Q1.

The heights of a particular type of plant have a normal distribution with mean 20
centimetres and variance 6.5536 cm2

A random sample of 25 plants is taken.

(a) (i) Describe the distribution of the sample mean of the 25 plants.
(1)

(ii) Find the probability that the mean height of the plants is greater than 21
centimetres, giving your answer to three significant figures.
(3)

(b) (i) Describe the distribution of the total height of the sample of 25 plants.
(1)

(ii) Find the probability that the total height of the plants is greater than 525
centimetres, giving your answer to three significant figures.
(3)

(c) Explain the link between your answers to parts (a)(ii) and (b)(ii).
(2)
(Total 10 marks)

Q2.
A weed treatment prevents weeds growing for a mean of 70 days in areas to which it is
applied.

A new chemical is added to the treatment. The new treatment is applied to a random
sample of 100 different areas and the number of days, x, for which the new treatment
prevents weeds growing is recorded. The results are summarised below.

∑x = 7060 and ∑x2 = 499 000

Test whether the mean number of days for which the weed treatment prevents weeds
growing has increased from 70 days, using the 1% level of significance.
(Total 10 marks)

Q3.
A random sample of 50 full-time university employees was selected as part of a higher
education salary survey.

The annual salary in thousands of pounds, x, of each employee was recorded, with the
following summarised results.

x̅ = 45.8 and s = 24.0

Also recorded was the fact that 6 of the 50 salaries exceeded £60 000.

(a) Show why the annual salary, X, of a full-time university employee is unlikely to be
normally distributed. Give numerical support for your answer.
(2)
 (b) (i) Indicate why the mean annual salary, X, of a random sample of 50 full-time
university employees may be assumed to be normally distributed.
(2)

(ii) Hence construct a 99% confidence interval for the mean annual salary of full-
time university employees.
(4)

(c) It is claimed that the annual salaries of full-time university employees have an
average which exceeds £55 000 and that more than 25% of such salaries exceed
£60 000.

Comment on each of these two claims.

(3)
(Total 11 marks)

Q4.
A random sample of 50 full-time university employees was selected as part of a higher
education salary survey.

The annual salary in thousands of pounds, x, of each employee was recorded, with the
following summarised results.

∑ x = 2290.0 and ∑ (x − x̅)2 = 28 225.50

Also recorded was the fact that 6 of the 50 salaries exceeded £60 000.

(a) (i) Calculate values for x̅ and s, where s2 denotes the unbiased estimate of σ 2.
(3)

(ii) Hence show why the annual salary, X, of a full-time university employee is
unlikely to be normally distributed. Give numerical support for your answer.
(2)

(b) (i) Indicate why the mean annual salary, X̅, of a random sample of 50 full-time
university employees may be assumed to be normally distributed.
(2)

(ii) Hence construct a 99% confidence interval for the mean annual salary of full-
time university employees.
(4)

(c) It is claimed that the annual salaries of full-time university employees have an
average which exceeds £55 000 and that more than 25% of such salaries exceed
£60 000.

Comment on each of these two claims.

(3)
(Total 14 marks)

Q5.
(a) A simple random sample is taken from car owners in a town.

(i) State the population for this sample.

(1)
 (ii) State a condition which must be satisfied by a simple random sample.
(1)

(b) State the parameter used in calculating probabilities using the Poisson distribution.
(1)

(c) State the parameters used in calculating probabilities using the normal distribution.
(2)
(Total 5 marks)

Q6.
The weight, X kilograms, of sand in a bag can be modelled by a normal random variable
with unknown mean μ and known standard deviation 0.4.

(a) The sand in each of a random sample of 25 bags from a large batch is weighed.
The total weight of sand in these 25 bags is found to be 497.5 kg.

(i) Construct a 98% confidence interval for the mean weight of sand in bags in
the batch.
(5)

(ii) Hence comment on the claim that bags in the batch contain an average of 20
kg of sand.
(2)

(iii) State why use of the Central Limit Theorem is not required in answering part
(a)(i).
(1)

(b) The weight, Y kilograms, of cement in a bag can be modelled by a normal random
variable with mean 25.25 and standard deviation 0.35.

A firm purchases 10 such bags. These bags may be considered to be a random

sample.

