Snowball sampling

From Wikipedia, the free encyclopedia - View original article

 
Jump to: navigation, search
For other uses, see Snowball (disambiguation).

In sociology and statistics research, snowball sampling[1] (or chain sampling, chain-referral sampling, referral sampling[2][3]) is a non-probability sampling technique where existing study subjects recruit future subjects from among their acquaintances. Thus the sample group appears to grow like a rolling snowball (similarly to breadth-first search (BFS) in computer science). As the sample builds up, enough data are gathered to be useful for research. This sampling technique is often used in hidden populations which are difficult for researchers to access; example populations would be drug users or sex workers. As sample members are not selected from a sampling frame, snowball samples, analogously to BFS samples,[4][5] are subject to numerous biases. For example, people who have many friends are more likely to be recruited into the sample.

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[6][7][8] has been shown to allow researchers to make 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.

What is snowball sampling?[edit]

Snowball sampling uses a small pool of initial informants to nominate, through their social networks, other participants who meet the eligibility criteria and could potentially contribute to a specific study. The term "snowball sampling" reflects an analogy to a snowball increasing in size as it rolls downhill [9]

Snowball Sampling is a method a used to obtain research and knowledge, from extended associations, through previous acquaintances, "Snowball sampling uses recommendations to find people with the specific range of skills that has been determined as being useful." An individual or a group receives information from different places through a mutual intermediary. This is referred to metaphorically as snowball sampling because as more relationships are built through mutual association, more connections can be made through those new relationships and a plethora of information can be shared and collected, much like a snowball that rolls and increases in size as it collects more snow. Snowball sampling is a useful tool for building networks and increasing the number of participants. However, the success of this technique depends greatly on the initial contacts and connections made. Thus it is important to correlate with those that are popular and honorable to create more opportunities to grow, but also to create a credible and dependable reputation.

Method[edit]

  1. Draft up a participation program (likely to be subject to change, but indicative).
  2. Approach stakeholders and ask for contacts.
  3. Gain contacts and ask them to participate.
  4. Community issues groups may emerge that can be included in the participation program.
  5. Continue the snowballing with contacts to gain more stakeholders if necessary.
  6. Ensure a diversity of contacts by widening the profile of persons involved in the snowballing exercise.

Applications of snowball sampling[edit]

When to use[edit]

Pre-assumption:The participants are likely to know others who share the characteristics that make them eligible for inclusion in the study.[10]

There are many reasons why an individual may want to use snowball sampling across any industry, research, job, etc. Specific to business and marketing, however, snowball sampling can be used to things such as identify experts in a certain field, product, manufacturing processes, customer relation methods, etc. 3M did this when they were trying to identify experts in different fields of work in order to become the lead user for surgical drapes, the small plastic covering that is applied at the incision site of a surgery. To do this, 3M called in specialist from all fields that related to how a surgical drape could be applied to the body. For example, they called in a veterinarian, who specializes with surgeries on creatures with a lot of hair, and a Broadway make-up artist who specialized in applying foreign materials to human skin in a non-irritating manner. In order to successfully identify these people, 3m used snowball sampling. They called "experts" that they had contacts and after gathering information, asked them to suggest another expert that they may know who could offer more information. They repeated this process until they were satisfied with their experts and felt that they had found the most knowledgeable individuals in a specific field. Thus, snowball sampling can be used to gather expert information.

Advantages[edit]

1. Locate hidden populations: It is possible for the surveyors to include people in the survey that they would not have known.

2. Locating people of a specific population: There is no lists or other obvious sources for locating members of the population of specific interest.

Disadvantages[edit]

1. Community Bias: The first participants will have strong impact on the sample. Snowball sampling is inexact, and can produce varied and inaccurate results. The method is heavily reliant on the skill of the individual conducting the actual sampling, and that individual’s ability to vertically network and find an appropriate sample. To be successful requires previous contacts within the target areas, and the ability to keep the information flow going throughout the target group.

2. Not Random: Snowball sampling contradicts many of the assumptions supporting conventional notions of random selection and representativeness[11] However, Social systems are beyond researcher’s ability to recruit randomly. Snowball sampling is inevitable in social systems.

