Snowball Sampling

| No Comments


When selecting a sample to research there are various non-representative sampling techniques we discussed in class. One of these techniques is referred to snowballing. Dana Grinshpan from Government Executive has written an article titled "3 Bad Research Techniques That Will Ruin Your Work". These three techniques are: snowball sampling, snowball research and snowball point of view. As we learned in class, snowball sampling is a research method in which you identify a group that you wish to study and then ask members of the group to identify acquaintances to also join the study.

The article notes that although snowball sampling allows us to reach subjects we may have been unable to reach, the sample group is no longer random and no longer represents the population at large. Without a random sample, a researcher is unable to extrapolate their research to the population at large, and the value of research is diminished. Although this seems to be a convenient way to capture a sample of the correct people, it nullifies the results as being valid.

I have actually used the second technique called snowball research, which includes using sources from one article to find additional information on the subject. Previously, I had not known that this was not a proper way of conducting research. From this article I learned that using this research technique gives a narrow perspective on the subject and also can lead to serious gaps in an argument. Initially this seems like a great way to find additional sources but as mentioned in our textbook when we base our results on secondary research reports, they are inaccurate and should generally be avoided.

The third technique to avoid is snowball point-of-view. This is the tendency for individuals to test their hypothesis with positive examples as opposed to negative ones. This seems to be a social norm for people to find sources of information that prove their argument. The article mentions that this is typically found in political writing which leads to a biased perspective.

Although these techniques seem obvious when put on paper, they tend to be instinctive for novice researchers and those unaware of their consequences. Although snowball techniques are typically the most convenient forms of data collection, as we discussed in class these are non-representative. When results are non-representative they can not be reported to generalize an entire population. Generally, when the data can not support the population at large, it is useless.

Article Source:

Leave a comment

About this Entry

This page contains a single entry by buono004 published on November 16, 2012 1:25 PM.

Consumer Neuroscience was the previous entry in this blog.

Find recent content on the main index or look in the archives to find all content.