of employment and unemployment each month. (The benchmark changes from annual State-level estimates of employment and unemployment to monthly national estimates of these measures.) In this way, economic shocks will be reflected in the State estimates on a real-time basis, and end-of-year revisions will be significantly smaller. The models with real-time benchmarking produce reliability measures for the seasonally adjusted and not seasonally adjusted series, and on over-the-month and over-the-year change.

Model-based Estimation in Six Additional Areas. Model-based estimation is extended to the following areas and the respective balance-of-State areas: Chicago metropolitan division, Cleveland metropolitan area, Detroit metropolitan area, Miami metropolitan division, New Orleans metropolitan area, and Seattle-Everett metropolitan division. This improves the statistical basis of the estimation for these areas, and provides important tools for analysis such as measures of error and seasonally adjusted series.

These area models are univariate and are benchmarked to the State employment and unemployment estimates on a real-time basis. As with the State models, seasonally adjusted series are produced, along with measures of error for the seasonally adjusted and not seasonally adjusted series, and on over-the-month and over-the-year change.

New and Reentrant Unemployment. Long-standing concerns were expressed in the regard to the estimation of unemployment at the substate level (for areas other than New York City, Los Angeles, and the balances of New York State and California). Difficulty in the measurement of unemployed new and reentrants to the labor market led to the use of large proportionate adjustment of area estimates to the State total unemployed as a way of controlling for the underestimate at the area level. The improved method addresses the issue of underestimation and eliminates the need for significant proportionate adjustment of area estimates to the monthly State levels of unemployment.

The new methodology incorporates the CPS new and reentrants State data and utilizes improved econometric modeling techniques. In this model, the values of the coefficients change from month to month as the models are updated with information from current observations. The model estimates are distributed to each labor market area in the State based on the area's share of the State population. New entrants are distributed based on the area's share of the State 16-19 year old population, and reentrants are distributed based on the area's share of the State 20 years and older population.

Residency Adjustment. The underlying concepts and definitions of all labor force data developed by the LAUS program are consistent with those of the CPS, including the requirement that measures relate to the place of residence of the labor force participant. Current, geographically comprehensive employment data at the area level are establishment-based and reflect jobs by place of work. Thus, these data must be adjusted to account for multiple-job holding and residency prior to use in the LAUS program. The prior Census-based residency adjustment procedure used a single ratio for the labor market area. Thus, it was the limited in the geographic scope for influencing the area's estimate of resident employed and static in nature. Also, labor market areas often are not defined to the point where commutation is zero, and, in the intercensal period, job growth can and does occur in the areas surrounding the estimating area.

In the new method, resident employment in an area is a function not only of the relationship between employed residents and jobs in that area, but in other areas within commuting distance. The procedure is more dynamic than the prior method insofar as job count changes in commuting areas can affect resident employment. As in the current procedure, however, the commuting ratios themselves are fixed for the intercensal period.

Detailed descriptions of the current and redesign approaches are available at the above address and at the BLS LAUS Web site http://www.bls.gov/​lau/​home.htm.

Signed in Washington, DC, this 14th day of January, 2005.

John M. Galvin,

Associate Commissioner, Office of Employment and Unemployment Statistics, Bureau of Labor Statistics.