Maximizing Sample Overlap between Two Independent Surveys

• Activity Number: 650
• Type: Topic Contributed
• Date/Time: Thursday, August 4, 2011 : 10:30 AM to 12:20 PM
• Sponsor: Section on Survey Research Methods
• Author(s): David Salvatore Piccone*+ and Edwin Robison and Shail Butani
• Companies: Bureau of Labor Statistics and Bureau of Labor Statistics and Bureau of Labor Statistics
• Keywords: Power allocation ; Neyman allocation ; sample rotation panels ; independent smaple designs ; sub-sampling ; swapping algorithm

Abstract

In 2010, the U.S. Bureau of Labor Statistics (BLS) began preparations to embark on a "green jobs" initiative. The goals are to provide information for the U.S. economy on: 1) number of green jobs and trends over time; 2) industrial, occupational, and geographic distribution of these jobs; and 3) what these jobs pay. A new Green Goods and Services (GGS) Survey of 120,000 units is designed to measure the number of green jobs and trends over time as well as industrial and geographical distribution; the data collection began in 2011. The occupational distribution and what these jobs pay are being measured through BLS existing Occupational Employment Statistics (OES) Survey of 1.2 million units. For various reasons, both GGS and OES have independent sample designs--allocation, selection, data collection, and estimation. A major goal of this project is to maximize sample overlap between