Instructions

• Use black ink or ball-point pen.

• If pencil is used for diagrams/sketches/graphs it must be dark (HB or B).
• Fill in the boxes at the top of this page with your name, centre number and candidate number.
• Answer all the questions and ensure that your answers to parts of questions are clearly labelled.
• Answer the questions in the spaces provided – there may be more space than you need.
• You should show sufficient working to make your methods clear. Answers without working may
not gain full credit.
• Inexact answers should be given to three significant figures unless otherwise stated.

Information
• A booklet ‘Mathematical Formulae and Statistical Tables’ is provided.
• There are 7 questions in this question paper. The total mark for this paper is 75.
• The marks for each question are shown in brackets – use this as a guide as to how much time to
spend on each question.
• Calculators must not be used for questions marked with a * sign.

Advice
• Read each question carefully before you start to answer it.
• Try to answer every question.
• Check your answers if you have time at the end.
• If you change your mind about an answer, cross it out and put your new answer and any working
underneath.
1. Accidents occur randomly at a road junction at a rate of 18 every year.
The random variable X represents the number of accidents at this road junction in the next
6 months.

(a) Write down the distribution of X.

(2)
(b) Find P(X > 7).
(2)
(c) Show that the probability of at least one accident in a randomly selected month is
0.777 (correct to 3 decimal places).
(3)
(d) Find the probability that there is at least one accident in exactly 4 of the next
6 months.
(3)

(Total 10 marks)
Mark scheme for Question 1
Examiner comment

2. (a) Define

(i) a Type I error,

(ii) a Type II error.

(2)

Rolls of material, manufactured by a machine, contain defects at a mean rate of 6 per roll.

The machine is modified. A single roll is selected at random and a test is carried out to see
whether or not the mean number of defects per roll has decreased. The significance level is
chosen to be as close as possible to 5%.

(b) Calculate the probability of a Type I error for this test.

(3)
(c) Given that the true mean number of defects per roll of material made by the
machine is now 4, calculate the probability of a Type II error.
(2)

(Total 7 marks)
Mark scheme for Question 2
Examiner comment
3. (a) Write down the two conditions needed to approximate the binomial distribution
by the Poisson distribution.
(2)
A machine which manufactures bolts is known to produce 3% defective bolts. The
machine breaks down and a new machine is installed. A random sample of 200 bolts is
taken from those produced by the new machine and 12 bolts are defective.

(b) Using a suitable approximation, test at the 5% level of significance whether or

not the proportion of defective bolts is higher with the new machine than with the
old machine. State your hypotheses clearly.
(7)

(Total 9 marks)
Mark scheme for Question 3
Examiner comment

4. An archer shoots at a target until he hits it. The random variable S is the number of shots
needed by the archer to hit the target.

(a) State a suitable distribution to model S.

(1)
Given that the mean of S is 8, calculate the probability of the archer

(b) hitting the target for the first time on his 5th shot,
(3)
(c) taking at least 3 shots to hit the target for the first time.
(3)
(d) State any assumptions you have made in using this model.
(2)

(Total 9 marks)
Mark scheme for Question 4
Examiner comment
5. A total of 100 random samples of 6 items are selected from a production line n a factory and
the number of defective items in each sample is recorded. The results are summarised in the
table below.

Number of defective
0 1 2 3 4 5 6
items
Number of samples 6 16 20 23 17 10 8

(a) Show that the mean number of defective items per sample is 2.91.
(2)

A factory manager suggests that the data can be modelled by a binomial distribution with
n = 6. He uses the mean from the sample above and calculates expected frequencies as shown
in the table below.

Number of defective
0 1 2 3 4 5 6
items
Expected frequency 1.87 10.54 24.82 a 22.01 8.29 b

(b) Calculate the value of a and the value of b, giving your answers to 2 decimal places.
(4)
(c) Test, at the 5% level, whether or not the binomial distribution is a suitable model for
the number of defective items in samples of 6 items. State your hypotheses clearly.
(8)

(Total 14 marks)
Mark scheme for Question 5
Examiner comment
6. The probability generating function of the random variable X is given by

Gx(t) = k(1 + 2t + 2t2)2.

1
(a) Show that k = .
25
(2)
(b) Find P(X = 2).
(2)
(c) Calculate E(X) and Var(X).
(8)
(d) Write down the probability generating function of 2X + 1.
(2)

(Total 14 marks)
Mark scheme for Question 6
Examiner comment

7. The random variable Y is the number of times a biased coin is tossed until 3 heads have
occurred. The variance of Y is 60.

