Confidence intervals for a Normal mean
Studying this course? Keep your progress in one place.
Key facts
- A confidence interval is a range, from a sample, likely to contain the population parameter.
- Say "we are confident that lies in the interval", never "a probability".
- With known: , with , , for , , .
- Width is : four times the sample halves it. Round up.
- A interval matches a two-tailed test at the level.
What an interval means
The confidence level describes the method over repeated samples, not one calculated interval.
A confidence interval is a range of values, calculated from a sample, that is likely to contain the unknown population parameter.
A interval is built by a method that, over many samples, gives intervals containing the true about of the time. Once calculated, is a fixed number that is inside it or not. So say: "we are confident that lies in the interval".
- 95% confidencethe method captures in 95% of repeated samples
What does ' confidence' describe?
Interval with known variance
Use , with from the confidence level.
If with known, then , so the standard error is .
The interval is . Check the level against the tails: leaves in each tail, so .
- Confidence interval
Worked example
, , . Find a confidence interval for .
- 1
Standard error .
- 2
Margin .
- 3
Interval .
90%
- z = 1.645
95%
- z = 1.96
99%
- z = 2.576
Which value is used for a confidence interval?
Width and sample size
The width is : it falls as grows, and you must round up.
The interval is symmetric about , with width .
Width falls as increases (halving it needs four times the sample size) and rises with the confidence level or with . For a maximum width , solve , so , then round up.
- Width
- Sample size, round up
Worked example
, confidence, maximum width . Find the smallest .
- 1
.
- 2
.
The sample size is increased. The confidence interval width...
Intervals and hypothesis tests
If the claimed mean lies outside the interval, a matching two-tailed test rejects it.
A confidence interval contains the values of that a two-tailed test at the level would not reject. So matches , and matches .
If a claimed value lies outside the interval, reject ; if inside, there is no evidence against it. This agrees with against the critical value.
Worked example
, , . Use a interval to test and .
- 1
Standard error ; margin .
- 2
Interval: .
- 3
is inside: not rejected. is outside: rejected.
- 4
Check: .
A interval for is . Is rejected at the level (two-tailed)?
Try an exam question
The masses of bags of flour are Normally distributed with standard deviation g. A random sample of bags has mean mass g. Find a confidence interval for the mean mass, and say what it shows about a claim that the mean is g.
[4 marks]
- [1]Standard error .
- [1]Uses : margin .
- [1]Interval .
- [1] is outside the interval: evidence at the level that the mean is not g.
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