Skip to main content icon/video/no-internet

A population consists of all the objects or events of a certain type about which researchers seek knowledge or information. A population might be broad in scope (e.g., adult males living in the United States) or narrow (e.g., blog postings in the first 24 hours after a significant event). Even when a population consists of a relatively small number of objects or events, it is often impractical or impossible to gather data about each member of the population. Instead, researchers select a subset of the population, called a sample, which is a manageable size for observation. From their observations about the sample, researchers make generalizations about the population from which the sample was chosen. The ability of researchers to make generalizations depends on how representative the sample is of the target population.

Often when researchers talk about populations and samples, they are talking about the objects or events that they are observing. However, researchers also take other samples, such as selecting certain items from the universe of possible items to form a measurement scale. This entry describes general considerations for researchers when taking a sample from a population regardless of the type of population from which the researcher is sampling. Specifically, the entry discusses defining the population, sample representativeness, and generalizability. Then, the entry discusses the special example of selecting a sample of items from the universe of possible items to measure a particular construct.

Defining the Population

An important step that researchers take in designing their studies is to identify the population of objects or events that they want to understand. The universe of these objects or events is often called the target population. Target populations exist on many levels. They may include individuals, social roles (e.g., parents), positions (e.g., city health department directors), and relationships (marital partners). Target populations may also include social groupings, such as families, organizations, classrooms, cities. In addition, researchers often study nonhuman entities, such as news content, blog posts, videos, texts, and physical spaces. As part of their studies, researchers need to clearly define what units constitute the population. For example, when studying online comments, researchers need to determine whether individual posts make up the population or whether complete threads are the appropriate unit of analysis.

Once researchers have identified their units of analysis, they need to carefully define their population of interest, including key characteristics that should or should not be included in the population. For example, in a study of marital partners, a researcher might want to specify that the marital partners must be living in the same residence and have been married for a certain length of time. The researcher might also want to specify whether the population includes marital partners of the same or opposite sexes and/or whether the partners have or do not have children. Once researchers have considered important characteristics for inclusion and exclusion in the clearly defined population, they also need to identify known characteristics that exist in the population that are important to be represented in the population.

...

  • Loading...
locked icon

Sign in to access this content

Get a 30 day FREE TRIAL

  • Watch videos from a variety of sources bringing classroom topics to life
  • Read modern, diverse business cases
  • Explore hundreds of books and reference titles

Sage Recommends

We found other relevant content for you on other Sage platforms.

Loading