Why Four Population Terms Matter
A survey result is not meaningful until we know who the result is intended to describe. A campus questionnaire might reach students on one official email list, while its authors want to describe all students currently enrolled. A health survey might contact patients at a clinic but aim to describe people with a particular condition across a region. In each case, the group contacted, the group of interest, and the list used to make contact are related, but they are not automatically identical.
Four terms help make those relationships explicit: target population, sampled population, sample, and sampling frame. Stating each one carefully helps clarify what a survey can describe. It also prevents a common leap: assuming that because a group of people answered a survey, their answers necessarily represent everyone the researchers hoped to understand.
Separating the Terms
The target population is defined by the study’s question, not by the list that happens to be available. It should specify the relevant individuals and, when needed, the setting and time period. For example, “students” may be too vague if the question concerns current undergraduates at a particular campus during a particular academic term. A precise target population might be “all undergraduate students enrolled at North Campus in fall 2026.”
The sampled population names the group from which selection actually takes place. It may match the target population, or it may be narrower or otherwise different. Researchers might intend to describe all current undergraduates but have a usable list that contains only students registered for at least one in-person course. The list and the process determine which people can actually be selected; they do not redefine the original goal after the fact.
A sampling frame is not the population itself. It is the practical means of identifying units in the sampled population. It may be a student register, a clinic appointment database, a list of households, or a telephone-number database. A frame can identify people directly, or it can identify other units, such as households, that are relevant to the study. Its purpose is operational: it provides a basis for finding eligible units.
The sample consists of the units selected from the sampled population. In a survey, some selected people may not provide data. It is useful to state whether “sample” means the selected people or only those who responded, because those are not always the same set. Either way, a response does not change the definition of the target population: the target remains the group the study set out to describe.
| Term | Question it answers | Example |
|---|---|---|
| Target population | About whom do we want to draw conclusions? | All undergraduates enrolled at a campus in fall 2026 |
| Sampled population | From whom are units actually selected? | Undergraduates represented in the campus’s current registration system |
| Sampling frame | What source is used to identify units for selection? | The registration system’s student list |
| Sample | Which units were selected or observed? | The 250 students selected for the survey |
These are roles in a study, not necessarily four groups of different people. In a well-aligned design, the target population and sampled population may be the same, and the frame may list that population accurately. The sample is still a smaller selected set. In other designs, the target and sampled populations differ, or the frame does not represent every member of the sampled population. Naming the roles separately lets us describe the design rather than assume they coincide.
Worked Example: A Campus Survey
Suppose a university wants to estimate how many hours its undergraduate students study outside class during a typical week of fall term. The research team obtains an electronic list of students registered for at least one in-person course, randomly selects 180 names from that list, and receives completed surveys from 151 selected students. Identify the four terms, and note the distinction between selected and responding students.
Target population. The research question is about undergraduate students at the university during fall term. A precise target is all undergraduates enrolled at the university in fall term, with study hours referring to a typical week in that term. This definition includes the intended people and period.
Sampling frame. The electronic list of students registered for at least one in-person course is the frame: it is the operational source from which names are selected.
Sampled population. The group represented by that list—and therefore available for selection under this design—is undergraduates registered for at least one in-person course. This might not be exactly the same as all undergraduates enrolled at the university.
Sample. The 180 selected students are the selected sample. If the study uses “sample” to mean people who supplied survey data, then its respondent set contains 151 students. Stating which meaning is intended avoids treating all 180 selected students as if they had answered.
The key distinction is between the study’s goal and its available selection group. If some enrolled undergraduates are not represented on the list, they remain part of the target population as defined, even though they are not part of the sampled population described here.
Applying the Definitions Across Settings
In a health survey, the target population often depends on a health condition, location, and time. The sampled population may instead be determined by a clinic’s records or the institutions participating in the survey. In public-opinion research, the target might be eligible voters in a specified jurisdiction at a specified time, while a database or contact list supplies the frame. In both settings, use the same questions: Who is the study trying to describe? From whom can it select? What source identifies those units? Which units were selected or observed?
Worked Example: A Regional Health Survey
A health network wants to describe weekly physical activity among adults diagnosed with asthma who live in Pine County. It searches its patient database for adults with an asthma diagnosis and a current Pine County address, then selects 120 records for survey contact. Identify the target population, sampled population, sampling frame, and sample.
