Editing Snowball sampling (section)

{{Short description|Nonprobability statistical sampling technique}}
{{other uses|Snowball (disambiguation)}}
{{Use dmy dates|date=March 2023}}
In [[sociology]] and [[statistics]] research, '''snowball sampling'''<ref>{{cite journal | author= Goodman, L.A. | title= Snowball sampling| journal= Annals of Mathematical Statistics| year= 1961| volume= 32 | issue= 1| pages= 148–170 | doi= 10.1214/aoms/1177705148| doi-access= free}}</ref> (or '''chain sampling''', '''chain-referral sampling''', '''referral sampling'''<ref>{{cite news |title=Snowball Sampling |agency=Experiment-resources.com |url=http://www.experiment-resources.com/snowball-sampling.html}} (accessed 8 May 2011).</ref><ref>{{Cite web |title=Snowball sampling |url=http://changingminds.org/explanations/research/sampling/snowball_sampling.htm |access-date=2022-11-17 |website=changingminds.org}}</ref>) is a [[nonprobability sampling]] technique where existing study subjects recruit future subjects from among their acquaintances. Thus the sample group is said to grow like a rolling snowball. As the sample builds up, enough data are gathered to be useful for research. This sampling technique is often used in hidden populations, such as drug users or sex workers, which are difficult for researchers to access.
As sample members are not selected from a [[sampling frame]], snowball samples are subject to numerous [[Sampling bias|biases]].  For example, people who have many friends are more likely to be recruited into the sample. When virtual social networks are used, then this technique is called virtual snowball sampling.<ref name="Baltar"/>

It was widely believed that it was impossible to make unbiased estimates from snowball samples, but a variation of snowball sampling called '''respondent-driven sampling'''<ref>
{{cite journal | first1= D.D. |last1= Heckathorn| title= Respondent-Driven Sampling: A New Approach to the Study of Hidden Populations| journal= Social Problems| year= 1997| volume= 44 | issue= 2| pages= 174–199| doi= 10.1525/sp.1997.44.2.03x0221m}}
</ref><ref>
{{cite journal | author1= Salganik, M.J. |author-link1=Matthew J. Salganik|author2= D.D. Heckathorn| title= Sampling and Estimation in Hidden Populations Using Respondent-Driven Sampling| journal= Sociological Methodology| year= 2004| volume= 34 | issue= 1| pages= 193–239| doi= 10.1111/j.0081-1750.2004.00152.x|s2cid=16626030}}</ref><ref>
{{cite journal | first1= D.D. |last1= Heckathorn| title= Respondent-Driven Sampling II: Deriving Valid Estimates from Chain-Referral Samples of Hidden Populations| journal= Social Problems| year= 2002| volume= 49 | issue= 1| pages= 11–34| doi= 10.1525/sp.2002.49.1.11}}</ref>
has been shown to allow researchers to make [[asymptotic analysis|asymptotically]] unbiased estimates from snowball samples under certain conditions.  Snowball sampling and respondent-driven sampling also allows researchers to make estimates about the [[social network]] connecting the hidden population.