Quota Sampling

Quota sampling uses key categories in the larger population to specify how many members of the sample should fall into each of those categories or combinations of categories. This sampling is a nonprobability technique because it requires only that the quota for each category be met without any further attention to how those sample members are actually located. For example, a study of social service organizations might set quotas for both the number of public and private providers and the number of larger and smaller agencies in the sample. Similarly, an interview study might select participants using a two-by-two table for gender and age so that one quarter of the informants were younger women, one quarter were older men, and so on.

Survey research originally used quota sampling as a quicker and cheaper alternative to random sampling, but abandoned this approach during the 1950s because of the potential for producing unrepresentative samples. Quota samples are not truly generalizable because even though the quota-based categories may match their size in the larger population, the sample may be unrepresentative on other characteristics outside the quota system. For example, in the population of older people, there are more women than there are men, but adjusting the quotas for a study of this group to reflect gender accurately would not ensure that the sample was representative with regard to income, health, frequency of family contacts, and so on.

In contrast, quota sampling in qualitative research is a specific technique for selecting a sample that has been defined using a purposive sampling strategy to define the categories of data sources that are eligible for a study. As a technique for selecting a sample in qualitative research projects, quota sampling is often connected to stratified sampling as a specific approach to purposive sampling. In particular, stratified sampling often breaks the population into theoretically specified categories for comparative purposes, and [Page 723]these categories would then be matched by quotas for data collection.

Another important use for quota sampling in qualitative research is not to create a representative sample, but rather to avoid bias on key characteristics, by assuring their inclusion in the sample. For purposive sampling, this process is much more likely to set quotas that match important substantive categories from study, rather than demographic or background characteristics that are not directly relevant to the topic of the study. For example, a study of how health affects older men and women would set quotas for gender and poor versus good health and then investigate how other factors, such as income and frequency of family contacts, operated within the key categories of interest. This demonstrates how quota sampling assures that the most important population categories will be adequately represented in the sample.