Activity Number:
|
75
|
Type:
|
Contributed
|
Date/Time:
|
Monday, August 12, 2002 : 8:30 AM to 10:20 AM
|
Sponsor:
|
Section on Survey Research Methods*
|
Abstract - #300886 |
Title:
|
Pair Sampling in Household Surveys
|
Author(s):
|
James Chromy*+ and Michael Penne
|
Affiliation(s):
|
RTI International and RTI International
|
Address:
|
3040 Cornwallis Road, Box 12194, Research Trianlge Park, North Carolina, 27709-2194, USA
|
Keywords:
|
Household rosters ; Person selection ; Unequal probability sampling ; Pair sampling
|
Abstract:
|
Computer-assisted dwelling unit screening provides the mechanism for targeted sampling of both individuals and pairs of individuals. Selection algorithms can be programmed into the screening instrument to implement unequal probability sample selection algorithms. This paper discusses a modification of Brewer's method for samples of size two as a means of selecting samples of 0, 1, or 2 persons from eligible dwelling units. A second adaptation which can be used to control the number of pairs selected is also discussed. Some empirical data on household roster composition, and response rates based on the number of persons selected, are presented from the National Survey on Drug Use and Health.
|