Opening the book…
When reading criminal justice research, one of the first questions you should ask is "Who or what was studied?" We have already seen that understanding a study's topic and research design is important, but it is also important to understand where the information came from. The answer to this question helps you decide how much confidence to place in the findings and whether they can be applied to other situations.
Researchers are often interested in understanding large groups of people, organizations, events, or records. For example, a researcher may want to learn about correctional officers who work for the Wisconsin Department of Corrections Division of Adult Institutions. As of June 2026, this population included approximately 2,601 correctional officers.1 In this example, and in many criminal justice studies, collecting information from every member of the group would often be expensive, time-consuming, and impractical. In this example, it could be possible to have every single correctional officer participate, but many populations in criminal justice are not as clearly defined or accessible to researchers. Instead, researchers typically collect information from a smaller group and use what they learn to better understand the larger group. Understanding this process is important for evidence-informed practitioners because it affects how much confidence we can place in a study's findings.
A population is the entire group a researcher wants to learn about.2 Researchers must clearly define the population they are studying.3 In the correctional officer example, the population is not simply "correctional officers." Instead, it is all correctional officers working in the Wisconsin Department of Corrections Division of Adult Institutions. Depending on the study, a population might also include all people released from county jails during a particular year, all police departments in a region, or all criminal cases processed by a court system. The population is the group that the researcher ultimately wants to draw conclusions about.
A sample is the smaller group from which the researcher actually collects information. Returning to the correctional officer example, a researcher interested in job satisfaction may not be able to survey all 2,601 officers. Instead, the researcher might survey 300 correctional officers and use their responses as the study's sample. The goal is to use information gathered from the sample to better understand the larger population of correctional officers.
Many researchers study samples rather than entire populations, making it important to consider whether the sample represents the population well. If the sample differs significantly from the larger population, the findings may not accurately reflect the experiences or views of the group being studied. For example, a researcher who surveys only correctional officers working at maximum-security institutions may not capture the experiences of officers working in medium-security, minimum-security, or specialized facilities. As informed consumers of research, you should consider who was included in the sample, who may have been excluded, and whether the sample appears reasonably representative of the larger population the researchers hope to understand.
The process of selecting a sample is called sampling. Researchers use different sampling methods depending on their research question, available resources, and the population they want to study. As evidence-informed practitioners, you do not need to become experts in sampling techniques. However, you should understand that the quality of a study's sample can affect the quality of its findings.
Sampling Methods
Researchers use different methods to select samples, but most sampling approaches can be grouped into two broad categories: random sampling and non-random sampling. Understanding the difference between these approaches can help you evaluate how much confidence to place in a study's findings.
Random Sampling
In random sampling, participants are selected by chance. Every member of the population has a known chance of being selected for the sample. For example, if a researcher wanted to study correctional officers working in Wisconsin's Division of Adult Institutions, they might use a list of all correctional officers and randomly select officers to participate in the study. Since participants are selected by chance rather than by researcher choice, random samples are often more likely to represent the larger population.
NOTE: Do not confuse random sampling with random assignment. Random sampling is used to select participants for a study, while random assignment is used in experiments to place participants into treatment and control groups. Researchers may use one, both, or neither depending on the purpose of the study.
Non-Random Sampling
In non-random sampling, participants are selected using methods other than chance. Researchers may choose people because they are easy to access, because they have specific experiences that are relevant to the study, or because they volunteer to participate. For example, a researcher studying correctional officer job satisfaction might survey only officers attending a professional training conference or interview officers who have worked in a particular type of institution. These approaches may provide useful information, but the resulting sample may not fully represent all correctional officers in Wisconsin.
Researchers use many different types of non-random sampling. The following sections introduce two common examples, convenience sampling and purposive sampling, because they are frequently used in criminal justice research. While other non-random sampling methods exist, understanding these two approaches will help you recognize and evaluate many of the studies you may encounter as a criminal justice practitioner.
