Sample Size Calculator

Work out how many completed responses your survey needs before you send a single invitation. Enter your population size, pick a confidence level, set the margin of error you can live with, and the number updates as you type.

Free to use
No sign-up
Runs in your browser

Calculate your sample size

Your inputs

Everyone you want the result to speak for. Surveying your own company? That is your total headcount.

How sure you want to be that the real answer sits inside your margin of error. 95% is the usual choice.

The wobble you will accept, in percentage points. Tighten it and the sample size climbs fast.

Nothing you type here leaves your device.

Sample size

Enter a population size and a margin of error to see the sample size you need.

Key terms

Population size

Total number of people in the population you are researching. If you survey your organization, population size is the total number of employees.

Confidence level

A percentage that indicates how sure you can be that a certain amount of the population will select an answer. A 95% confidence level, for example, means that the outcomes between x and y are 95% certain.

Margin of error

A percentage that tells you how much you would expect your survey results to represent overall population views. The lower the margin of error, the better the confidence.

This figure assumes a simple random sample and a 50/50 population proportion, the most cautious assumption you can make. Real accuracy also rests on who answers and how well they represent everyone else.

How many people need to take your survey?

Surveying everyone is slow and expensive, so researchers sample instead: question a smaller group, then read the answer back onto the whole population. The sample size is what makes that step defensible. Question too few people and you are reading noise; question far more than you need and you have paid for precision the decision never called for.

1
Size the population
Count the group you want the result to speak for. An estimate is fine above a few tens of thousands, where the number stops moving.
2
Set your tolerance
Choose a confidence level and a margin of error. 95% and 5% is the pairing most survey work is built on.
3
Plan the invites
The number above is completed responses. Divide it by the response rate you expect to get the size of your send list.

The sample size formula

Nothing here is invented for this page. It is the textbook method for sampling a proportion, so you can check any number the calculator gives you.

Sample Size Formula
  1. z is the z-score for your confidence level: 1.28 at 80%, 1.65 at 90%, 1.96 at 95%, 2.58 at 99%.
  2. p is the population proportion, held at 0.5 here because a 50/50 split demands the largest sample and never leaves you short.
  3. e is your margin of error written as a decimal, so 5% becomes 0.05.
  4. The finite population correction then divides that figure down using your population size N, which matters for small groups and fades away for large ones.

Free, private, and built for research

Most calculators of this kind want your email before they will show a number, and many run the arithmetic on someone else's server. This one does neither.

  • 01

    Runs in your browser

    No API call sits behind this page. Your population size and study parameters stay on your machine.

  • 02

    No account, no email wall

    Change an input, read the number, close the tab. Nothing is logged and nothing is asked of you.

  • 03

    Working you can check

    The formula is printed above and the same inputs always return the same figure, so you can defend it in a method section.

Who reaches for a sample size calculator

Anyone who has been asked "but is that enough people?" and wanted a number rather than an opinion.

01
Researchers
Size the sample before fieldwork starts and write the justification straight into your method section.
02
Product teams
Know how many users have to answer before a feature survey is worth taking to a roadmap meeting.
03
Marketing and CX
Back a brand tracker or satisfaction study with a sample you can defend instead of a round number.
04
HR and people teams
Work out how many employees make an engagement result representative of the whole company.
05
Students and academics
Produce the sample calculation an ethics submission or dissertation committee expects to see.
06
Agencies
Show a client in respondents, not adjectives, what a tighter margin of error actually costs.

Work the other direction

Sample size and margin of error are two readings of the same equation.

Margin of Error Calculator
Already collected your responses? Find out how accurate the result you are holding actually is.
Open calculator
Sample size with response distribution
Know how your answers are likely to split? Set the distribution yourself and lower the sample you need.
Open calculator

Frequently asked questions

How many people do I need to survey?

That depends on three things: how large the group you are studying is, how confident you want to be in the result, and how much error you can live with. Enter those three values above and the calculator returns the minimum number of completed responses you need. As a rough anchor, a population of 10,000 at a 95% confidence level and a 5% margin of error needs about 370 responses.

What formula does this calculator use?

The standard formula for estimating a proportion. It starts with n = (z squared times p times (1 minus p)) divided by e squared, where z is the z-score for your confidence level, p is the population proportion, and e is your margin of error as a decimal. It then applies the finite population correction so a small population does not demand more responses than it contains. The formula image is shown on this page so you can check the working.

Why is the population proportion set to 50%?

A 50/50 split is the most cautious assumption you can make, because it produces the largest required sample. Use it when you have no prior data on how answers will fall. If you already know a question skews heavily one way, the true requirement will be lower than the figure shown here.

Do I need to know my exact population size?

A close estimate is enough. Above a few tens of thousands the correction barely moves the number, so the difference between 40,000 and 45,000 is negligible. Population size matters most for small, defined groups, such as the 300 employees at a company or the 900 customers on a list, where it can cut the required sample considerably.

What confidence level should I pick?

95% is the working default for most survey research and is what reviewers expect to see. Move to 99% when the decision carries real cost and a wrong call is expensive, and be ready for the required sample to climb. 90% or lower is defensible for exploratory work where you want direction rather than precision.

Does the calculated sample size account for people who ignore the survey?

No. The number here is completed responses, not invitations. Divide it by the response rate you expect to get the size of your send list. At a 20% response rate, 370 completed responses means inviting roughly 1,850 people.

Is anything I type stored?

No. The calculation is arithmetic that runs in your browser. There is no API call behind it, no account, and no record of what you entered.

Related articles

Explore more
Scripts are blocked. This site won’t work properly. If you’re using Brave, click the Shields icon and turn off Block scripts. Otherwise disable your ad blocker for this site.