Not sure which lesson to do first? Find your level and get a plan →

Statistics · Grade 6-8

Population vs Sample

In statistics, the population is the entire group of individuals or items you want to study, while the sample is the smaller subset you actually collect data from.


Quick Answer

In statistics, the population is the entire group of individuals or items you want to study, while the sample is the smaller subset you actually collect data from. We use sample statistics to estimate unknown population parameters. Name the population first, because it decides what your numbers describe: if 130 of 200 sampled students want a later school start, 65% is a fact about the sample and only an estimate for the district's 10,000 students. Population values are parameters, such as μ; sample values are statistics, such as xˉ.

Why This Matters

Almost every number in the news is a sample standing in for a population: a poll of 1,000 voters, a test of 50 batteries from a batch of 10,000. Knowing which is which tells you what a number can claim and how sure to be. Mixing them up leads to treating a sample's 52% as an exact fact, or to generalizing about a group that was never studied.

Intuitive Explanation

A doctor checking your blood takes a few millilitres, not all of it. All of your blood is the population, everything the doctor wants to know about. The few millilitres in the tube are the sample, the part actually measured. The test works because blood is well mixed, so the tube looks like the rest. Statistics works the same way: measure a sample, then reason about the population it came from.

Numbers get different names depending on where they come from. A number describing the whole population is a parameter, such as the true mean height μ of all 10,000 students in a district. It is fixed but usually unknown. A number calculated from the sample is a statistic, such as the mean xˉ of 200 measured students. Statistics change from sample to sample; the parameter does not. The letters help: Greek for the population (μ, σ, N), Latin for the sample (xˉ, s, n).

Population and sample are roles, not sizes. If a teacher wants to know about her own class of 28, those 28 are the population, and measuring all of them is a census whose mean is a parameter, with nothing left to estimate. The same 28 become a sample the moment the question is about all 7th graders in the state, and then you must ask whether they represent that bigger group.

Think of it like this. The population is the whole pot of soup and the sample is the spoonful you taste. A spoonful from a well-stirred pot tells you about the pot; one skimmed from the unstirred top may not. People cannot be stirred, so statisticians mix them in a different way: by choosing the sample by chance.

Core idea. Every study has a population it wants to describe and a sample it actually measures; sample statistics estimate population parameters, so a result describes the sample exactly and the population only approximately.


When to Use

Sort out population and sample whenever a problem describes who was studied and then makes a claim about a larger group: "a survey of 200 students", "a test of 50 batteries". The group the question is about is the population; the measured part is the sample. If every member was measured, it is a census and its results are parameters. If the question is about how the sample was chosen, turn to sampling bias and random sampling.

Tip. Ask: Must you decide whether a number describes everyone in the group you care about or only the members actually measured?

How to Recognize It

Before working with a survey or study number, find the whole group the question is about and the smaller group that was actually measured.

  1. Does the problem name a whole group you want conclusions about, such as all students in a district?

    Yes, that group is the population, and it decides what your numbers can describe. If no such group is named, ask who the result is supposed to be about before going further.

  2. Was data collected from only some members of that group?

    Yes means those members are the sample, and their numbers are statistics that estimate the population's parameters. If the task is to list every possible outcome of a coin or die, that is Sample Space.

  3. Is a value written with a Greek letter such as μ, or a Latin one such as xˉ?

    Greek letters stand for population parameters, which are usually unknown; Latin letters stand for sample statistics, which you can calculate from the data you have.

  4. Is the real worry how the members were picked rather than which group is which?

    Then the question has moved past naming the groups to whether the sample is fair, which is Sampling Bias or Random Sampling.

Population vs Sample vs Sample Space vs Sampling Bias vs Random Sampling

The word sample shows up in all four, which is why they blur together. Ask whether you are naming groups, listing chance outcomes, judging how a sample was picked, or describing a fair way to pick it.

Population vs Sample

Meaning
The population is the whole group a question is about, and the sample is the part of it that was actually measured.
Key test
Does this number describe everyone, or only those who were measured?
Example
All 10,000 district students are the population; the 200 surveyed are the sample, and their 65% estimates the district's share.

