Web-based Network Sampling: Efficiency and Efficacy of Respondent Driven Sampling for On-line Research

ondent-driven s were found to progress very fast. Studies with large samples can be expected to proceed up to 20 times faster than with traditional methods; in fact, to prevent bias from temporal filtering, d, because of sation should ential recruits. findings, based on theoretical and empirical evidence, indicate that web-based RDS can be much faster, easier, and cheaper than both regular RDS and standard sampling methods. Additionally, RDS estimates are compared to institutional data and potential sources of bias associated with the random recruitment assumption and sample size are discussed Abstract This study tests the feasibility, effectiveness, and efficiency of resp sampling (RDS) as a web-based sampling method. First, RDS referral chain studies with small target samples should limit hourly response rates. Secon the relative ease of the web-based RDS process for each recruit, compen remain low. High rewards appear too good to be true and may scare off pot The results also demonstrate that web-based RDS can be used with minimal staffing. Our 2