Confidence Interval Calculator screenshot

Confidence Interval Calculator

A t-based confidence interval for a mean from a pasted sample, at 90, 95 or 99 percent.

Privacy First
0 Runs
Updated 2026-11-06
No upload
Runs in this tab
No signup

What this page computes

Paste one number per line and choose a level. The interval is x̄ ± t*·s/√n, where s uses the n − 1 divisor, df = n − 1, and t* is the two-sided critical value taken from the inverse of the t distribution the p-values on other pages use. The page prints the interval, the mean, s, the standard error, the degrees of freedom, t* and the half-width. Figures print to six significant figures.

The interval is about the mean, not about the data: it does not contain 95% of future observations, and it assumes the sample is independent and roughly normal. A constant sample is refused, because s would be zero.

Nothing leaves the tab, so the same sample and level always print the same two endpoints.

The page builds a confidence interval for a mean from a pasted sample: x̄ ± t*·s/√n, where s uses the n − 1 divisor and t* is the two-sided critical value at n − 1 degrees of freedom. The eight values 2, 4, 4, 4, 5, 5, 7, 9 give 3.21251 … 6.78749 at 95%, with t* = 2.36462 on 7 degrees of freedom and a half-width of 1.78749. A sample that never varies is refused, because s is zero and the interval would have no width to compute.

Build a t-based confidence interval for a mean from raw data. The level is yours; the standard error and degrees of freedom are printed.

How to use it

Paste the sample with one value per line — a comma inside a line is refused, because this page reads a column. Then type the confidence level in percent; it must be strictly between 0 and 100. The result line gives the interval, and the line under it repeats the mean, s, the standard error, n and the degrees of freedom so the interval can be rebuilt by hand.

The formula, the divisor and t*

The standard deviation uses the n − 1 divisor, Bessel’s correction, and the critical value comes from the inverse of the same t cumulative function the t-test page uses — so this interval and a one-sample t-test on the same column cannot disagree. The level only moves t*: at 99% the interval is wider, and the printed t* shows by how much. The page does not assume the population standard deviation is known and does not fall back to a normal critical value.

What to Expect

Best for

  • Reporting a mean with an interval that matches a t-test

What this tool keeps

  • Nothing leaves this tab: the arithmetic runs in the page you are reading, and a reload discards both the input and the result.

Sample input

2 4 4 4 5 5 7 9

Sample output

95% CI of the mean = 3.21251 … 6.78749 mean = 5, s = 2.13809, SE = 0.755929, n = 8, df = 7 t* (two-sided) = 2.36462, half-width = 1.78749 the interval is x̄ ± t*·s/√n with the n − 1 divisor for s

Frequently asked questions

Which standard deviation does the interval use?

The sample standard deviation with the n − 1 divisor, and the printed s, standard error and degrees of freedom let you check it. The critical value is the two-sided t* at n − 1 degrees of freedom.

How do I enter the data?

One value per line. A line containing a comma is refused, because this page reads a column rather than a comma-separated list.

Is my sample uploaded?

No. The mean, s, standard error and interval are computed in this page from the pasted column, and nothing is posted or stored.

Developer program

Build custom tools for your store

Join the SDK program to create useful ecommerce utilities for your store.