Informational

How to calculate a confidence interval

For a mean, the interval is x̄ ± (critical value × SE), where SE is σ/√n if σ is known, or s/√n if you estimate it. The critical value is z* when σ is known and t* when you use s.

What the interval is for

A point estimate (the sample mean) is a single guess. A confidence interval gives a range of plausible values for the unknown population mean, at a stated confidence level such as 90%, 95%, or 99%.

Formulas

Known σ: x̄ ± z* · (σ / √n)
Unknown σ: x̄ ± t* · (s / √n), df = n − 1

Common z* values: 1.645 (90%), 1.96 (95%), 2.576 (99%). t* is larger than z* for small df and is read from a t table.

Worked example (known σ)

n = 36, x̄ = 12.4, σ = 3.0, 95% confidence.

  1. SE = 3.0 / √36 = 0.5.
  2. Margin of error = 1.96 × 0.5 = 0.98.
  3. Interval: 12.4 − 0.98 to 12.4 + 0.98 → (11.42, 13.38).
Interpretation

We are 95% confident that the population mean lies between 11.42 and 13.38 (in the problem’s units).

Useful tips

  • Larger n shrinks the interval. Higher confidence widens it.
  • If the homework gives only a list of values, compute x̄ and s first — see mean and standard deviation.
  • A CI and a two-sided t-test at the same α are two views of the same arithmetic.

Common mistakes

  • Saying “there is a 95% chance the mean is in this interval” after the interval is computed. The long-run coverage idea belongs to the method, not this one realized interval.
  • Using z* with s and n = 12.
  • Forgetting to divide σ by √n (using σ as if it were already the standard error).

How Statistics Problem Solver Pro helps

The Confidence Interval calculator is free and offline. For a paragraph-style problem, scan it to see substitutions and the formula the app used. The listing also includes a t-test calculator, which is the hypothesis-test twin of a mean CI.

Step-by-step solution with the exact formula shown in Statistics Problem Solver Pro

Check a confidence interval on iPhone

Use the free CI calculator, or scan the full homework item.

Download on the App Store

Related guides

FAQ

When do I use t instead of z for a CI?

When the population SD is unknown and you plug in the sample SD s. Degrees of freedom are n − 1 for a one-sample mean.

Learn the matching t-test steps →
Is there a confidence interval app for iPhone?

Yes. Statistics Problem Solver Pro includes a CI calculator that the listing says is free and offline.

See the calculator list →

Statistics Problem Solver CI calculator

Get