(a) Find the probability of obtaining a head.

(5)
(b) Find P(Y = 8).
(2)
(c) Find P(Y ≤ 10 the first head was gained on the second toss).
(5)

(Total 12 marks)
Mark scheme for Question 7
Examiner comment

TOTAL FOR PAPER: 75 MARKS

 A level Further Mathematics – Further Statistics 1 – Practice Paper 02 –
Mark scheme –
Mark scheme for Question 1 (Examiner comment) (Return to Question 1)

Question Scheme Marks

1(a) X ~ Po(9) M1A1

(2)
(b) P(X > 7) = 1 − P( X ≤ 7) M1

= [1 − 0.3239] =
0.6761 A1
(2)
(c) [Y = no. of accidents in a month] Y~Po(1.5) B1
P(Y ≥ 1) =1 − P(Y =0) M1
= [1 − 0.2231] =
0.7769 (= 0.777 (3dp))* A1cso
(3)
(d) [A = no. of months with at least one accident] A ~ B(6, 0.777) M1
6
P( A =   (0.777) 4 (0.223) 2
= 4) M1
 4
= 0.2719… awrt 0.272 A1

(3)

(10 marks)
 Mark scheme for Question 2 (Examiner comment) (Return to Question 2)

Question Scheme Marks

2(a)(i) Type I - H 0 rejected when it is true B1

(ii) Type II - H 0 is accepted when it is false B1

(2)
(b) P(X< c | λ = 6) ≈ 0.05 M1

P(X ≤ 2) = 0.0620

P(X ≤ 1) = 0.0174

Critical region = X ≤2 A1

P(Type 1 error) = P(X ≤ 2 | λ = 6) = 0.062 A1cao

(3)
(c) P(Type 2 error) = P(X ≥ 3 | = 4) M1

= 1 – 0.2381

= 0.7619 A1

(2)

(7 marks)
 Mark scheme for Question 3 (Examiner comment) (Return to Question 3)

Question Scheme Marks

3(a) n – large/high/big/ n >50 B1

p – small/close to 0 / p < 0.2 B1

(2)
(b) H0 : p = 0.03 H1 : p > 0.03 B1B1
Po(6) B1
P(X > 12 ) = 1– P(X < 11 ) or P(X ≤ 10 ) = 0.9574 M1
= 1 – 0.9799 P(X > 11 ) = 0.0426

= 0.0201 CR X > 11 A1

(0.0201 < 0.05)

Reject H0 or Significant or 12 lies in the Critical region. M1d

There is evidence that the proportion of defective bolts has increased. A1ft

(7)

(9 marks)
 Mark scheme for Question 4 (Examiner comment) (Return to Question 4)

Question Scheme Marks

4(a) Geometric B1

(1)
(b) p= 1
8 B1

P(S = 5) = ( 87 )4 × (81 ) M1

= 0.073 A1
(3)
(c) M1
P(S ≥ 3) = (1 – p)2
A1ft
= ( 87 )2 = 49
64 awrt 0.766 A1

(3)
(d) Assume shots are independent and probability of hits is constant B1B1

(2)

(9 marks)
 Mark scheme for Question 5 (Examiner comment) (Return to Question 5)

Question Scheme Marks

5(a) 1×16 + 2 × 20 + ... + 6 × 8

Mean= = 2.91 **ag** M1A1
100

(2)
(b) 2.91
=p = 0.485 B1
6
a = 100 × C36 × 0.4853 × 0.5153 = 31.17 M1A1

100 × 0.4856 =
b= 1.3(0) A1
(4)
(c) H 0 : Binomial is a good fit
H1 : Binomial is a not a good fit B1

Number
of
0 or 1 2 3 4 5 or 6
defective M1
items
O 22 20 23 17 18
E 12.41 24.82 31.17 22.01 9.59
(O − E ) 2 (22 − 12.41) 2 (20 − 24.82) 2 (18 − 9.59) 2
∑= E 12.41
+
24.82
+ ... + = 18.998...
9.59 M1A1
awrt 19.0

ν =5-2=3 degrees of freedom B1

χ 32 (5%) = 7.815 B1ft

18.998... >7.815 so reject H 0 M1

Binomial is a not a good fit (and is not a good model for the number of
A1
defective items in samples of size 6)
(8)

(14 marks)
 Mark scheme for Question 6 (Examiner comment) (Return to Question 6)