Convenience Sampling
A convenience sample consists of participants who are easy for the researcher to access.4 Researchers may use convenience sampling when time, resources, or access to participants are limited. For example, a researcher might survey criminal justice students enrolled in a particular class because they are readily available. Convenience samples can provide useful information, but the findings may not represent the larger population.
Purposive Sampling
A purposive sample is created when researchers intentionally select participants because they have specific knowledge, experiences, or characteristics related to the research topic.5 For example, a researcher studying prison reentry may interview formerly incarcerated individuals who recently completed a reentry program. Purposive sampling allows researchers to gather information from people who can provide valuable insights about a particular issue. However, findings from purposive samples may not be applicable to a larger population.
Neither approach, random or non-random sampling, is automatically better than the other. The most appropriate sampling method depends on the purpose of the study. Researchers who want to describe a large population often prefer random sampling because it increases confidence that the sample reflects the larger group. Researchers seeking a deeper understanding of a particular experience or issue may use non-random sampling to identify participants who have specific knowledge or experiences related to the topic being studied.
Evaluating the Sample
As evidence-informed practitioners, you do not need to become experts in sampling methods. However, when reading research, it is important to ask how participants were selected. Studies that use random sampling are often more likely to include a sample that reflects the larger population, while studies that use non-random sampling may provide valuable insights but may be less applicable to other groups or settings. Understanding this distinction can help you better evaluate the strength and usefulness of research findings.
When evaluating research, it is important to look at who was included in the study and who may have been left out. Ask yourself: Does the sample appear to represent the population the researchers are trying to understand? The answer can help you determine how much confidence to place in the findings and whether they are applicable to the criminal justice issue, agency, or community you are interested in. It is also important to consider whether the findings apply to the specific population you are interested in. For example, findings from a study of correctional officers in Wisconsin may not automatically apply to police officers, probation officers, or correctional officers working in another state. Similar job roles may still differ in important ways, so practitioners should be cautious when applying research findings beyond the population that was actually studied.
Applying Findings Beyond the Sample
Researchers often collect information from a sample rather than an entire population. One reason the sample is important is that researchers usually hope to learn something about the larger population from which the sample was drawn. Generalizability refers to the extent to which findings from a sample can be applied to a larger population. In other words, generalizability helps us determine whether what researchers learned from a smaller group is likely to apply to the larger group they are trying to understand. For example, if researchers study a sample of Wisconsin correctional officers, generalizability refers to whether the findings can reasonably be applied to correctional officers throughout Wisconsin rather than only to the officers who participated in the study.
Studies that use representative samples are generally more likely to produce findings that reflect the larger population. A representative sample is a sample that closely resembles the larger population on important characteristics related to the study. Random sampling can help improve generalizability because members of the population are selected by chance rather than by researcher choice. For example, if a randomly selected sample of correctional officers closely reflects the characteristics of correctional officers throughout Wisconsin, researchers can be more confident that the findings apply to the larger population. Not all studies are designed to achieve a high degree of generalizability. Some researchers intentionally study smaller groups or people with specific experiences in order to gain a deeper understanding of a particular issue. These studies can still provide valuable information, but their findings may not apply as broadly to other people, agencies, or settings.
As evidence-informed practitioners, it is important to ask whether a study's findings can reasonably be applied beyond the sample that was studied. Understanding who participated in the research can help you determine whether the findings are relevant to the population, agency, or community you serve.
- Wisconsin Department of Corrections. (n.d.). Corrections staff overview dashboards. State of Wisconsin. https://doc.wi.gov/Pages/DataResearch/Corrections-Staff-Overview-Dashboards.aspx.
- (Blackstone, 2012).
- (Williams, 2022).
- (Williams, 2022).
- (Williams, 2022).
This page titled 7.1: Population, Samples, and Sampling was last modified on Tue, 03 Nov 2026 03:24:39 GMT and is shared under a CC BY-NC-SA 4.0 license and was authored, remixed, and/or curated by Denise Borchert, Western Technical College.
The book could not be loaded just now.