RDS main

NEW: RDS Authors, we are putting together a database of RDS related publications as a reference tool for researchers. If you would like us to include your RDS related publication(s), Click Here.

What is Respondent Driven Sampling ?

Respondent-driven sampling (RDS), combines "snowball sampling" with a mathematical model that weights the sample to compensate for the fact that the sample was collected in a non-random way. More.

Data Requirements for RDS Analysis

While data requirements for RDS analysis are minimal, there are three fields which are essential for analysis (NOTE: RDS analysis CAN NOT BE PREFORMED without these fields for each respondent):

Personal Network Size (Degree) - Number of people the respondent knows within the target population.
Respondent's Serial Number - Serial number of the coupon the respondent was recruited with.
Respondent's Recruiting Serial Numbers - Serial numbers from the coupons the respondent is given to recruit others.

References

NEW! RDS Publication Archive
Respondent-Driven Sampling References
Peer-Driven Intervention References

Core RDS References:

Heckathorn, Douglas D. 1997." Respondent-Driven Sampling: A New Approach to the Study of Hidden Populations." Social Problems.

The original article in which RDS was introduced

Heckathorn, Douglas D. 2002." Respondent-Driven Sampling II: Deriving Valid Population Estimates from Chain-Referral Samples of Hidden Populations." Social Problems.

Article extending the RDS method to include calculation of standard errors and post-stratification to control for differences in network size and clustering across groups

Salganik, Matthew J. and Douglas D. Heckathorn. 2004. "Sampling and Estimation in Hidden Populations Using Respondent-Driven Sampling." Sociological Methodology.

Article showing through both analytic means and simulations that the RDS population estimator is statistically unbiased
Outstanding Article Publication Award of the Mathematical Sociology Section of the American Sociological Association
“Making Unbiased Estimates from Hidden Populations Using Respondent-Driven Sampling.” Paper presented at the International Social Network Conference, February, 2003, Cancun, Mexico

Heckathorn, Douglas D. 2007." Extensions of Respondent-Driven Sampling: Analyzing Continuous Variables and Controlling for Differential Recruitment." Sociological Methodology.

Wejnert, Cyprian and Douglas D. Heckathorn. "Web-Based Network Sampling: Efficiency and Efficancy of Respondent-Driven Sampling for Online Research." Forthcoming - Sociological Methods and Research.
- This Article presents WebRDS as an online sampling method, compares RDS estimates to institutional data, and provides a test of several assumptions associated with RDS.

Downloads

In order to help the community take advantage of the Respondent Driven Sampling methodology, we have developed a software package capable of analysing RDS data sets. The Respondent Driven Sampling Analysis Tool (RDSAT) includes the following features:

Estimation of important population parameters such as

Population proportions of user defined groups

Average personal network sizes

Homophily

Measures of statistical significance for population estimates

Data display and editing
Export of analysis results to formatted html
Data visualization and graphics
Analysis of groups defined by a breakpoint of a continuous variable

Updates

Updates in 5.0
Updates in 5.2.beta
Updates in 5.3

Documentation for RDSAT:

RDSAT 5.6 User Manual

Manual Supplements and Extras:

Training Videos Downloads:

Importing SAS, SPSS, and STATA Data Into RDSAT (8.8 MB)

About RDSAT

Primary author of RDSAT: Erik Volz
Current maintainers of RDSAT: Cyprian Wejnert and Ismail Degani

How to Cite RDSAT:
Volz, E., Wejnert, C., Degani, I., and Heckathorn, D. D. 2007 Respondent-Driven Sampling Analysis Tool (RDSAT) Version 5.6. Ithaca, NY: Cornell University.

RDSAT Download Options:
RDSAT v.5.4 is now available for Linux, Mac, and Windows operating systems. There are several download options, depending on your operating system, and system configuration. RDSAT was developed in JAVA, and can be run on any machine which has a JAVA Runtime Environment installed on it. For users who have a recent JAVA Runtime Environment (v.1.4 or greater), you may download option #1 below. If you do not have the JAVA Runtime Environment, you have two options: Get the latest JAVA RE from http://java.com/en/download/manual.jsp, and then download option #1 below. Or, you may download option #2 below, which includes a JAVA runtime; note that option#2 is a much larger file. As a final option, if you do not want an installation program, you may download the executable JAR file listed as option#3.

Special Instructions for Vista Users:
To install RDSAT in a Vista system, please try to the following. During the setup process, when you get to the Select Destination Directory screen, do not choose the default, which is something like, C:\Program Files\rdsatdw\

Instead, choose an alternative, such as C:\rdsatdw\ (i.e., delete the text, "\Program Files").

This change in the installation procedure is necessary when using Vista, because users do not have read/write access to files in the Program Files folder, so the program would not be able to create and delete files in the manner necessary for the program to function.

**Linux/Unix**
Option#1	RDSAT_unix_5_6.sh	1.2 MB
Option#2	RDSAT_linux_5_6.rpm	1.2 MB

**Windows**
Option#1	RDSAT_windows_5_6_noJRE.exe	1.7MB
Option#2	RDSAT_windows_5_6.exe (includes JVM)	15MB

If you aready have an earlier version of RDSAT, use Option#1 (see RDSAT Options for details)

**Mac**
Option#1	RDSAT_macos_5_6.dmg	1.0MB

RDSAT was orginally created by Erik Volz, Cornell University.

NEW!

RDSAT 6.0 Beta integrates new analytical methods presented in Heckathorn (2007) and is now available for advanced users.

Reporting Bugs:

If you encounter a bug while using RDSAT, there is a simple way to report it. You will find a 'error.log' file in your installation directory. Simply email deganii@gmail.com with a description of the bug, and attach the error.log file.

RDS Coupon Manager:

The Respondent Driven Sampling Coupon Manager (RDSCM) provides a convenient way to keep track of coupons numbers and respondent compensation.

Default password for RDSCM is "password" (all lowercase)
RDSCM is available three languages: English, Spanish, and Russian.

Download RDSCM:

Contact:

Douglas Heckathorn is the originator of Respondent Driven Sampling. He can be reached at:

Department of Sociology
Cornell University
Ithaca, NY 14850

Email: douglas.heckathorn@cornell.edu

Fax: 607.255.8473
Voice: 607.255.4368
Internet: http://www.soc.cornell.edu/faculty/heckathorn.shtml

Direct questions, issues and bug reports regarding the software to:

Ismail Deganii
Email: deganii@gmail.com

Document last updated: 04/21/06