(i) Determine the probability that the mean weight of cement in the 10 bags is
less than 25 kg.
(4)

(ii) Calculate the probability that the weight of cement in each of the 10 bags is
more than 25 kg.
(4)
(Total 16 marks)

Q7.
Becky owns a taxi. Each weekday morning, she collects Steve from his home and takes
him to the train station.

A record of the times, x minutes, for a random sample of 65 such taxi journeys is
summarised by

and

(a) (i) Calculate the value of the sample mean, x.

 (1)

(ii) Show that, correct to two decimal places, s = 2:50, where s2 denotes the
unbiased estimate of the population variance.
(2)

(b) (i) Construct a 96% confidence interval for the mean journey time.
(4)

(ii) State why use of the Central Limit Theorem was required in calculating this
confidence interval.
(1)

(c) Comment on Becky’s claim that the mean journey time is more than 20 minutes.
(2)
(Total 10 marks)
Mark schemes

Q1.

Answer Mark Comments

(a)
(i) B1 oe

(ii)

M1 Standardises

= 1 – Φ(1.95)
M1 PI
= 1 – 0.97441
= 0.0254 to 0.0256 A1 AWFW

(b)
(i) B1 oe

(ii)

M1 Standardises

= 1 – Φ(1.95)
M1 PI
= 1 – 0.97441
= 0.0254 to 0.0256 A1 AWFW

(c) The probabilities are the

E1 oe
same
This is because a total height
of 525 centimetres is the
same as a mean height of 21 E1 oe

cm as

Total 10 marks
Q2.

Answer Marks Comments

H0: µ = 70 [days]
B1
H1: µ > 70

B1 Seen or used

Attempt at variance formula

M1
Allow one slip

A1 Implied by correct answer

(oe 188/33)
ARWT 5.70
accept s = 2.38[6832566]

M1

M1 Calculates z with their s2, their

and their µ
or for se = 0.238…
or P( ≥ 70.6) = 0.006

= 2.5[13791745] A1 or sight of 70.56 for

or 0.00597
AWRT 2.3 or for CR is >
zcrit = 2.3[26347931] B1
70.56
Reject H0 as 2.5[137…] > A1ft Allow ‘accept H1’
2.3[263…]
Follow through their z and zcrit
or z > zcrit provided signs are consistent
or comparison of 70.6 > 70.56
or comparison of their
‘0.00597’ to 0.01
Evidence to suggest that E1 Must be consistent with their
weed treatment has an conclusion on whether to
increase in the ‘mean number accept H1 or not based on
of days’ claimed [at the 1% their z and zcrit if not explicitly
level] stated

10

Question Total 10

Q3.
(a) x̅ − ns = (45.8 − n × 24.0) < 0
 SC: Accept quoted values of (−4 to −1) (n = 2) or
(−28.5 to −23.5) (n = 3) (both AWFW)
and
Allow (45 to 47) and any multiple of (23.5 to 24.5)
which
gives value < 0
Must clearly state the value of a numerical
expression

M1

negative salaries are impossible

OE; must be in context
Negative values impossible ⇒ A0

A1
2

Alternative solution 1

P(X < 0 | N(45.8, 24.02)) = P(Z < −1.91)

Standardising 0 using 45.8 & 24.0

(M1)

= 0.027 to 0.03
In addition to probability within range, must state
that
negative salaries are impossible

(A1)
(2)

Alternative solution 2

P(X > 60 | N(45.8, 24.02)) = P(Z > 0.59)

Standardising 60 using 45.8 & 24.0

(M1)

= 0.27 to 0.28
In addition to probability within range, must
compare
calculated value to 6/50 = 0.12 OE

(A1)
(2)

(b) (i) Large sample or n > 25 or 30 or n = 50

so
OE

B1
 CLT applies
Must indicate CLT; dependent on B1
Indication that other than sample mean is normally
distributed ⇒ Bdep0

Bdep1
2

(ii) 99% (0.99) ⇒ z = 2.57 to 2.58

AWFW (2.5758)

B1

CI for µ is x̅ ± z ×
Used with (45.8 & 24.0) and
z(1.64 to 2.58) & ÷ with n > 1

M1

Thus 45.8 ± 2.5758 ×

F on z(1.64 to 1.65 or 2.32 to 2.33

or 2.57 to 2.58) and ÷

AF1

Hence 45.8 ± (8.7 to 8.8) or 45800 ± (8700 to 8800)

