A convenience sample is a sample of study subjects taken from a group which is conveniently accessible to a researcher. The advantage of a convenience sample is that it is easy to access, requiring little effort on the part of the researcher. The disadvantage is that it is not an accurate representation of the population, which can skew the results quite radically. In fact, convenience sampling is regarded as a form of sampling bias, meaning that the results from a study conducted with such a sample cannot be generalized to the population as a whole.

In a classic example of a convenience sample, sociology students might want to conduct a survey to learn more about a particular sociological issue, such as the connection between certain beliefs about society and income. The students might distribute the survey to their classmates, because the members of the class are easy to access, and they will likely get a high response rate, as the class members recognize the value of collecting as much data as possible.

Any number of biases can occur in a convenience sample. By selecting from a specific population, such as students enrolled in Sociology 101, people who visit Mall X between 10 and 2:00 on Saturdays, or library patrons, the study inadvertently excludes a great deal of the population. Sometimes, this is not a problem. For example, a study on library patrons could easily take a convenience sample of library patrons and generalize the results. On the other hand, a study on social attitudes towards people with disabilities could not use the students in a sociology class as a convenience sample, as the sociology class does not represent an accurate cross-section of the population.

Researchers who want more valid results will take a probability sample, which attempts to get an accurate representation of the population. It's not possible to study everyone, but it is possible to randomly assign people to a study with an eye towards retaining a balance of characteristics seen in the population in general. For example, organizations which conduct political polling draw on a large database of people to select study subjects randomly.

If a convenience sample is used, by convention, researchers must disclose this. In fact, good research always includes a detailed overview of the research techniques used, so that people reading about the research have a better understanding of how it was conducted. When revealing that a convenience sample was used, the researcher may also present justifications for the use of this type of sample population, and discuss the ramifications of the results in light of the fact that a convenience sample was used.