Sample Space

Meaning
The sample space is the list of every possible outcome of a chance process.
Key test
Lists outcomes of a chance event, not people chosen from a group.
Formula
S={1,2,3,4,5,6}
Example
Spinning a spinner with red, blue and green parts has the sample space red, blue, green.

Sampling Bias

Meaning
Sampling bias is a way of choosing the sample that keeps favoring some members of the population over others.
Key test
Asks whether the way the sample was chosen tilts the results.
Example
Asking only chess club members about favorite hobbies over-counts chess.

Random Sampling

Meaning
Random sampling uses chance to choose the sample, so every member of the population has the same chance of being picked.
Key test
Describes a fair way to choose the sample from the population.
Example
Drawing 200 student ID numbers at random from the full district list.

Formula & Notation

How to read it: Population parameters use Greek letters: μ (mean), σ (standard deviation), N (size). Sample statistics use Latin letters: xˉ (mean), s (standard deviation), n (size).

Worked Examples

Example 1 — Name the parts of a survey

Easy

A district has 10,000 students. Researchers randomly select 200 of them, and 130 say they want school to start later. Identify the population, the sample, the statistic and the parameter, and estimate how many students in the district want a later start.
Show the steps and the answer
  1. Population: all 10,000 students in the district.

    The question is about what the district's students want, so that whole group is the population.

  2. Sample: the 200 students who were asked.

    These are the only students whose answers were collected.

  3. Statistic: 130200=0.65, so 65% of the sample.

    It is calculated from the sample, so it is known exactly but describes only those 200.

  4. Parameter: the true share of all 10,000 students who want a later start, which is unknown. Estimate it with the statistic: 0.65×10,000=6,500.

    A random sample's statistic is a reasonable estimate of the parameter, though another sample could give a slightly different number.

Answer: Population: 10,000 students; sample: 200 students; statistic: 65%; parameter: the true district share (unknown). Estimate: about 6,500 students.

Takeaway: Statistics come from the sample and are known; parameters belong to the population and are estimated.

Example 2 — When the whole class is the population

Standard

A teacher records the test scores of all 28 students in her class and finds a mean of 81. (a) If she wants to describe her class, is 81 a statistic or a parameter? (b) What if she wants to describe all 7th graders in her state?
Show the steps and the answer
  1. (a) The population is her class of 28, and all 28 were measured.

    Measuring every member of the population is a census, so there is nothing left to estimate.

  2. So μ=81 exactly: a parameter.

    A number describing the whole population is a parameter, however small the population is.

  3. (b) Now the population is every 7th grader in the state, and her 28 students are a sample, so xˉ=81 is a statistic.

    The same numbers change roles when the question names a bigger group.

  4. Ask whether the class represents the state: it was not chosen at random, and one school may differ from others.

    A sample only supports claims about a population it fairly represents.

Answer: (a) A parameter, the exact class mean. (b) A statistic from a sample that was not chosen at random, so it is a weak estimate of the state mean.

Takeaway: Population and sample are set by the question being asked, not by how many people were measured.

Example 3 — Find the mistake: a statistic treated as exact

Application

A random poll of 400 voters in a town of 20,000 finds 52% support a new park. Ravi writes: "Exactly 52% of the town, 10,400 people, support the park, so it will win the vote." Find the mistake and correct it.
Show the steps and the answer
  1. Label the 52%: it is a statistic from 400 voters, not the parameter for all 20,000.

    Ravi treated the sample's value as if it were the population's exact value.

  2. Recall that another random sample of 400 could easily give 49% or 55%.

    Statistics vary from sample to sample; a random sample of 400 typically lands within about 5 percentage points of the truth.

  3. State the range: roughly 52%−5%=47% to 52%+5%=57%.

    Part of that range is below 50%, so the poll cannot say which side will win.

  4. Keep his estimate but mark it as one: about 0.52×20,000=10,400 supporters.

    The arithmetic is fine; only the word "exactly" and the prediction are wrong.

Answer: The poll estimates that about 52% (roughly 47% to 57%) of voters support the park, around 10,400 people; it does not show that the park will win.