OR
(37.(0) to 37.1, 54.5 to 54.6) or (37000 to 37100, 54500 to
54600)
CAO / AWFW (8.74)
Ignore (absence of) quoted units
AWFW

A1
4

(c) Clear correct comparison of 55 or 55000 with c’s UCL or CI

Accept 55000 compared with c’s 54.5 to 54.6
(ie different units)

B1

(6/50 or 0.12 or 12%) </≠ 0.25 or 25%

OE; correct comparison mentioning both 12% and
25%

B1

Reject both / each of the two claims

 Dependent on B1 B1

Bdep1
3

Additional comment illustrations

It / (claimed) mean / (claimed) value > UCL / CI

Must indicate 55 or 55000

(B0)

99% have (mean) weights between CLs so...

(B0)

Any comparison of 60 (£60 000) with UCL / CI

Value of 60 does not refer to mean

(B0)

P(X > 60 | N(45.8, 24.02)) = P(Z < 0.59)

= (0.27 to 0.28) > 6/50 = 0.12
Assumes salaries ~ N; cf (a)(ii)

(B0)
[11]

Q4.

(a) (i) x̅ = = 45.8 or 45800

CAO

B1

(s2 =) or (s =)
Ignore notation

M1

s = 24(.0) or 24000 to 24001

AWRT / AWFW (24.00064)
(σ = 23.75942)

SCs: (for no seen working)

M1 A1 for 24.0 or 24000 to 24001
M1 A0 for 24 or 23700 to 23800

A1
 3

(ii) x̅ − ns = (45.8 − n × 24.0) < 0

SC: Accept quoted values of
(−4 to −1) (n = 2) or (−28.5 to −23.5) (n = 3) (both AWFW)
Allow (45 to 47) and any multiple of
(23.5 to 24.5) which gives value < 0
Must clearly state the value of a numerical
expression

M1

and negative salaries are impossible

OE; must be in context
Negative values impossible ⇒ A0

A1
2

Alternative solution 1

P(X < 0 | N(45.8, 24.02) = P(Z < −1.91)

Standardising 0 using 45.8 & 24.0

(M1)

= 0.027 to 0.03
In addition to probability within range,
must state that negative salaries are impossible

(A1)
(2)

Alternative solution 2

P(X > 60 | N(45.8, 24.02)) = P(Z > 0.59)

Standardising 60 using 45.8 & 24.0

(M1)

= 0.27 to 0.28
In addition to probability within range,
must compare calculated value to 6 / 50 = 0.12 OE

(A1)
(2)

(b) (i) Large sample or n > 25 or 30 or n = 50

OE

B1

so CLT applies
 Must indicate CLT; dependent on B1
Indication that other than sample mean
is normally distributed ⇒ Bdep0

Bdep1
2

(ii) 99% (0.99) ⇒ z = 2.57 to 2.58

AWFW (2.5758)

B1

CI for μ is x̅ ± z ×
Used with (x̅ & s) from (a)(i) and
z(1.64 to 2.58) & ÷ with n > 1

M1

Thus 45.8 ± 2.5758 ×

F on (x̅ & s) with ÷ &
z(1.64 to 1.65 or 2.32 to 2.33 or 2.57 to 2.58)
AF1

Hence 45.8 ± (8.7 to 8.8)

or 45800 ± (8700 to 8800)
OR
(37.(0) to 37.1, 54.5 to 54.6)
or (37000 to 37100, 54500 to 54600)

CAO / AWFW (8.74)

Ignore (absence of) quoted units
AWFW

A1
4

(c) See supplementary sheet for additional illustrations

Clear correct comparison of 55 or 55000 with c’s UCL or CI

Accept 55000 compared with
c’s 54.5 to 54.6 (ie different units)

B1

(6/50 or 0.12 or 12%) </≠ 0.25 or 25%

OE; correct comparison mentioning both 12% and
25%

B1
 Reject both / each of the two claims
Dependent on B1 B1

Bdep1
3

Additional comment illustrations

It / (claimed) mean / (claimed) value > UCL / CI

Must indicate 55 or 55000

(B0)

99% have (mean) weights between CLs so...

