Adaptive Sampling in Behavioral Surveys (From The Validity of Self-Reported Drug Use: Improving the Accuracy of Survey Estimates, P 296-319, 1997, Lana Harrison and Arthur Hughes, eds. - See NCJ 167339)

• NCJ Number: 167352
• Author(s): S K Thompson
• Date Published: 1997
• Length: 24 pages
• Sale Source: National Institute on Drug Abuse; NCJRS Photocopy Services
• Publication Type: Report (Study/Research)
• Language: English
• Country: United States of America
• Note: DCC

Annotation

This article examines the use of adaptive sampling and graph sampling methods for studies of behavioral characteristics in rare and hidden populations, and discusses methods of adjusting for the nonsampling errors that arise in such studies.

Abstract

Studies of populations such as drug users encounter difficulties because the members of the population are rare, hidden, or hard to reach. Conventionally designed large-scale surveys detect relatively few members of the population, so estimates of population characteristics have high uncertainty. In adaptive sampling, the procedure for selecting people depends on variables of interest observed during the survey. Types of adaptive sampling designs include ordinary sequential sampling, adaptive allocation in stratified sampling, adaptive cluster sampling, and optimal model-based designs. Graph sampling refers to people connected by such things as social links or geographic proximity. Graph sampling designs include network sampling, snowball sampling, link-tracing, chain referral, and adaptive cluster sampling. References