June 2023 Paper 3 Q4
4. A study was made of adult men from region \(A\) of a country.
It was found that their heights were normally distributed with a mean of 175.4 cm and standard deviation 6.8 cm.
A student claimed that the mean height of adult men from region \(B\) of this country was different from the mean height of adult men from region \(A\).
A random sample of 52 adult men from region \(B\) had a mean height of 177.2 cm
The student assumed that the standard deviation of heights of adult men was 6.8 cm both for region \(A\) and region \(B\).
You should
- state your hypotheses clearly
- use a 5% level of significance
| Scheme | Marks | AO |
|---|---|---|
| [Let \(N\) = height from region \(A\); \(\mathrm{P}(N \gt 180) =\)] 0.24937… awrt 0.249 | B1 | 1.1b |
| (1) |
Notes
B1: for awrt 0.249
| Scheme | Marks | AO |
|---|---|---|
| \(\mathrm{H}_0 : \mu = 175.4 \qquad \mathrm{H}_1 : \mu \neq 175.4\) | B1 | 2.5 |
| [\(S\) = height from region \(B\)] \(\bar{S} \sim \mathrm{N}\left(175.4,\ \dfrac{6.8^2}{52}\right)\) Allow \(\sigma^2 =\) awrt 0.889 | M1 | 3.3 |
| \([\mathrm{P}(\bar{S} \gt 177.2)] = 0.02814\ldots\) | A1 | 3.4 |
| [0.028… > 0.025, Not sig, do not reject \(\mathrm{H}_0\)] Insufficient evidence to support student’s claim | A1 | 2.2b |
| (4) |
Notes
B1: for both hypotheses correct in terms of \(\mu\) (See below for one-tail test)
M1: for selecting the correct model, may be implied by standardisation using correct values or may be implied by a correct value in 1st A1
e.g.(Prob =) 0.028 or awrt 0.972, (\(Z\) =) 1.9(08..) (CV=) 177.25
Condone use of \(S\) (or any other letter) instead of \(\bar{S}\)
Condone use of \(\bar{S} \sim \mathrm{N}\left(177.2,\ \dfrac{6.8^2}{52}\right)\) but this will lose 2nd A mark
1st A1: for probability of awrt 0.028 (allow 0.03 if \(\mathrm{P}(\bar{S} \gt 177.2)\) is seen)
Condone 1 – 0.02814 … = 0.9718…(awrt 0.972) only if clearly compared with 0.975
ALT: Allow \(Z = 1.9(088\ldots)\) and comparison with 1.96 (or better: calc gives 1.95996…)
or CR of \(\left[\bar{S}\right] \geqslant 177.248\ldots\) (awrt 177.25) Allow \(\left[\bar{S}\right] \gt 177.248\ldots\) (awrt 177.25)
Implied by diagram or correct interpretation of inequality with their CV
(Ignore any attempt at a lower CR for \(\bar{S}\))
2nd A1: (dep on 1st A1 and use of correct model. Use of N(177.2, …) scores A0)
for a conclusion using context: e.g. does not support student’s claim
or e.g. insufficient evidence of a difference in heights
Do not allow 2nd A mark for contradictory statements e.g. “significant” so “no support for claim”
| Scheme | Marks | AO |
|---|---|---|
| [\(p\)-value \(= 2 \times 0.02814\ldots =\)] 0.05628… in range 0.056~0.06 or 5.6(%)~6(%) | B1ft | 1.2 |
| (1) | ||
| (6 marks) |
Notes
B1ft: for answer in range 0.056~0.06 or 5.6%~6% (Ranges are inclusive, condone missing %)
(can ft their probability, provided < 0.5, from part (b) but not 0.025 leading to 5%)
NB: One-tail test [Max of 3/5 for (b) and (c)]
In (b) B0 (hypotheses) M1(model as above) 1st A1[for probability or \(Z\) compared with 1.6449 or CR \(\left[\bar{S}\right] \geqslant\) or \(\gt 176.95\ldots\) (awrt 177)] 2nd A1 for conclusion in context that supports claim or “heights of men from \(B\) is different from/greater than from \(A\)”
In (c) B0