Lesson 7 of 7 · 18 min
Using intervals to judge claims
Decide whether a claimed proportion is plausible from where it sits relative to a confidence interval, word the conclusion carefully, and model real problems with their assumptions.
What you will be able to do
- Decide whether a claimed value of is supported by a confidence interval.
- Judge claims such as "a majority" or "fewer than 1 in 4" with an interval.
- Interpret an interval in context and state the assumptions behind it.
- Solve unfamiliar problems with interval estimates, with and without technology.
Confidence intervals earn their keep when someone makes a claim. A council says 70% of residents support a new bikeway. A company says fewer than 5% of its products are faulty. A poll says one candidate is ahead. An interval from a random sample tells you which claims the data support.
Key idea
Inside or outside
- Claimed value inside the interval: the claim is plausible; the data are consistent with it. That doesn't prove it: other values in the interval are also plausible.
- Claimed value outside the interval: the data give evidence against the claim, at that confidence level. Say which way the truth seems to lie (higher or lower).
The council survey interval . A claim of 65% is plausible; the claim of 70% lies outside, above the interval.
Worked example
Does the survey support the council's claim?
A city council claims that 70% of residents support a new bikeway. A random sample of 850 residents finds that 561 support it.
(a) Calculate an approximate 95% confidence interval for the proportion of all residents who support the bikeway.
(b) Use your interval to evaluate the council's claim.
Step 1: Find the sample proportion
Step 2: Calculate the margin of error
Step 3: Write the interval
Step 4: Compare the claim with the interval
The claimed value lies above the interval.
Step 5: Conclude in context
The survey gives evidence, at 95% confidence, that support for the bikeway is lower than the council claims: plausibly between 62.8% and 69.2%. Support is still clearly a majority.
Evaluating a claim means saying whether the data support it, and what the data suggest instead.
Try it yourself first, then check the working one step at a time.
Answer
(a) . (b) 0.70 is outside (above) the interval, so the data suggest support is lower than 70%, although still a clear majority.
Method
Calculate the interval.
Inside: plausible. Outside: evidence against, in a stated direction.
Conclude in context.
Watch out for
Saying "the claim is proven false": the interval gives evidence, at a stated confidence level, not proof.
A random sample gives a 95% confidence interval of for the proportion of Australian adults who have donated blood. A blood service says one in four adults has donated. What do the data say about this claim?
Key idea
Claims about a majority, or a threshold
For "more than half", compare the whole interval with 0.5:
- entirely above 0.5: evidence of a majority;
- containing 0.5: we can't conclude there is a majority (or that there isn't);
- entirely below 0.5: evidence of a minority.
A poll with and gives the 95% interval . Even though 53% "is ahead", the interval includes 0.5, so the poll can't confirm a majority.
A 95% confidence interval for the proportion of voters in an electorate who support Candidate A is . Which conclusion is best supported?
Common mistake
A large sample can't fix a biased one
The interval assumes a random sample. A voluntary online poll of 20 000 readers, or koalas brought into a wildlife hospital because they look sick, can give a narrow interval around the wrong value. The margin of error measures random sampling variation only, not bias.
Worked example
Modelling a koala disease survey
Researchers test 180 randomly selected koalas in a South East Queensland region and find that 63 have chlamydia.
(a) Calculate an approximate 95% confidence interval for the proportion of koalas in the region with chlamydia.
(b) A news story claims that "at least half of the region's koalas are infected". Evaluate this claim.
(c) The researchers want a margin of error of at most 0.05 in next year's survey. Using this year's result, how many koalas should they test?
(d) A volunteer suggests saving money by testing koalas brought in to a wildlife hospital. Explain why this would be a problem.
Step 1: Interval
. , so the interval is .
Step 2: Check the conditions
and are both large, and the koalas were randomly selected, so the approximation is reasonable.
Step 3: Evaluate the claim
The whole interval lies below 0.5, so the data give evidence against the claim: plausibly 28% to 42% of the koalas are infected, which is serious but less than half.
Step 4: Sample size
, so test at least 350 koalas.
Using this year's as the prior estimate gives a smaller than 0.5 would (385). If the true proportion is nearer 0.5 the margin will be slightly bigger than 0.05.
Step 5: Bias
Koalas brought to a wildlife hospital are more likely to be sick, so they are not a random sample. Their proportion with chlamydia would overestimate the region's, and the margin of error can't correct for this bias.
Try it yourself first, then check the working one step at a time.
Answer
(a) (b) The interval is entirely below 0.5, so the data are evidence against the claim. (c) 350 koalas. (d) Hospital koalas are a biased sample, likely to overestimate the infection rate.
Method
Calculate and check the interval.
Compare a threshold claim with the whole interval.
Use a prior for the sample size, rounded up.
Comment on randomness: the interval assumes a random sample.
Watch out for
Using the margin of error to "fix" a biased sample: it measures random variation only.
Exam tip
Writing an interpretation or evaluation
A full-marks interpretation names the confidence level, the population and the proportion in context, and uses the interval's numbers:
"We are 95% confident that between 62.8% and 69.2% of all residents of the city support the bikeway."
A full-marks evaluation then compares the claim with the interval and says what it means: "The council's 70% lies above the interval, so the survey gives evidence that support is lower than the council claims." Add a comment on assumptions (random sample, honest responses) if the question asks you to evaluate the reasonableness.
Summary
A claimed value inside the interval is plausible (consistent with the data), not proven.
A claimed value outside the interval is evidence against the claim; say whether the truth seems higher or lower.
For "a majority", the whole interval must lie above 0.5.
Interpret in context: confidence level, population, proportion, and the interval in the units of the question.
Intervals assume a random sample; a large biased sample still gives a misleading interval.
Finished the lesson?
Try the 2 quick checks above and the lesson completes itself, or mark it complete now.