Activity Number:
|
227
- Non-Traditional Approaches for Sampling Rare Populations
|
Type:
|
Topic Contributed
|
Date/Time:
|
Monday, July 31, 2017 : 2:00 PM to 3:50 PM
|
Sponsor:
|
Survey Research Methods Section
|
Abstract #323413
|
View Presentation
|
Title:
|
Sampling Late Baby Boomers: Increasing Cluster- and Household-Level Eligibility Rates with External Data
|
Author(s):
|
Daniel Guzman* and Richard Valliant and Sunghee Lee and Paul Burton
|
Companies:
|
University of Michigan and University of Maryland and University of Michigan and University of Michigan
|
Keywords:
|
external data ;
small population ;
rare population ;
multi-stage sampling
|
Abstract:
|
Traditional sampling techniques to study small or rare population often are inefficient due to the low number of eligible participants on the general population. One strategy to improve efficiency is to increase eligibility rates by targeting likely eligible participants. However, to implement this strategy the sampling frame requires to include a set of variables that correlate with eligibility. This paper presents the use of external data at cluster and household level to improve eligibility rates for sampling late baby boomers. Census data was used at the cluster level to select area with higher density of late baby boomers with higher probability. At the household level, commercial data was attached to households. This is information was used to stratified households in selected cluster. Likely baby boomers according to the commercial data were sampled at higher rate. The use of external data proved to be effective on increasing efficiency of selecting late baby boomers.
|
Authors who are presenting talks have a * after their name.