Abstract

Gwyn R. Ferguson, Chester H. Ponikowski and Erin McNulty "State and Local Government Sample Design for the National Compensation Survey"

The National Compensation Survey is conducted by the Bureau of Labor Statistics to compute measures of the pay and benefits for America's workers. Since the early 1990's, the survey design used a three-stage sample design to select samples of areas, establishments, and jobs for which wage and benefit data are collected periodically over a five-year rotation. In 2011, we presented a new two-stage sample design for private industry establishments that introduces a three-year rotation of establishment samples. This new design is a national design without any area sampling under which we select samples of establishments and jobs in the two stages of selection. This paper will explore design alternatives for selection of establishments in the State and local government sectors of the economy that are more consistent with the new private industry design. Design topics that are being studied and will be presented include sample rotation, allocation, sample frame preparation, establishment selection, and sample initiation scheduling. Recommendations for the design to be used when selecting future public sector samples will be presented.