U.S. flag

An official website of the United States government

Department of Labor Logo United States Department of Labor
Dot gov

The .gov means it's official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you're on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Bureau of Labor Statistics > Office of Survey Methods Research > Publications > Browse Research Papers

What Would the Unemployment Rate Have Been Had the Redesigned Current Population Survey Been in Place from September 1992 to December 1993?

Stephen M. Miller

Abstract

The official monthly labor force estimates from January 1994 onwards will be based on data from a comprehensively redesigned Current Population Survey (CPS). The redesign incorporates changes in the basic questionnaire and collection methodology. In addition, these estimates will be constructed using 1990-Census-based population controls rather than 1980-Census-based population controls.

To better understand the effect of the CPS redesign on published estimates, a Parallel Survey, intended to provide annual average labor force estimates, was conducted from July 1992 to December 1993 using a separate monthly sample of households approximately one-fifth the size of the regular CPS sample. Because of the small sample size, monthly estimates from the Parallel Survey are highly variable.

To help analysts interpret the 1994 monthly CPS estimates, the CPS Bridge team has modeled the Parallel Survey estimates from September 1992 through December 1993 for the purposes of producing more accurate estimates of what the CPS might have looked like during that period had the redesigned CPS been in place. The modeling has used only data from the Parallel Survey and the CPS and yields monthly estimates with approximately one-half the sampling variability of the monthly Parallel Survey estimates, but still about twice the variance of the regular CPS estimates. While the model estimates are less variable than the monthly estimates from the Parallel Survey, it should be noted that, because not all design differences could be taken into account, the model estimates may not provide a completely accurate picture of what the estimates from the redesigned CPS would have looked like during that period. The model estimates were seasonally adjusted with factors computed under the old CPS, so not all seasonality may be accounted for.