(B0)

Any comparison of 60 (£60 000) with UCL / IC

Value of 60 does not refer to mean

(B0)

P(X < 60 | N(45.8, 24.02)) = P(Z > 0.59)

= (0.27 to 0.28) < 6 / 50 = 0.12
Assumes salaries ~ N; cf (a)(ii)

(B0)
[14]

Q5.

Answer Mark Comments

(a)
All the car owners in the town E1 Must include ‘all’ or ‘every’
(i)

(ii) A sample where each

member of the population has
an equal probability of being
chosen
or E1 oe
Each sample of the required
size from the population has
an equal probability of being
chosen

(b) Average number of events in

B1 oe
an interval
 (c) Mean B1
Standard deviation B1 Accept variance
SC1 for μ and σ or μ and σ2

Total 5 marks

Q6.

(a) (i) x̅ = = 19.9

CAO

B1

98% (0.98) ⇒ z = 2.32 to 2.33

AWFW (2.3263)

B1

CI for μ is x̅ ± z ×
Used with z (2.05 to 2.58),
x̅ (497.5 or 19 to 21) and σ (0.4)
and ÷ with n > 1

M1

Thus 19.9 ± 2.3263 ×

z (2.05 to 2.06 or 2.32 to 2.33 or 2.57 to 2.58),
x̅ (19.9) and σ (0.4) and ÷
A1

Hence19.9 ± 0.2
CAO / AWRT (0.186104)

or

(19.7, 20.1)
AWRT

A1
5

(ii) Clear correct comparison of 20 with CI

F on CI providing it contains 20

eg 20 is within CI or LCL < 20 < UCL

Quoting values for CI is not required
 BF1

Agree with claim or no reason to doubt claim

OE; dependent on previous BF1

Bdep1
2

(iii) Weight of sand in a bag or X / x or original

distribution or parent population
It / mean / data / sample / information / sand is
normal ⇒ B0

is normal
Reference only to sample size or standard
deviation ⇒ B0

B1
1

(b) (i) Y ~ N(25.25, 0 35 )

2

Accept percentage equivalent probabilities

V(mean) = 0.352 / 10 or 0.0122 to 0.0123

CAO / AWFW (0.01225)

or

SD (mean) = 0.35 / √10 or 0.11 to 0.111

CAO / AWFW (0.11068)

B1

Standardising 25 using 25.25 and 0.35 / √10 OE

but allow (25.25 − 25)

M1

= P(Z < − 2.25877) = 1 − P(Z < 2.25877)

Correct area change
May be implied by a correct answer or an answer
< 0.5

m1

= 1 − (0.98809 to 0.98778)

= 0.011 to 0.013
AWFW (0.01195)
(0.987 to 0.989) ⇒ B1 M1 m0 A0
 A1
4

(ii)
Standardising 25 using 25.25 and 0.35 but allow
(25.25 − 25)

M1

= P(Z > −0.71429) = P(Z< 0.71429)

= 0.761 to 0.764
AWFW (0.76247)
(0.236 to 0.239) ⇒ M1 A0

A1
P(Y > 25 in each of 10) = p10

Any p providing 0 < p < 1

10

May be implied by a correct answer

M1

= 0.065 to 0.068
AWFW (0.06641)

A1
4
[16]

Q7.
(a) (i) Mean,
CAO

B1
1

(ii) Standard deviation

Expression must be seen

M1

= 2.50
AWRT (2.50075)

A1
2
 NB: (6.15754 or 6.25375)
No and / or use of divisor n

(B1)

or

(2.48144)
Use of divisor n

(B1)

(b) (i) 96%(0.96) z = 2.05 to 2.06

AWFW (2.0537)

B1

CI for μ is
Used
Must have with n > 1

M1

Thus 20± 2.0537 ×

F on and z

A1F

Hence or (19.8, 21(.0))

AWRT

A1
4

(ii) Times / X are not (known to be) normally distributed

Or equivalent
Not data, values, sample, n large

B1
1

(c) CI in (b)(i) contains/includes 20

Or equivalent
Dependent on CI in (b)(i)
 B1F

thus

no (significant) evidence to support claim

Or equivalent
Dependent on B1F

Bdep1
2
[10]