An Evaluation of Different Small Area Estimators for the Annual Survey of Public Employment and Payroll

• Activity Number: 207
• Type: Invited
• Date/Time: Monday, August 4, 2014 : 2:00 PM to 3:50 PM
• Sponsor: Survey Research Methods Section
• Author(s): Bac Tran*+ and Brian Dumbacher
• Companies: U.S. Census Bureau and U.S. Census Bureau
• Keywords: Government Units ; Horvitz-Thompson ; Composite Estimator ; Empirical Bayes ; Monte Carlo Simulation ; SPREE

Abstract

Abstract: The Governments Division of the U.S. Census Bureau employs small area estimation techniques for the Annual Survey of Public Employment and Payroll (ASPEP). ASPEP provides statistics on the number of federal, state, and local government civilian employees and their gross payrolls. Different small area estimators can be produced using the ASPEP data and auxiliary information from the preceding Census of Governments. We develop a design-based Monte Carlo simulation experiment in which we draw repeated samples from the 2007 Census of Governments data using the ASPEP sample design. We compute a wide range of estimates that use the generated sample and the 2002 Census of Government data. We then compare simulated design-based biases, variances, mean squared errors and coverage probabilities of these estimators. We repeat the experiment using the 2012 Census of Governments data in order to understand if these properties change over years. The estimators covered under our simulation study include Horvitz-Thompson, Structure PREserving Estimation (SPREE), traditional composite and empirical Bayes methods.