Adaptive Cluster Sampling in Large-Scale Data: Applications in Dynamic Social Network

Increasing data complexity and volume demand efficient, accurate sampling strategies for large-scale, dynamic populations, such as social networks. This paper examines the application of adaptive cluster sampling (ACS) in these situations, emphasizing its effectiveness in capturing hidden and rare clustered populations with greater efficiency and smaller sample sizes than conventional methods. By incorporating adaptive link-tracing techniques, ACS improves access to hard-to-reach, dynamic populations. With a design tailored for sampling units selection in evolving populations, this approach shows potential to enhance data reliability and its applications in data science.

Keywords:

Rare and Clustered Populations , Adaptive Cluster Sampling , Big Data , Dynamic Populations , Social Networks