Skip to main content icon/video/no-internet
icon backReturn to Entries

Simple Random Sampling

Researchers are often faced with the task of making statements about entire populations. However, including every member of a population into a study is often not possible and simply not feasible. Thus, subsets of the population (samples) must be chosen to represent the population. If samples are collected properly, precise statements can be made about a population, with a fairly high degree of confidence, from relatively small samples. Numerous techniques have been developed to ensure that the subset, or sample, is representative of the overall population so generalizations can be made. Simple random sampling is a probability method of selecting a subset, or sample, from a larger population in such a manner that every element (individual member of the population whose characteristics are to be measured) has the same probability of being chosen into the sample during each stage of the sampling process.

Simple random sampling is one of the most basic and simplest forms of sampling used. The basic principle behind the method is that every element in a population retains the exact same probability of being selected into a sample. For example, a university campus has 2,000 parking spots and 6,000 students who applied for a parking permit. The 2,000 available permits are distributed so that each of the 6,000 students has the same probability of receiving a permit. This can be achieved by numerous means, such as putting names in a hat or using student identification numbers and a random number generator to choose the first 2,000 students. Typically, sampling in this manner is done without replacement. That is to say, once a student’s name is drawn it is removed from the pool of remaining students. Although this technically does impact the odds of the remaining students, during the initial setup each student has the exact same probability of selection. Sometimes, sampling with replacement is used to ensure exact probability of selection remains for each element.

Requirements

Simple random sampling requires a population, sampling frame, and elements. A population is the entire set of entities from which a sample will be drawn. In the previous example, the population is the 5,000 students. Elements are the individual members of the population. This could be people, families, nations, schools, classes or whatever the researcher is examining. In the example provided, the elements are the students. The sampling frame is similar but has an additional important feature. The sampling frame is a list of all of the elements or other units containing the elements in a population. In the example provided, a sampling frame would be a list of all of the student applicants. Developing a sampling frame and identifying all of the elements in a population can prove challenging for researchers. Some research environments are simply not conducive to this type of probability sampling. For example, conducting research on the homeless or research conducted in conflict-impacted areas may prove challenging to identify, or locate, members of the population. Developing the sampling frame can also prove challenging in less volatile environments. Something as simple as creating a sampling frame of faculty at a university can prove challenging. The conceptualization of “faculty,” or whatever the researcher is studying, is vitally important to the generation of a sampling frame. A major challenge faced by people who conduct polls is that the phonebook or voter registration rolls are not complete. The increase in cell phone use and reduction in landlines mean that attempting to use the phonebook as a sampling frame does not allow for the inclusion of those who have moved away from landlines, as such not everyone in the population has the equal probability of selection. Although it may seem insignificant, and the researcher could decide to create a sampling frame from the phonebook, there are systematic differences in age, sex, race, and voting tendencies that have been known to significantly impact findings. In simple random sampling, the researcher must be sure that any differences in characteristics between the sample and characteristics of the population are due purely to chance and not introduced by selection bias.

...

  • 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

Read next

More like this

Sage Recommends

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

close

Have you created a personal profile? Login or create a profile so that you can save clips, playlists and searches

close
close
close Signed In to profile You are signed in as:
close
Logged in Institution Institution