Confidence intervals for the mean
In a minute
A is a range of plausible values for a mean, worked out from one . If is known you use the ; if not, the . Then you say what the interval means in context.
You'll be able to
- Find a confidence interval for the mean of a normal population when is known, using the normal distribution.
- Find a confidence interval when is unknown, using the t-distribution with , whatever the sample size.
- Interpret a confidence interval in context and use it to judge a claimed mean.
- Explain how the confidence level and the sample size change an interval's width.
Before you start3 quick questions on what this builds on
Revise first: 4.1 Sampling, data quality and outliers, 4.3 Central tendency and dispersion, 4.9 Normal distribution, 4.11 Chi-squared tests and the t-test, 4.14 Linear combinations and unbiased estimates and 4.15 Sample mean and the central limit theorem
Intervals when σ is known
A sample mean estimates the population mean , but another sample would give a different . So you give a range of plausible values for instead, with a level of confidence.
In 4.15 you met the . For a normal population with standard deviation , . So of sample means lie within of .
Turn that round: if is within of , then is within of . So contains for of samples.
The multiplier cuts off the middle of . For , , so . For it is , and for it is .
The part after is the margin of error, and the interval is centred on . The GDC's Z interval does the whole calculation.
Try it first, then reveal one step at a time.
- is known, so use the normal distribution:
- Margin of error: cm.
- Interval: , which is .
- Round each end only now: cm.
Try it first, then reveal one step at a time.
- is known, so this is a Z interval. Write down what you enter: , , , C-Level .
- The GDC gives , so hours.
- Check: agrees.
- Interpret: we are confident that the mean battery life of all phones in the batch is between and hours.
Intervals when σ is unknown
Usually you don't know . You estimate it from the sample with . Its square is the of from 4.14; itself is the usual estimate of , though not exactly unbiased.
The estimate adds uncertainty, so the multiplier must be bigger than . The t-distribution gives it: the same distribution as the in 4.11.
As grows, it gets closer to . For , when and when , against .
cuts off the middle of that t-distribution. The GDC's T interval does it all, from a list of data or from , and .
Try it first, then reveal one step at a time.
- is unknown, so use a T interval with degrees of freedom.
- Enter the values in a list and run the T interval with C-Level .
- The GDC shows , and the interval .
- Round each end: mg. So we are confident the mean caffeine content of the café's cups is between and mg.
Try it first, then reveal one step at a time.
- is unknown, so use t, even though is large: .
- Convert to , the square root of the unbiased variance estimate: cm.
- has with : Margin:
- Interval: . On the GDC: T interval with Stats input, , Sx , , C-Level .
- We are confident that the mean three-week height of all seedlings of this variety is between and cm.
Interpreting a confidence interval
The describes the method, not one interval. is fixed, so a particular interval either contains it or doesn't. Build intervals from many random samples, and about of them contain .
So write: 'We are confident that the mean [quantity] of all [population] is between and [units].' Never say there is a probability that is in your interval.
To judge a claimed value of , see where it falls. Inside the interval, it is plausible: no evidence against the claim. Outside, the data give evidence against the claim. An interval never proves a claim.
A higher confidence level uses a bigger multiplier, so a wider interval. For the same standard deviation, a larger sample gives a narrower one: four times the sample size roughly halves the width.
Both intervals assume a normally distributed population and a random sample, so the values are independent. Exam questions often ask you to state one of these.
Try it first, then reveal one step at a time.
- (a) Name the population, the mean and the units.
- (b) lies inside , so mg is a plausible value of the mean.
- (c) lies outside the interval, above its upper end, so mg is not a plausible value of the mean.
- Give the reason (inside or outside) first, then the conclusion about the claim.
- (a) We are confident that the mean caffeine content of all the café's cups is between and mg. (b) is inside the interval, so it is plausible: no evidence against the menu's claim. (c) is outside the interval, so the data give evidence against the website's claim.
Try it first, then reveal one step at a time.
- (a) is unknown, so use t with degrees of freedom: Margin:
- Interval: , so g.
- (b) To catch for of samples instead of , the interval must reach further: rises from to .
- (c) With adults, halves and drops a little, so the interval becomes about half as wide: g.
Common mistakes
- Using the normal distribution because the sample is large. If is estimated from the sample, use the t-distribution with degrees of freedom, whatever is.
- Saying there is a probability that is in your interval. The belongs to the method: about of intervals built this way contain .
- Commenting on a claim with no reason. Say whether the value is inside or outside the interval, then what that means for the claim.
- Writing the interval in terms of , such as . The interval estimates the population mean .
- Rounding early or to the wrong accuracy. Each end usually earns its own mark: keep full GDC values and round only the ends, as asked.
Exam tips
- **Find** a confidence interval: name the interval (T if is unknown, Z if known) and the values entered, then both ends to the accuracy asked.
- **Comment** on a claim: say the value is inside or outside the interval, then conclude about the claim in context. A conclusion with no reason scores nothing.
- **State** an assumption: the variable is normally distributed in the population, or the sample is random (independent values).
- **Interpret** an interval: 'We are confident that the mean [quantity] of all [population] is between and [units].'
Key takeaways
Practise this
4 past-paper questions on Confidence intervals for the mean in the AI HL bank, each with a mark scheme and a worked explanation.