Indirect Estimators in U.S. Federal Programs

Federal statistical agencies produce estimates of a variety of population quantities for both the nation as a whole and for subnational domains. Domains are commonly defined by demographic and socioeconomic variables. However, geographic location is perhaps the single variable used most frequently to define domains. Regions, states, counties, and metropolitan areas are common geographic domains for which estimates are required. Federal agencies use different data systems and estimation methods to produce domain estimates. Those systems designed for the purpose of producing published estimates use standard, direct estimation methods. Data systems are designed within time, cost and other constraints which restrict the number of estimates that can be produced by standard methods. However, the demand for additional information and the lack of resources to design the required data systems have led federal statistical agencies to consider non-standard methods. Estimation methods of a particular type, referred to as small area or indirect estimators, have sometimes been used in these situations.

The National Center for Health Statistics (NCHS) through its vital registration system collects and publishes data on vital events (births and deaths) for the United States (NCHS 1989). NCHS produces national, State, county, and smaller area vital statistics for sociodemographic and health characteristics which are available from birth and death certificates. The Division of Vital Statistics of NCHS produces annual summary tables for the United States showing trends in period and cohort fertility measures and characteristics of live births. Also, NCHS produces detailed tabulations by place of residence and occurrence for each State, county, and city with a population of 10,000 or more; by race and place of delivery and place of residence for population-size groups in metropolitan and nonmetropolitan counties within each State by race, attendant and place of delivery, and birth weight. These statistics are based on a complete count of vital records.

The Bureau of Economic Analysis (BEA) maintains a program of State and local area (county and metropolitan area) economic measurement that centers on the personal income measure. This program originated in 1939 when estimates of income payments to individuals by State were first published. At the national level, personal income is the principal income measure in the personal income and outlay account, one of the five accounts that compose the national income and product accounts. The State and local area personal income estimates are derived by disaggregating the detailed components of the national personal income estimates to States and counties. Estimates for all other geographic areas are made by aggregating either the State or county estimates in the appropriate combinations. This building block approach permits estimates for areas whose boundaries change over time, such as metropolitan areas, to be presented on a consistent geographic defmition for all years.

The Bureau of Labor Statistics’ (BLS) Local Area Unemployment Statistics (LAUS) Program produces state and area employment and unemployment estimates under a federal-state cooperative program. At present, monthly employment and unemployment estimates are prepared for the 50 states and the District of Columbia, all Metropolitan Statistical Areas (MSA’s), all counties, and selected subcounty areas for which data are required by legislation -- more than 5,300 areas. The Current Population Survey (CPS), conducted by the Bureau of the Census for the BLS, is the official survey instrument for measuring the labor force in the United States. The CPS sample provides direct monthly survey estimates of employment and unemployment for the nation, selected states and New York City and Los Angeles. However, the CPS sample is not sufficiently large in most states and substate areas to provide reliable monthly estimates. Therefore, methods are used to combine data from other sources with current and historical CPS sample estimates to produce monthly estimates of employment and unemployment for the remaining states, the District of Columbia, and substate areas.

The National Agricultural Statistics Service (NASS) of the U.S. Department of Agriculture (USDA) has published county estimates of crop acreage, crop production, crop yield and livestock inventories since 1917. These estimates assist the agricultural community in local agricultural decision making. Also the Federal Crop Insurance Corporation (FCIC) and the Agricultural Stabilization and Conservation Service (ASCS) of the USDA use NASS county crop yield estimates to administer their programs involving payments to farmers if crop yields are below certain levels. The primary source of data for these estimates has always been a large non-probability survey of U.S. farmers, ranchers, and agribusinesses who voluntarily provide information on a confidential basis (see Chapter 7). In addition, the U.S. Census of Agriculture, conducted by the Bureau of the Census every five years, serves as a valuable benchmark for the NASS county estimates.

The National Agricultural Statistics Service (NASS) of the U.S. Department of Agriculture (USDA) publishes over 300 reports annually regarding the Nation’s crop acreage, crop production, livestock inventory, commodity prices, and farm expenses. The primary source of this information is surveys of U.S. farmers, ranchers, and agribusinesses who voluntarily provide information on a confidential basis. These surveys are normally designed to provide State and U.S. level indications of agricultural commodities. There is also a need for county level estimates to assist fanners, ranchers, agribusinesses, and government agencies in local agricultural decision making.

There is a continuing need to assess health status, health practices and health resources at both the national level and subnational levels. Estimates of these health items help determine the demand for quality health care and the access individuals have to it. Although National Center for Health Statistics (NCHS) survey data systems can provide much of this information at the national level, little can be provided directly at the subnational level, except for a few large states and metropolitan areas. The need for State and substate health statistics exists, however, because health and health care characteristics are known to vary geographically. Also, health care planning often takes place at the state and county level.

Starting with income year 1974, the U.S. Census Bureau has computed model-based estimates of median annual income for 4-person families by state using data from the decennial censuses, the Current Population Survey (CPS), and estimates of per capita income (PCI) from the Bureau of Economic Analysis (BEA). Originally, these estimates were used in determining eligibility for the former Title XX Program of the Social Security Act, which provided social services for individuals and families

During the design of a data system, indirect estimators rarely, if ever, are considered for Federal statistical programs when resources to produce direct estimates of adequate precision are available. However, given an existing system, if direct estimation is judged to be inadequate for a domain not specified in the design, indirect estimation may, in some cases, prove to be a valuable alternative. There are a number of reasons that direct estimators are preferable to indirect ones and, if federal statistical agencies are to improve the usefulness of indirect estimates, a number of important issues, including those that follow, should receive additional attention. The following points are developed further in the sections of this chapter.