Small Area Research for the Occupational Employment Statistics Survey

The Occupational Employment Statistics (OES) Survey is a yearly mail survey designed to produce estimates of employment and wages for more than 700 occupations in the U.S. The OES sample is stratified by geographic area, economic activity, and employment size class; with geographic area defined by State, Metropolitan Statistical Area (MSA) and balance of State area, and economic activity defined by 3-digit Standard Industrial Classification (SIC) codes. While the sample is designed to produce reliable design-based estimates for large geographic areas, our research investigates synthetic estimators for smaller geographic areas, such as at the county level. 1. The Occupational Employment Statistics Survey The Occupational Employment Statistics (OES) survey program at the U.S. Bureau of Labor Statistics (BLS) is a yearly mail survey designed to produce estimates of employment and wages for specific occupations by geographic areas and by industry. Estimates based on geographic areas are available at the National, State, and Metropolitan Statistical Area (MSA) levels. Estimates of occupational employment (OE) and wages for over 400 industries are available at the The views expressed in this article are those of the authors and do not constitute the policy of the Bureau of Labor Statistics. The authors can be contacted at: U.S. Bureau of Labor Statistics, Postal Square Building, Suite 1950, 2 Massachusetts Ave. NE. Washington, DC 20212-000, or E-Mail: li [email protected]; miller [email protected]. national level. The OES samples approximately 400,000 establishments per year, collecting data on wage and salary of workers in nonfarm establishments for over 700 occupations. The OES program, as a Federal-State cooperative program, provides information heavily utilized by both federal and local policy makers. Increasingly States are interested in producing estimates for additional geographic areas. Many of the additional areas of interest are at the county level. Estimation of OE and wages are available at a basic level defined by State, MSA, and 3digit SIC and at aggregates of the basic level. The weighted sample employment, at the basic estimation level, is adjusted to the total employment derived from BLS’s Longitudinal Database. Any estimates below the basic level, such as at the sub-MSA level, are not controlled, and therefore are subject to bias and a high level of sampling variability. We consider in this study three synthetic estimators to produce subMSA OE estimates which may provide higher statistical accuracy. 2. Synthetic Estimators for Local Occupational Employment 2.1 Notation This section lists the notation that will be used throughout the paper. E total employment, e.g. E d, g is the total employment of population group g in small domain d; E d, · is the total employment in small domain d. P , , o percentage of OE for occupation o, e.g., P d, g, o, is the percentage ENAR Spring Meeting Section on Government Statistics