Confidence Interval for a Mean (σ unknown) Explained with Worked Examples

When is unknown, a confidence interval for the mean is , where comes from the -distribution with degrees of freedom.

Write 2x or 2*x to multiply, ^ for powers, and ; between simultaneous equations. You can also type factor, expand, derivative of, integrate … from a to b, limit … as x->0 or 15% of 80.

Try an example

Before you start

This page is easier if you are comfortable with:

What Confidence interval for a mean (σ unknown) means

A confidence interval gives a range of plausible values for the population mean. A 95% interval is built so that 95% of such intervals would contain the true mean.

Since the population standard deviation is estimated by the sample value , the -distribution replaces the normal. Its critical values are larger for small samples.

The interval is wider when the sample is small, when is large, or when you want more confidence. The standard deviation is estimated by the sample variance, and the quantity used is the one-sample t statistic.

This page is part of Hypothesis tests and confidence intervals in Statistics. Topics that work alongside it: One-sample t statistic, Hypothesis test for the mean of a normal, Sample (unbiased) variance, Hypothesis test for correlation, Hypothesis test for a binomial proportion and Five-number summary (box plot).

What is it used for?

A confidence interval gives a range of plausible values for a population mean. When σ is unknown, the sample standard deviation and the t-distribution are used.

How to use confidence interval for a mean (σ unknown)

  1. Find , and .
  2. Find for degrees of freedom and the confidence level.
  3. Calculate the margin of error .
  4. Write margin.

Graph

The central 95% of a normal distribution-4-3-2-10123400.10.20.30.4The central 95% of a normal distributionxyGraph with x from -4 to 4 and y from -0.02 to 0.45. Shows the curve y = exp(-x^2/2)/sqrt(2*3.14159265); a shaded region.

About 95% of the area lies between −1.96 and 1.96 (for a normal distribution; the t-distribution is a little wider for small samples).

Worked examples

These examples are worked by hand, step by step, so you can compare your own working.

Example 1: a 95% interval

A sample of 25 has mean 50 and standard deviation 10. Find a 95% confidence interval for the mean. (For 24 degrees of freedom, .)

Worked example
Answer
(45.87, 54.13)(45.87,\ 54.13)
  1. Standard error
  2. Margin of error
  3. Interval

Example 2: n = 16

A sample of 16 has mean 20 and standard deviation 4. Find a 95% confidence interval for the mean.

Worked example
Answer
(17.87, 22.13)(17.87,\ 22.13)
  1. Standard error
  2. t value with 15 degrees of freedom
  3. Interval

Example 3: n = 9

A sample of 9 has mean 50 and standard deviation 6. Find a 95% confidence interval for the mean.

Worked example
Answer
(45.39, 54.61)(45.39,\ 54.61)
  1. Standard error
  2. t value with 8 degrees of freedom
  3. Interval

Special cases

A few situations come up again and again. Knowing them saves time and helps you spot answers that cannot be right.

x̄ = 50, s = 8, n = 16, t₁₅ = 2.131

half-width

4.262.

same

lower

45.738.

same

upper

54.262.

n = 25, t₂₄ = 2.064, s = 10

half-width

4.128.

Word problems

x̄ ± t(n−1, α/2) × s/√n. The t critical value is larger than z, especially for small n.

SE

s/√n = 8/4.

  1. 2
  2. Check: ✓2

Half-width

2.131 × 2.

  1. 4.262
  2. Check: ✓4.262

Lower limit Higher

50 − 4.262.

  1. 45.738
  2. Check: ✓45.738

n = 25 Higher

2.064 × 10/5.

  1. 4.128
  2. Check: ✓4.128

Common mistakes

Using z

z ✗

t with n − 1 d.f. ✓

σ unknown.

Using n d.f.

n ✗

n − 1 ✓

Degrees of freedom.

Forgetting √n

s ✗

s/√n ✓

Standard error.

σ in place of s

wrong ✗

sample s ✓

Unknown σ.

Exam tips

  1. x̄ ± t·s/√n.
  2. d.f. = n − 1.
  3. t > z for small n.
  4. Table lookup.
  5. Wider than z interval.

Practice questions

Try each one on paper, then open the answer. Use the solver above to see the full working.

1. SE: s = 12, n = 9 Foundation

4

2. Half-width: t = 2.262, s = 6, n = 9, 3 dp Foundation

4.524

3. Lower limit: x̄ = 100, half-width 5.2 Foundation

94.8

4. Half-width: t = 2.093, s = 10, n = 20, 4 dp Higher

4.6801

5. SE: s = 5, n = 25 Higher

1

6. Upper limit: x̄ = 30, t = 2.131, s = 4, n = 16 Higher

32.131

Practice generator

Unlimited fresh questions with instant marking. Choose a level, work it out on paper, then type your answer.

Solve: …

Key terms

t-distribution
Heavier tails than normal.
Degrees of freedom
n − 1.
Standard error
s/√n.
Confidence interval
Range for μ.
Critical value
t(n−1, α/2).
Sample SD
s.

Frequently asked questions

What is the CI for a mean with σ unknown?

x̄ ± t s/√n with n − 1 degrees of freedom.

Why t not z?

Because s estimates σ.

How many degrees of freedom?

n − 1.

Is it wider than the z interval?

Yes.

Which page covers the t statistic?

one-sample t statistic.

Which page covers sample variance?

sample variance.

More in Statistics and the formula sheets.