Takeaway: A sample result is an estimate of the population value, so report it with its uncertainty, never as an exact fact.

Where You'll See It

  • Average height of all 8th graders

    The population is every 8th grader in the country; you can't measure them all, so you measure a sample of 500 and use their average to estimate the population's average.

  • Tasting soup

    The whole pot is the population and the spoonful you taste is the sample — but only if you stir first, so the spoonful represents the whole pot.

  • Video game review scores

    If you want to know what all players think of a game (population) but only read 50 online reviews (sample), your estimate may be off because reviewers are a self-selected, not representative, subset.

Common Mistakes

  1. The slip: A statistic from the sample is the exact value for the whole population.

    Why it's tempting: If the sample average is 162 cm, it feels like the population average must be 162 cm.

    Instead: A sample statistic ESTIMATES the population parameter with some error. The parameter is fixed but usually unknown; the statistic varies from sample to sample.

  2. The slip: If the sample is huge, you don't need to worry about how it was chosen.

    Why it's tempting: A large sample feels like it must cover everyone.

    Instead: A large but biased sample (e.g., only your friends) still misrepresents the population. Representativeness depends on the sampling method, not just size.

  3. The slip: The population is always 'a lot of people' and a sample is 'a few people.'

    Why it's tempting: Students anchor on size to tell them apart.

    Instead: Population vs sample is about ROLE, not size: the population is the entire group you want to describe, and the sample is the subset you actually collect data from — the population could even be small.


Mini Practice

Try these on your own. Tap Reveal when you want to check.

  1. A city wants the average number of books read last summer by its 5,000 middle schoolers. It surveys 250 of them. Name the population, the sample, and the sample size.

    Hint: Who is the question about, and who actually answered?

  2. In a random sample of 40 of a school's 320 seventh graders, 12 walk to school. Estimate how many of all 320 seventh graders walk to school.

    Hint: Find the fraction of the sample that walks, then apply it to the whole grade.

  3. A teacher computes the mean test score of all 28 students in her class: 81. She then picks 7 students at random, and their mean is 84. Which number describes the population, and which is a sample statistic?

    Hint: Which mean used every student she cares about?

  4. Survey A asks 2,000 visitors to a fitness website how often they exercise. Survey B picks 200 adults at random from the town's list of residents. Which gives a better estimate of how often town adults exercise?

    Hint: A bigger sample helps only if it looks like the population.

  5. A number cube is rolled once, and the possible results are {1, 2, 3, 4, 5, 6}. Is this list a population and a sample, or a sample space?

    Hint: Are these people or things being studied, or results that could happen?

  6. Jay measured the heights of the 15 players on the school basketball team and found a mean of 172 cm. He wrote: "The mean height of students at our school is 172 cm." What is wrong with his conclusion?

    Hint: Does this sample look like the whole school?

Want the full set?

50 practice questions for this concept — free to try, every one with a complete worked solution showing the why, not just the answer.

Frequently Asked Questions

Can a population be small, like just my class?

Yes. A population is whatever whole group your question is about. If you only want to know about your class of 28, those 28 students are the population, and asking all of them is a census, so the answer is exact rather than an estimate. The same class turns into a sample the moment you use it to guess about the whole school.

Why not just measure the whole population every time?

It is often too slow, too expensive or impossible. Some tests destroy what they check: a company finding out how long its light bulbs last cannot burn out every bulb it sells. Other things change too fast to count everyone, like opinions the week before an election. A well-chosen sample of a few hundred or a thousand can estimate the population closely and quickly, which is why most real statistics come from samples.

Does a population always have to be people?

No. A population can be any complete set of things you want to describe: every apple in an orchard, every light bulb a factory made this month, every day of weather records for a city, or every song on a streaming service. The sample is the part you actually examine. Statisticians call the members of any population individuals or units, even when they are objects or days.

Learning Path

Population vs Sample

You are here

You need Data Collection (how information is gathered) and Sample Space (the full set of possible outcomes, a different kind of whole) first. This concept adds the split between the group you care about and the part you measure, and between parameters and statistics. Next, Sampling Bias shows how a sample can misrepresent its population, and Random Sampling shows how to choose one that does not.

See Also