Managing Response Burden by Controlling Sample Selection and Survey Coverage

• Activity Number: 349
• Type: Contributed
• Date/Time: Tuesday, August 2, 2011 : 10:30 AM to 12:20 PM
• Sponsor: Section on Survey Research Methods
• Author(s): Sebastien Landry*+
• Companies: Statistics Canada
• Keywords: Business surveys ; Response burden ; Sample selection ; Take-none strata

Abstract

Statistical agencies are constantly making efforts to control the response burden of their household and business survey respondents. Statistics Canada's Survey on Employment, Payroll and Hours is no exception. This monthly business survey, which produces estimates and determines the month-to-month changes for variables such as employment, earnings and hours at detailed industrial levels for Canada, the provinces and the territories, currently manages response burden by making use of administrative data and by having rules that prevent establishments from rotating in the sample too soon after being rotated out. Recently, two new ideas to decrease even more the response burden for respondents to this survey have been studied. The first is to control the overlap of the samples from one month to the next by the use of the microstrata method (Rivière (2001)) in the sample selection process. The second is the increased number of establishments in the take-none strata. This paper will present the studies that evaluated the pros and cons of implementing each of these new features in the survey.