Network model-assisted inference from respondent-driven sampling data

Respondent-driven sampling is a widely used method for sampling hard-to-reach human populations by link tracing over their social networks. Inference from such data requires specialized techniques because the sampling process is both partially beyond the control of the researcher, and partially impl...

Full description

Saved in:
Bibliographic Details
Published in:Journal of the Royal Statistical Society. Series A, Statistics in society Vol. 178; no. 3; pp. 619 - 639
Main Authors: Gile, Krista J., Handcock, Mark S.
Format: Journal Article
Language:English
Published: England Blackwell Publishing Ltd 01.06.2015
John Wiley & Sons Ltd
Oxford University Press
Subjects:
Alternative approaches
Bootstrap method
Demonstrations
Estimating techniques
Estimation
Estimation bias
Estimators
Exponential family random graph model
Hard-to-reach population sampling
High risk
HIV
Human immunodeficiency virus
Infections
Inference
Link tracing
Network analysis
Network sampling
Population
Population estimates
Population size
Respondents
Sampling
Sampling bias
Sampling studies
Simulations
Social networks
Statistical inference
Network sampling
Exponential-family random graph model
Social networks
Link-tracing
Hard-to-reach population sampling
ISSN:0964-1998, 1467-985X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Respondent-driven sampling is a widely used method for sampling hard-to-reach human populations by link tracing over their social networks. Inference from such data requires specialized techniques because the sampling process is both partially beyond the control of the researcher, and partially implicitly defined. Therefore, it is not generally possible to compute the sampling weights for traditional design-based inference directly, and likelihood inference requires modelling the complex sampling process. As an alternative, we introduce a model-assisted approach, resulting in a design-based estimator leveraging a working network model. We derive a new class of estimators for population means and a corresponding bootstrap standard error estimator. We demonstrate improved performance compared with existing estimators, including adjustment for an initial convenience sample. We also apply the method and an extension to the estimation of the prevalence of human immunodeficiency virus in a high-risk population.
Bibliography:ark:/67375/WNG-MVT6S95N-7
istex:82FA99A51B2EBCE3ACF8C6375A32CEDA8E1C9F1D
ArticleID:RSSA12091
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-1
ObjectType-Feature-2
content type line 23
ISSN:0964-1998
1467-985X
DOI:10.1111/rssa.12091