Target population. The stated goal concerns all adults diagnosed with asthma who live in Pine County during the period covered by the survey. The phrase “all adults” matters: the goal is broader than “patients of this health network” unless the research question explicitly limits itself to network patients.
Sampling frame. The health network’s patient database, after applying the diagnosis, age, and address criteria, is the frame used to find potential survey participants.
Sampled population. The group available for selection is the eligible adults with asthma who are represented in that network database and meet the stated criteria. It is not automatically every adult with asthma in Pine County.
Sample. The 120 records selected for contact identify the selected units. If the network later reports results from respondents only, it should distinguish those responding individuals from the 120 selected records.
This classification does not establish whether the selected group adequately represents the target; it makes clear which group was actually used. A conclusion intended for all county adults with asthma concerns a wider group than a conclusion limited to eligible network patients.
Worked Example: A Public-Opinion Survey
A research group asks, “What proportion of eligible voters in Lake City support a proposed transit measure in November 2026?” It uses a commercial list of registered voters with Lake City addresses, selects 400 entries, and records answers from 327 people. Identify the four terms and explain why “registered voters on the list” should not automatically be used as the target.
Target population. The question names eligible voters in Lake City in November 2026. The target is all people who meet that eligibility definition in the city at that time, not merely those who appear on the available commercial list.
Sampling frame. The commercial list of registered voters with Lake City addresses is the source used to identify and select entries. It is a frame, not a synonym for all eligible voters.
Sampled population. The group from which entries can actually be selected is the eligible-looking voter records represented on that list, subject to the criteria used to construct it. If the list includes only registered voters, for example, its represented group is not necessarily identical to every person who meets the target’s eligibility definition.
Sample. The 400 selected entries are the selected sample. The 327 people who provide answers are the respondents, a subset of the selected group.
The wording of the research question determines the target; the available list determines the frame. Changing the target to “people on the commercial list” simply because that is the source available would answer a narrower question than the one originally asked.
A Practical Way to Map a Study
A useful justification for keeping these terms separate is to trace the steps that connect a question to the data. The question identifies the target. A real selection process uses a frame to identify units from a sampled population. The selected units form the sample, and measurements are recorded for some or all of them. Each transition can involve a difference in who is included. Therefore, an accurate description of the target alone is not enough; the selection group, frame, and actual sample must also be named.
Specify who the study seeks to describe, and include the relevant place and time period.
Describe the sampled population from which units can actually be selected.
Identify the list, register, database, or other source used to locate eligible units.
State which units were selected and, when relevant, how many supplied data.
This sequence is a description of the study’s scope, not a method for choosing units. Two surveys may have the same target population but different sampled populations and frames. Conversely, two surveys may use the same frame but ask questions about different target populations. The terms let readers see those differences before interpreting any reported result.
Common Mistakes and Why the Distinction Matters
- Calling the frame the population. “We surveyed people on the database” identifies a source, not necessarily everyone the question is about. Name the intended group separately.
- Calling respondents the target population. Respondents are people who provided data. The target is the group the study hopes to describe, whether or not every member was contacted or answered.
- Leaving out place or time. “Adults with asthma” may be too broad. If the question concerns adults with asthma in Pine County during a defined period, say so.
- Using the sample to define the goal after the fact. If researchers wanted to study all campus undergraduates but selected from an in-person-course list, the target does not silently become “students on that list.” The two groups should be reported separately.
- Mixing up selected units and completed surveys. If 180 people are selected and 151 answer, those numbers describe different sets. Report both when the distinction is relevant.
These distinctions matter because a statistic calculated from observed data describes the sample directly, while a claim about a broader population requires a justified connection between the sample and that population. Carefully stating the four terms does not, by itself, guarantee that the connection is strong. It does show exactly which groups the claim would need to bridge and lets readers assess whether the study’s stated scope matches its evidence.
Check Your Understanding
For each item, identify the relevant terms or explain the distinction.
- A college wants to describe sleep duration among all first-year students enrolled in spring term. It selects students from its dormitory-resident list. Which group is the target population, and what is the sampling frame?
- A clinic uses its patient database to select 90 people with a particular diagnosis for a survey. Explain the difference between the database and the sampled population.
- A poll selects 500 people from a voter list, and 420 respond. Distinguish the selected sample from the respondent set.
- Why does a health survey’s target population not automatically become “the patients in the clinic database” just because that database was used?
- Rewrite “we surveyed students” as a more precise target-population description by adding a location and time period of your choice.