3. Vague Overall Sampling Size: There is no way to know the total size of the overall population.[12]

4. Wrong Archoring: Another disadvantage of snowball sampling is the lack of definite knowledge as to whether or not the sample is an accurate reading of the target population. By targeting only a few select people, it is not always indicative of the actual trends within the result group. Identifying the appropriate person to conduct the sampling, as well as locating the correct targets is a time consuming process which renders the benefits only slightly outweighing the costs.

Examples[edit]

Positive[edit]

When attempting to gather information about a particular topic, and a limited number of participants or test subjects are available, snowball sampling would increase the efficiency of the study. It is cost efficient to use this method because locating respondents to acquire information may take time and finances. In order to acquire more participants, snowball sampling relies on referrals and by word of mouth. The more effort that goes into the preliminary rounds of the study, contacting people and spreading the word of the main goals of the study,will pay dividends in the long run due to the increase in size of the overall study sample. Bias plays a major role within every study, and increasing the amount of participants will only help the accuracy of the information.

A positive example of snowball sampling would be if a researcher is having trouble reaching individuals within its target market. For instance, if someone was attempting to do a research sample involving football players because they were trying to sell a customized piece of equipment, they would need to meet with some players to get their point of view about the product. If the researcher only knew a few players, they would have to go out and personally introduce themselves to other players to expand their study. They could contact the player or players that they already know and ask them to refer them to a few others. They could offer a small incentive to quicken the process, and maybe this perk would attract other players to participate in the study. They could also gain access to the roster from the school’s website and try and contact players via email or telephone. The more relationships they create, the more information they will receive. If they put the effort in to meet with a few kids from a few different teams, they would have the opportunity to be referred to by every kid on the team. The snowball effect would occur as more and more referrals are acquired. If I was attempting this study I would try and meet with the captain or seniors on the team and offer incentives to them. If you attract the "best" players to be involved within your study, it is a safe assumption to say that others will follow. Another example would be drug dealers. Although the topic is inappropriate, it is a good example to explain the essence of snowball sampling. As the dealer brings in product, they need to find customers to move their product. Everyone they sell their products to can refer them to other potential customers which will increase their business and continue to make them revenue.

In the area of deviant behavior, especially research on drug use and addicion, snowball sampling has been used to gather materials for studies now thought of as classics in the field. The overall objective of the study was to gain some understanding of the processes that result in the "natural" recovery from heroin addiction, to understand how some people manage to break an addiction to herion without the aid of any therapeutic intervention.[13]

Negative[edit]

Snowball sampling can be a strenuous process at times if not planned out properly. A number of issues can arise when using snowball sampling as a method for gathering information. For instance, if a marketing team is trying to gather information that will result in a new, innovative product that can spur the business’s success and develop a competitive advantage. As the marketing team contacts people throughout their respective customer base and other important individuals in their industry, a number of challenges or barriers may develop. Certain individuals may become resistant and not want to provide referrals based upon the people they know who may possibly help the firm’s efforts. If this information cannot be obtained, the targeted individuals the team is seeking may not be complete and vital ideas generated from such individuals will not be taken into consideration. Resistance to providing referrals will cause the team to waste time having to research new contacts to get in touch with. This inability to gather appropriate information from select participants and loss of time will possibly jeopardize the opportunity to develop an innovative product in time and allow competitors to take advantage of this setback. This negative example of snowball sampling illustrates some of the difficulties associated with utilizing snowball sampling as a method for gathering information from select individuals.

Although chain referral sampling has been widely used in qualitative social research, the procedures and problems entailed in its use have received only cursory attention. A number of problems are involved in using it to gather study materials, some of which are purely methodological in nature and others which emanate from particular constraints formed by the research focus. Moreover, one broad issue to be addressed concerns the generality of data provided by the snowball method. Are the findings limited to the sample alone? Or is the sample's generality limited ony to a population that has undergoune similar social experiences?[14]

Improvements for snowball sampling[edit]

