One-sample t-test
Studying this course? Keep your progress in one place.
Key facts
- Use a t-test for the mean of a normal population when the variance is unknown and the sample is small.
- The test statistic is , with degrees of freedom.
- Use the unbiased estimate .
- For a two-tailed test, put half the significance level in each tail.
- If is in the critical region, reject ; always conclude in context.
When to use a t-test
Use the -distribution when you estimate by from a small sample of a normal population.
The statistic follows the t-distribution with degrees of freedom.
It is symmetric about like the normal but has heavier tails, allowing for the extra uncertainty from estimating . As increases it approaches the standard normal.
The test needs a normal population and a random sample.
| z-test | t-test | |
|---|---|---|
| Population variance | Known | Unknown, estimated by |
| Distribution used | Normal | with degrees of freedom |
| Normal population needed | For small | Yes |
z-test
- Population variance:
- Known
- Distribution used:
- Normal
- Normal population needed:
- For small
t-test
- Population variance:
- Unknown, estimated by
- Distribution used:
- with degrees of freedom
- Normal population needed:
- Yes
A sample of values is used in a one-sample -test. How many degrees of freedom?
Finding s from the data
Use the unbiased estimate of the variance, which divides by , then take the square root.
The unbiased estimate is the one you need for the test. If the question gives the variance, take the square root to get before dividing by .
Check the wording: an 'unbiased estimate of the variance' is already , whereas a 'sample variance' with divisor must be multiplied by .
- Unbiased variance
- Divisor to sample variance
Worked example
A sample has , and . Find and .
- 1
.
- 2
.
- 3
.
A sample of values has variance calculated with divisor . What is the unbiased estimate ?
Hypotheses and critical regions
State and about , then read the critical value from the -table using and the tail probability.
Test against or (one-tailed), or (two-tailed).
The significance level goes wholly in one tail for a one-tailed test, and half in each tail for a two-tailed test. For a two-tailed test use the column.
The critical region is the set of values beyond the critical value.
| One-tailed, 5% | Two-tailed, 5% | |
|---|---|---|
| Table column | ||
| Critical value for |
One-tailed, 5%
- Table column:
- Critical value for :
Two-tailed, 5%
- Table column:
- Critical value for :
For a two-tailed test at the significance level, which table column do you use?
Carrying out the test
Calculate , compare it with the critical value, then state the conclusion in context with cautious wording.
If is in the critical region, reject H0.
If it is not, say there is insufficient evidence against . Do not say that is true.
- 1
Hypotheses
and about
- 2
Statistic
Find , , then
- 3
Critical value
Use and the tail
- 4
Compare
Is in the critical region?
- 5
Conclude
In context, cautiously
Worked example
A café claims its coffees hold ml. A sample of has and . Test at the level whether the mean is below ml.
- 1
, (one-tailed).
- 2
.
- 3
, and the critical value at is .
- 4
, so is in the critical region and we reject .
A test statistic lies outside the critical region. What is the correct conclusion?
Try an exam question
A teacher claims that the mean reaction time of her class is s. A random sample of students has mean s and unbiased standard deviation s. Assuming reaction times are normally distributed, test at the level whether the mean differs from s. (The two-tailed critical value for is .)
[5 marks]
- [1], .
- [1].
- [1].
- [1], so is not in the critical region.
- [1]Insufficient evidence at the level that the mean reaction time differs from s.
That's the notes covered.
Carry on to the next subtopic.
Try a question
How many degrees of freedom does the -statistic have in a test of the mean using this sample?
1 mark, marked against the mark scheme
How many degrees of freedom does the -statistic have in a test of the mean using this sample?
1 mark, marked against the mark scheme