Confidence intervals for a mean
Studying this course? Keep your progress in one place.
Key facts
- The sample mean of a normal population is normal: .
- The standard error shrinks as grows.
- A interval for is , with , or for , or .
- With a large sample and unknown , use (divisor ) in its place.
- Wider intervals come from higher confidence, larger spread or smaller .
Distribution of the sample mean
For a normal population, the sample mean is also normal, with the same mean and a variance divided by .
If a population is normal with mean and variance , the mean of a random sample of size is also normal.
The standard deviation of is the standard error. It shrinks as grows, so larger samples pin down more precisely.
A confidence interval uses this to give a range of plausible values for .
- Sample mean
- Standard error
A population has . What is the standard error of the mean for a sample of size ?
Interval when the variance is known
Go either side of the sample mean by standard errors, where is chosen from the confidence level.
A symmetric confidence interval for is .
The critical value has of the standard normal distribution between and . The interval is a symmetric interval, centred on the sample mean.
- :
- :
- :
Worked example
A population has . A sample of has mean . Find a confidence interval for .
- 1
Standard error .
- 2
Margin .
- 3
Interval .
Which value is used for a confidence interval?
Unknown variance, large sample
With a large sample, use the sample estimate in place of and keep the same values.
If the sample is large (roughly ), is a reliable estimate of , so the interval is .
Use the unbiased estimate of the variance, with divisor .
- Large-sample interval
- Unbiased variance
Worked example
A sample has , and . Find a confidence interval for .
- 1
Standard error .
- 2
Margin .
- 3
Interval .
Why can we use in place of and still use values?
Making inferences from an interval
The interval shows which values of are plausible, and its width depends on confidence level, spread and sample size.
If a claimed value of lies inside the interval, the data are consistent with the claim. If it lies outside, there is evidence at the matching level (for example for a interval) that the mean is different, and the interval shows in which direction. Always answer in context.
For a interval of width at most , solve for and round up.
Wider interval
- Higher confidence level (larger )
- Larger
- Smaller
Narrower interval
- Lower confidence level
- Smaller
- Larger
Which change makes a confidence interval narrower?
Try an exam question
The masses of packets of sugar are normally distributed with standard deviation g. A random sample of packets has mean mass g. Find a confidence interval for the mean mass, and say whether it is consistent with the manufacturer's claim that the mean is g.
[4 marks]
- [1]Standard error .
- [1]Interval .
- [1].
- [1] lies inside the interval, so the data are consistent with the claim.
That's the notes covered.
Carry on to the next subtopic.
Try a question
Find the standard error of the sample mean.
1 mark, marked against the mark scheme
Find the standard error of the sample mean.
1 mark, marked against the mark scheme