Composite Estimation in Current Population Survey

• Activity Number: 105
• Type: Invited
• Date/Time: Monday, August 5, 2013 : 8:30 AM to 10:20 AM
• Sponsor: Survey Research Methods Section
• Author(s): Jun Shao and Zhou Yu*+
• Companies: University of Wisconsin and University of Wisconsin-Madison
• Keywords: Composite estimation, bias, mean squared error, variance estimation.

Abstract

A composite estimator is currently used to estimate the monthly total of the employment, unemployment, and other characteristics of the non-institutionalized civilian population in the The Current Population Survey (CPS), a household sample survey sponsored by the US Bureau of Labor Statistics and conducted by the US Bureau of the Census. Statistical of the current composite estimator, however, is unknown except that it has a non-negligible bias unless some conditions are satisfied. We study the bias and variance of the composite estimator and develop an adaptive method to find the best values of the tuning parameters in composite estimation. Other issues, such as the use of administrative information and variance estimation, will also be studied.