Research on Quarterly Benchmarking for the Current Employment Statistics Survey

• Activity Number: 165
• Type: Contributed
• Date/Time: Monday, August 3, 2009 : 10:30 AM to 12:20 PM
• Sponsor: Section on Government Statistics
• Author(s): Victoria Battista*+ and Chris Manning and Kenneth W. Robertson
• Companies: Bureau of Labor Statistics and Bureau of Labor Statistics and Bureau of Labor Statistics
• Keywords: Current Employment Statistics ; benchmark ; wedge ; data quality ; employment ; estimation

Abstract

The CES survey, conducted by the Bureau of Labor Statistics, is a large monthly survey of over 390,000 business establishments. The CES program publishes monthly estimates on employment, hours, and earnings by industry for the nation, states, and metropolitan areas. CES sample-based employment estimates are benchmarked - or controlled - annually to the Quarterly Census of Employment and Wages (QCEW), which is a near-universe count of employment based on unemployment insurance tax account records. Because the QCEW data are available quarterly, it is technically possible to benchmark CES estimates four times a year. Several alternative quarterly benchmarking procedures were evaluated to determine if the quality of the CES estimates could be improved. The authors describe the alternative procedures and examine the costs and benefits of benchmarking on a quarterly basis.