Change search
ReferencesLink to record
Permanent link

Direct link
Multiple seed structure and disconnected networks in respondent-driven sampling
Stockholm University, Faculty of Science, Department of Mathematics.
Karolinska Institutet, Stockholm, Sweden; Université de Namur, Belgium.
(English)Manuscript (preprint) (Other academic)
Abstract [en]

Respondent-driven sampling (RDS) is a link-tracing sampling method that is especially suitable for sampling hidden populations. RDS combines an efficient snowball-type sampling scheme with inferential procedures that yield unbiased population estimates under some assumptions about the sampling procedure and population structure. Several seed individuals are typically used to initiate RDS recruitment. However, standard RDS estimation theory assumes that all sampled individuals originate from only one seed. We use a random walk with teleportation to describe the multiple seed structure of RDS and develop an estimator based on this process. The new estimator is also valid for populations with disconnected social networks. We numerically evaluate our estimator by simulations on artificial and real networks. Our estimator outperforms previous estimators, especially when the proportion of seeds in the sample is large. We recommend our new estimator to be used in RDS studies, in particular when the number of seeds is large or the social network of the population is disconnected.

National Category
Probability Theory and Statistics
Research subject
Mathematical Statistics
Identifiers
URN: urn:nbn:se:su:diva-129257OAI: oai:DiVA.org:su-129257DiVA: diva2:920624
Funder
Swedish Research Council, 621-2012-3868
Available from: 2016-04-18 Created: 2016-04-18 Last updated: 2016-04-20
In thesis
1. Studies in respondent-driven sampling: Directed networks, epidemics, and random walks
Open this publication in new window or tab >>Studies in respondent-driven sampling: Directed networks, epidemics, and random walks
2016 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

Respondent-driven sampling (RDS) is a link-tracing sampling methodology especially suitable for sampling hidden populations. A clever sampling mechanism and inferential procedures that facilitate asymptotically unbiased population estimates has contributed to the rising popularity of the method. The papers in this thesis extend RDS estimation theory to some population structures to which the classical RDS estimation framework is not applicable and analyse the behaviour of the RDS recruitment process. 

Place, publisher, year, edition, pages
Stockholm: Department of Mathematics, Stockholm University, 2016. 46 p.
National Category
Probability Theory and Statistics
Research subject
Mathematical Statistics
Identifiers
urn:nbn:se:su:diva-129287 (URN)978-91-7649-430-1 (ISBN)
Public defence
2016-06-15, sal 14, hus 5, Kräftriket, Roslagsvägen 101, Stockholm, 10:00 (English)
Opponent
Supervisors
Funder
Swedish Research Council
Note

At the time of the doctoral defense, the following papers were unpublished and had a status as follows: Paper 2: In press. Paper 3: Accepted. Paper 4: Manuscript.

Available from: 2016-05-23 Created: 2016-04-20 Last updated: 2016-05-11Bibliographically approved

Open Access in DiVA

No full text

Other links

arXiv
By organisation
Department of Mathematics
Probability Theory and Statistics

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 4 hits
ReferencesLink to record
Permanent link

Direct link