Premium
A Protocol for Identifying and Sampling From Proxy Populations
Author(s) -
Lu Tao,
Franklin Aimee L.
Publication year - 2018
Publication title -
social science quarterly
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.482
H-Index - 90
eISSN - 1540-6237
pISSN - 0038-4941
DOI - 10.1111/ssqu.12519
Subject(s) - proxy (statistics) , population , protocol (science) , nonprobability sampling , computer science , selection (genetic algorithm) , sampling (signal processing) , expansive , econometrics , statistics , artificial intelligence , machine learning , medicine , environmental health , mathematics , pathology , compressive strength , alternative medicine , materials science , filter (signal processing) , composite material , computer vision
Objectives Increasingly it is more and more difficult for researchers to garner a robust response rate from their target population. In response, they often turn to more accessible proxy populations. However, guidance on how to identify and select a proxy population that reasonably mimics the target population is neither expansive nor systematic. Our objective is to fill this gap by offering a standardized protocol for selecting appropriate population. We introduce a proxy selection protocol that combines convenience with purposive nonprobability sampling. Methods The protocol introduces a method following a step‐by‐step process to evaluate the suitability of a different potential proxy populations as a reasonable representation of the target population. Results and Conclusion We come to an conclusion that this proxy selection protocol can overcome low response rates and avoid contamination of a limited target population when conducting exploratory or early‐stage explanatory research of potential causal relationships.