If you’re trying to find out the general population’s opinion about something, you can go door to door, or reach out to people in the streets, or try calling or mailing individuals; there are many ways. If you want to learn about a certain group—say cancer survivors, for example—you can probably get lists from somewhere. But how do you reach people who are hard to find or unwilling to reveal themselves, such as drug addicts or ex-convicts?
Snowball sampling is a survey method in which the researcher collects data on the few members of the target population he or she can locate and then asks those individuals to provide information needed to locate other members of that population whom they know. The “snowball effect” occurs as referrals multiply at each step. For example, if you get two referrals from each person, then if you started with two people, you’d get four referrals, then eight, sixteen, and so on.
This sampling method is suitable for researching populations that are difficult to locate. For instance, if you are studying the homeless, you are not likely to find a list of all the homeless people in your city. However, if you identify one or two homeless individuals that are willing to participate in your study, it is likely that they know other homeless individuals in their area and can help you locate them. The same goes for followers of underground subcultures or populations that might want to keep their identity hidden, such as undocumented immigrants.
See for yourself: http://explorable.com/snowball-sampling
Learn more about this method of reaching “hidden” (and often “forbidden”) populations at the links below.