Related BLS programs | Related articles
September 1993, Vol. 116, No. 9
Overhaul of the Current Population Survey
Redesigning the questionnaire
Anne E. Polivka and Jennifer M. Rothgeb
Probably the single most politically sensitive number published by the Federal Government is the seasonally adjusted monthly unemployment rate. This measure, along with other information about the U.S. labor force, such as earnings, number of hours worked, and job search intentions of those not in the labor force, is calculated using data collected through the Current Population Survey (CPS). Nevertheless, despite the importance of the statistics derived from the survey, and the changing American economy, the CPS has remained virtually unchanged since 1967.
In 1986, the Bureau of Labor Statistics (BLS), in collaboration with the Bureau of the Census, began a program to modernize the CPS. An integral part of this effort was evaluating and redesigning the survey questionnaire. The result is a completely redesigned questionnaire, which will be implemented in January 1994. This article briefly elaborates on the history of and concepts underlying the CPS questionnaire, as discussed by John E. Bregger and Cathryn S. Dippo on pages 3-9. Its chief focus, however, is the new questionnaire: the need for the redesign; methods used to test alternative versions; comparisons of the revised questionnaire with the current one; and the extent to which labor force misclassification appears to be reduced through the redesign.
Background in brief
Since its inception as a national survey of sample households in 1940, the CPS has based its measurement of employment and unemployment on individuals' activities. However, the implementation of these activity-based measurements (and the auxiliary information collected with the CPS) has undergone some alterations throughout the years.
The most fundamental changes to the CPS questionnaire occurred in 1945 and 1967. In 1945, four standardized questions were incorporated to ascertain whether individuals were employed, unemployed, or not in the labor force. Previously, enumerators had assigned labor force classifications during the interview by following a complicated prioritization scheme. However, special studies conducted at the time demonstrated that the lack of specifically worded questions resulted in the exclusion from the labor force of a large number of part-time and intermittent workers, and created inconsistencies among individuals' labor force classifications. The introduction of specific questions ensured uniformity in data collection and relieved enumerators of the burden of applying complicated prioritization schemes.1
This excerpt is from an article published in the September 1993 issue of the Monthly Labor Review. The full text of the article is available in Adobe Acrobat's Portable Document Format (PDF). See How to view a PDF file for more information.
Read abstract Download full text in PDF (1389K)
1 See Louis Ducoff and Margaret Jarman Hagood, "Labor Force Definitions and Measurements," in National Commission on Employment and Unemployment Statistics, Counting the Labor Force, Readings in Labor Force Statistics, appendix vol. III (Washington, U.S. Government Printing Office, 1979), pp.32-43.
Overhaul of the Current Population Survey: Why is it necessary to change? September 1993.
Within Monthly Labor Review Online:
Welcome | Current Issue | Index | Subscribe | Archives
Exit Monthly Labor Review Online:
BLS Home | Publications & Research Papers