Probability vs. Nonprobability Sampling: From the Birth of Survey Sampling to the Present Day

At the beginning of 20th century, there was an active debate about random selection units versus purposive groups for survey samples. Neyman’s (1934) paper tilted balance strongly towards varieties probability sampling combined with design-based inference, and most national statistical offices have adopted this method their major surveys. However, nonprobability has remained in widespread use many areas application, over time been challenges to Neyman paradigm. In recent years, greater several reasons, including: growing imperfections costs applying sample designs; emergence internet other sources obtaining data from very large samples at low cost high speed; current ability apply advanced methods calibrating conform external population controls. This presents overview history birth A. N. Kiær (1895) present day.