Small Area Estimation in Government Surveys (U.S. Census Bureau)

• Activity Number: 409 - Small-Area Estimation and Use of Unit-Level Models
• Type: Contributed
• Date/Time: Tuesday, August 1, 2017 : 2:00 PM to 3:50 PM
• Sponsor: Survey Research Methods Section
• Author(s): Bac Tran*
• Companies: US Census Bureau
• Keywords: governmental units ; hierarchical Bayes ; Monte Carlo Simulation ; Small Area Estimation

Abstract

The Annual Survey of Public Employment & Payroll (ASPEP), conducted by the U.S. Census Bureau, provides statistics on the number of federal, state, and local government civilian employees and their gross payrolls. The universe of ASPEP is about 90,000+ state and local government units. Every five years Census Bureau conducts a Census of Governments: Employment. Between two consecutive censuses, Census Bureau conducts the ASPEP, a nationwide sample survey covering all state and local governments in the United States. The ASPEP survey is designed to produce reliable estimates, for example, the number of full-time and part-time employees and payroll at the national level for large domains. However, it is also required to estimate the parameters for individual function codes within each state. This requirement prompted us to develop a methodology that employs Small Area Estimation (SAE) methods. The outlier treatments (Trinh & Tran, JSM 2017) will be discussed briefly in this research to improve the quality of the estimates.