Confidence Interval Calculator
Build confidence intervals for a sample mean or proportion.
All calculations happen locally in your browser — nothing is uploaded, stored or tracked.
Choose mean or proportion
Depending on your data.
Enter the statistics
Sample size, and mean ± SD or successes.
Pick a confidence level
90%, 95% or 99%.
What Is a Confidence Interval?
A confidence interval is a range around a sample estimate that likely contains the true population value, at a chosen confidence level. A 95% confidence interval means that if you repeated the sampling process many times, about 95% of the intervals would capture the true value.
The calculator supports two cases: estimating a population mean from a sample (using the sample mean, standard deviation and size) and estimating a population proportion (from the number of successes and sample size). Confidence levels of 90%, 95% and 99% are provided.
The Formula
The critical values z* are 1.645 (90%), 1.96 (95%) and 2.576 (99%). These formulas assume a large enough sample (n ≥ 30 for means is the common rule of thumb).
Your data never leaves your device.
Every calculation on this site runs in your browser using vanilla JavaScript. Nothing is uploaded, stored or tracked.
- 100% local, client-side calculations
- No data stored on any server
- No tracking, no analytics, no ads scripts
- Works offline once loaded
Frequently Asked Questions
What does 95% confidence mean?
If the study were repeated many times, about 95% of the computed intervals would contain the true population value.
How do I calculate a confidence interval?
Take your estimate, add and subtract z* × standard error. The calculator does this for means and proportions.
What is the margin of error?
The z* × SE part of the formula — the plus/minus amount around the estimate.
Does sample size affect the interval?
Yes — larger samples produce smaller standard errors and narrower intervals.
Can I use this with small samples?
For small samples (n < 30), the t-distribution is more appropriate than the normal approximation used here.