Sampling Algorithms

This book provides a comprehensive overview of innovative sampling methods. Building on the foundations of general sampling theory, it offers a rigorous yet accessible framework for understanding and implementing modern sampling algorithms.

Sampling has undergone a profound transformation since the early 2000s. This new edition has been substantially expanded and offers a far more comprehensive treatment than the first, providing both broader scope and greater depth in modern sampling methodology. It places particular emphasis on state-of-the-art approaches, including systematic and quasi-systematic designs; maximum entropy sampling designs; balanced sampling and its variants; spatial and spread sampling that ensure geographic dispersion for autocorrelated variables; sample coordination for repeated surveys; and sampling from data streams for real-time signal analysis. Sampling enables big data reduction, illustrating how sampling theory can efficiently handle massive datasets.

Each method is presented in detail with an emphasis on practical implementation. Numerous techniques are illustrated using the R programming language, and fully functional code is provided to facilitate immediate application.

This book is intended for master's and doctoral students, as well as experienced statisticians and researchers who already have a good grasp of sampling theory and wish to enrich their toolbox with theory-based, ready-to-implement techniques.