Search the complete library

What do you want to learn or calculate?

Quick linksAll calculatorsMath subjectsPractice questionsFormula library
← Statistics formulas

One-sample t statistic

Compare a sample mean with a null-hypothesis mean.

Statistics · Hypothesis tests
$$t=\frac{\bar x-\mu_0}{s/\sqrt n}$$

One-sample t statistic is one of 2 hypothesis tests formulas in the statistics section of this library, and it is used at ap · university level.

Why one-sample t statistic works

The top measures how far the sample mean sits from the claimed value, and the bottom measures how far it would typically wander by chance alone. Dividing converts a gap in the original units into a count of standard errors, which is a scale on which unusual has the same meaning in every problem.

What each symbol means

$\mu_0$ is null value and $n-1$ is the degrees of freedom.

One-sample t statistic: when it holds

Use independent data and verify the t-procedure’s shape or sample-size conditions.

When it stops applying

It assumes independent observations and a population shape close enough to symmetric for the sample size at hand. The most common breach is paired data: measuring the same people before and after and then ignoring the pairing wastes the design, because the correct approach is to run this statistic on the differences instead.

One-sample t statistic: a worked example

$\bar x=52,\mu_0=50,s=8,n=16$ gives $t=1$.

The mistake to avoid

What people do: Leaving s alone on the bottom without dividing it by the square root of n.

Why it goes wrong: With a mean of 52 against a claim of 50, a spread of 8 and 16 observations, the correct statistic is 1. Skipping that square root gives 0.25 and hides every effect the sample size was supposed to reveal.

Do this instead: Write the denominator as s divided by the square root of n as a single quantity, and compute that number before dividing.

One-sample t statistic: step by step

  1. Name the unknown, and the unit the answer has to come out in.
  2. Match the symbols to your values. $\mu_0$ is null value and $n-1$ is the degrees of freedom.
  3. Check the conditions before substituting. Use independent data and verify the t-procedure’s shape or sample-size conditions.
  4. Substitute, keep exact values to the last line, then test the sign, size, and unit against a rough estimate — the check that catches most statistics slips.

Where this formula fits

Subject
Statistics formulas — 21 entries in this library
Topic
Hypothesis tests
Level
AP · University

Formulas are easiest to keep when they sit inside a method rather than on a list. Use the links below to see where one-sample t statistic comes from, to check a calculation against a tool, and to practise it until you can recall it without looking.

Questions about one-sample t statistic

Is a t value of 1 large enough to be significant?

No. With 15 degrees of freedom, a two-sided p-value for t equal to 1 is about 0.333, meaning a gap this size or larger happens in a third of samples when the claim is true.

How do I turn t into a p-value?

Look up the tail area beyond your value on a t distribution with n minus 1 degrees of freedom, then double it for a two-sided test. Calculators and software do this with a single command.

What is the practical difference between this and a z statistic?

This one uses an estimated spread, so its distribution has heavier tails and needs degrees of freedom. Once the sample passes roughly 30 the two give nearly identical answers.

Does a very large t prove the claimed value is false?

No. It says the data would be surprising if the claim were true, which is weaker. A large value can also come from a broken assumption, such as dependent observations.

Stuck on a problem?

Work a one-sample t statistic problem step by step

Type your own problem, or upload a photo of it. You get the method, the answer, and a check you can repeat yourself.