Healthy Weight Calculator
Your healthy weight range from BMI, height and frame.
How many people you need to survey, and the margin of error.
Halving the margin costs four times the sample — the relationship is quadratic.
| Sample size | Margin of error |
|---|
| Population | Sample needed |
|---|
Responses needed
—
—
A 50% result would fall in this range
An expected proportion of 50 percent gives the largest — and therefore safest — required sample, which is why it is the default. Population size barely matters above about 20,000, which is why a national poll and a city poll use similar sample sizes.
The Sample Size Calculator works out how many survey responses you need for a given margin of error and confidence level, applies a finite population correction, and runs the same calculation backwards to show the margin a sample you already have actually delivers.
Find how many responses a survey needs to reach a chosen margin of error at a chosen confidence level, and work the calculation backwards to see the margin of error a sample you already have actually delivers.
Two things surprise people the first time they run these numbers. The first is that population size barely matters once it is reasonably large: a sample of about 1,000 gives roughly a three percent margin whether the population is fifty thousand or fifty million, which is why national polls are the size they are. The second is how expensive precision becomes — halving the margin of error requires four times the sample, because the relationship is quadratic rather than linear.
Size from a target margin, or the margin a sample you already collected actually achieves.
Applied automatically, which meaningfully reduces the requirement for smaller populations.
Shows how many people to invite, not just how many completed responses you need.
Halving the margin of error needs four times the sample, which is the fact that reshapes most survey budgets.
90, 95 and 99 percent presets, or a custom level you enter yourself.
95 percent is the usual default; 99 percent needs a substantially larger sample.
How much error you can tolerate, typically 3 to 5 percent.
Optional. Leave it out for a very large or unknown population.
The number of completed responses you need, plus how many to invite for a given response rate.
For a large population at 95 percent confidence, about 384 responses gives a 5 percent margin of error and about 1,067 gives 3 percent. Below a few thousand people, the population size starts to reduce the requirement.
Much less than most people expect. Above about 20,000 the required sample barely moves, which is why a national poll and a city poll use similar sample sizes.
The range around your result within which the true value probably lies. A 45 percent result with a 3 percent margin means the true figure is likely between 42 and 48 percent.
Because margin of error scales with the square root of the sample size. Going from 4 percent to 2 percent needs four times as many responses, not twice as many.
What people who use the Sample Size Calculator think of it. Reviews come from visitors and are posted as written.
No ratings yet
Yours would be the first.
0 reviews
Newest first
No reviews yet
Be the first to rate the Sample Size Calculator. It takes half a minute and no account.
Write the first reviewYour healthy weight range from BMI, height and frame.
One converter for length, weight, area, volume, speed, time and more.
Add and subtract hours, minutes and seconds without base-60 mistakes.
Equated monthly instalment with a principal and interest breakdown.
Add sales tax to a price, or strip it back out.
Snowball or avalanche: a plan for clearing every debt.
Area, perimeter, surface area and volume for every common shape.
Z-scores, percentiles and probabilities either way.