Items or individuals are selected without knowing their probabilities of selection. A common type of non-probability sampling is convenience sampling. Non-probability sampling can be more convenient, quick, and inexpensive than probability sampling. However, non-probability sampling can create a lack of accuracy due to selection bias, and the theories that support probability samples are inapplicable. While people often assume that respondents obtained from a panel represent a probability sample, this may not be true if the composition of the sampling frame is drastically different from the composition of the real market.
See this article from Pew Research.
« Back to Glossary Index
