Survey Weighting Adjustments and the Design Effect: A Case Study

• Activity Number: 541
• Type: Contributed
• Date/Time: Wednesday, August 12, 2015 : 10:30 AM to 12:20 PM
• Sponsor: Survey Research Methods Section
• Author(s): Golshid Chatrchi* and François Brisebois
• Companies: Statistics Canada and Statistics Canada
• Keywords: calibration ; complex survey design ; design effect ; multiple frames ; weighting

Abstract

The final sampling weights are the result of various steps of adjustments to the design weights such as frame integration, nonresponse and calibration. Evaluating the Design Effect at each of these adjustments sheds light on their impact on the precision of survey estimates. In this paper, we focus on the Canadian Community Health Survey (CCHS), which uses a complex survey design with multiple frames and multiple stages of selection, and empirically examine the effect of different steps of the weighting process on the overall variability in estimates. The results suggest that the use of unequal person-selection probabilities and the nonresponse adjustment have the most negative impact on the design effect of the CCHS while calibration decreases the design effect and improves the precision of the estimates.