Snowball sampling is a recruitment method that employs research into participants' social networks to access specific populations. According to research mentioned in the paper written by Kath Browne,[15] using social networks to research is accessible. In this research, Kath Browne used social networks to research non-heterosexual women. Snowball sampling is often used because the population under investigation is hard to approachable either due to low numbers of potential participants or the sensitivity of the topic. The author indicated the recruitment technique of snowball sampling, which uses interpersonal relations and connections within people.Due to the use of social networks and interpersonal relations, snowball sampling forms how individuals act and interact in focus groups, couple interviews and interviews. As a result, snowball sampling not only results in the recruitment of particular samples, use of this technique produces participants'accounts of their lives. To help mitigate these risks, it is important to not rely on any one single method of sampling to gather data about a target sector. In order to most accurately obtain information, a company must do everything it possibly can to ensure that the sampling is controlled. Also, it is imperative that the correct personnel is used to execute the actual sampling, because one missed opportunity could skew the results.

respondent-driven sampling[edit]

A new approach to the study of hidden populations. It is effectively used to avoid bias in snowball sampling. Respondent driven sampling involves both a field sampling technique and custom estimation procedures that correct for the presence of homophily on attributes in the population. The respondent-driven sampling method employs a dual system of structured incentives to overcome some of the deficiencies of such samples. Like other chain-referral methods, RDS assumes that those best able to access members of hidden populations are their own peers. [16]

References[edit]

  1. ^ Goodman, L.A. (1961). "Snowball sampling". Annals of Mathematical Statistics 32 (1): 148–170. doi:10.1214/aoms/1177705148. 
  2. ^ "Snowball Sampling". Experiment-resources.com.  (accessed 8 May 2011).
  3. ^ Snowball Sampling, Changing Minds.org, http://changingminds.org/explanations/research/sampling/snowball_sampling.htm (accessed 8 May 2011).
  4. ^ Kurant, M.; Markopoulou, A.; Thiran., P. (2010). "On the bias of BFS (Breadth First Search)". International Teletraffic Congress (ITC 22). 
  5. ^ Kurant, M.; Markopoulou, A.; Thiran., P. (2011). "Towards Unbiased BFS Sampling". IEEE JSAC 29 (9): 1799–1809. 
  6. ^ Heckathorn, D.D. (1997). "Respondent-Driven Sampling: A New Approach to the Study of Hidden Populations". Social Problems 44 (2): 174–199. doi:10.1525/sp.1997.44.2.03x0221m. 
  7. ^ Salganik, M.J. and D.D. Heckathorn (2004). "Sampling and Estimation in Hidden Populations Using Respondent-Driven Sampling". Sociological Methodology 34 (1): 193–239. doi:10.1111/j.0081-1750.2004.00152.x. 
  8. ^ Heckathorn, D.D. (2002). "Respondent-Driven Sampling II: Deriving Valid Estimates from Chain-Referral Samples of Hidden Populations". Social Problems 49 (1): 11–34. doi:10.1525/sp.2002.49.1.11. 
  9. ^ David L., Morgan (2008). The SAGE Encyclopedia of Qualitative Research Methods. SAGE Publications, Inc. pp. 816–817. ISBN 9781412941631. 
  10. ^ David L., Morgan (2008). The SAGE Encyclopedia of Qualitative Research Methods. SAGE Publications, Inc. pp. 816–817. ISBN 9781412941631. 
  11. ^ Atkinson, Rowland; Flint, John (2004). Encyclopedia of Social Science Research Methods. SAGE Publications, Inc. pp. 1044–1045. ISBN 9780761923633. 
  12. ^ David L., Morgan (2008). The SAGE Encyclopedia of Qualitative Research Methods. SAGE Publications, Inc. pp. 816–817. ISBN 9781412941631. 
  13. ^ Browne, Kath (2005). "Snowball sampling: using social networks to research non‐heterosexual women". International Journal of Social Research Methodology 8 (1). 
  14. ^ Browne, Kath (2005). "Snowball sampling: using social networks to research non‐heterosexual women". International Journal of Social Research Methodology 8 (1). 
  15. ^ Biernacki, Patrick; Waldorf, Dan (1981). "Snowball Sampling: Problems and Techniques of Chain Referral Sampling". Sociological Methods & Research 32 (1): 148–170. doi:10.1177/004912418101000205. 
  16. ^ http://www.respondentdrivensampling.org/reports/RDSsummary.htm

External links[edit]