|
Activity Number:
|
554
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Thursday, August 6, 2009 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Survey Research Methods
|
| Abstract - #303895 |
|
Title:
|
Components of Error Analysis in the Current Employment Statistics Survey
|
|
Author(s):
|
Larry L. Huff and Julie Gershunskaya*+
|
|
Companies:
|
Bureau of Labor Statistics and Bureau of Labor Statistics
|
|
Address:
|
, , ,
|
|
Keywords:
|
nonresponse bias ; error decomposition ; response rate
|
|
Abstract:
|
One of the prominent features of the Current Employment Statistics (CES) survey conducted by the U.S. Bureau of Labor Statistics (BLS) is that the data collection is conducted monthly and the estimates are published in a very short time period. It is important to analyze the effect of the survey nonresponse on the quality of the estimates. Several months after the reference period, universe data become available through the Quarterly Census of Employment and Wages (QCEW) BLS Program. The availability of the census data makes it possible to separate sources of potential divergence of the CES estimates from the corresponding population totals. The sources include sampling variability; the potential for nonresponse bias; the differences in the data reported to the two programs, i.e. reporting error; and frame imperfections due to the appearance of new establishments (births).
|