Question Scheme Marks

6(a) Gx(1)= 1 M1
1
k (1 + 2 + 2)2 = 1 ⇒ k= *AG cso A1
25
(2)
(b) 1 1
(1 +2t + 2t2) (1 +2t + 2t2) = (1 + 4t + 8t2 +…) M1
25 25
8
P(X = 2) = A1
25
(2)
(c) 2
G’x(t) = (1 +2t + 2t2)(2 + 4t) M1A1
25
12 12
G’x(t) = ⇒ E(X) = A1
5 5
2 2
G”x(t) = (2 + 4t) (2 + 4t) + (1 +2t + 2t2) . 4 M1A1
25 25
112
G”x(t) = A1
25
2
112 12  12  28
Var(X) = + −  = M1A1
25 5  5 25

(8)
(d) t
(1 + 2t2 + 2t4)2 B1B1
25
(2)

(14 marks)
 Mark scheme for Question 7 (Examiner comment) (Return to Question 7)

Question Scheme Marks

7(a) 3(1 − p )
60 = M1A1
p2

20p = 1 – p M1
(5p – 1)(4p + 1) = 0 M1
p= 1
5 A1

(5)
(b) 7
P(Y = 8) =   p2 (1 – p)5 × p M1
 2
3
7  1   4  5
=   ×   ×   = 0.05505 awrt 0.055 A1
 2  5   5 
(2)
(c) P(Y ≤ 10...) = 1 – P(Y ≥ 111st head on 2nd toss) M1

= 1 – P(0 heads in 8 tosses) – P(1 head in 8 tosses) M1

= 1 – 0.88 – 8 × 0.2 × (0.8)7 A1A1

= 0.49688 A1

(5)

(12 marks)
 A level Further Mathematics – Further Statistics 1 – Practice Paper 02 –
Examiner report –
Examiner comment for Question 1 (Mark scheme) (Return to Question 1)
1. Parts (a) and (b) were well answered although in part (a) a few candidates wrote down Poisson
but forgot to give the value of λ .
Since part (c) is a ‘show that’ question candidates were required to write down all the steps
needed to reach 0.777. Many candidates went straight from 1 – P(Y = 0) to 0.7769 to gain full
marks they were required to write down the figures between these two stages
(1 – 0.2231).
Most candidates identified the Binomial with n = 6 and p = 0.777 in part (d) but few could
progress any further. Many who did try either omitted 6C4 or used (0.777)2 (1 – 0.777)4.
Examiner comment for Question 2 (Mark scheme) (Return to Question 2)
2. The definitions of a type I and type II error were usually clearly written with many candidates
giving the exact definition given in the mark scheme.
In part (b) the main error was to select the critical region, X ≤ 1 rather than X < 2 since
P(X ≤ 2 ) is closer to 5% than P(X ≤ 1 ).
In part (c) most candidates were able to identify the correct probability required for a type II
error following their CR in part (b) so gaining the method mark.
Examiner comment for Question 3 (Mark scheme) (Return to Question 3)
3. This question was accessible to the majority of candidates. Whilst many candidates knew “the
two conditions needed to approximate the binomial distribution by the Poisson distribution this
knowledge was by no means universal. Some candidates appear to have tried to memorise the
conditions for:
• modelling a situation using a Binomial distribution
• modelling a situation using a Poisson distribution
• approximating the binomial distribution with the Poisson distribution
• approximating the binomial distribution with the Normal distribution

but failed to remember which set of conditions applies in which situation.

The response to part (b) was very good, with many candidates gaining full marks. The most
common error made was to state the hypotheses as H 0 : λ = 6 and H 1 : λ > 6 . The question
clearly states that we are testing for a ‘proportion’, so that the null hypotheses should be
H 0 : p = 0.03 and H 1 : p > 0.03 . The majority of candidates used the correct Poisson
distribution and successfully calculated the probability 0.0201.
It was common to see candidates using the incorrect statement P(X ≥ 12) = 1 – P(X ≤ 12) or
calculating 1 – P(X ≤ 10) and writing CR: X ≥ 10. The candidates who tried to find the critical
region were more likely to make an error and it is recommended that the probability route is
used.
It is pleasing to see that most candidates finished their answers well with a clear conclusion
using the context written in the question.
 Examiner comment for Question 4 (Mark scheme) (Return to Question 4)
4. Almost all the candidates used the geometric distribution in this question and the first two
parts were answered well. There was some misinterpretation of “at least 3” in part (c) but
most obtained the correct answer although not always from simply writing down (1 − p ) 2 .
The examiner required the answers in part (d) to be given in context. Thus a comment that
simply stated that the trials (not the shots) were independent, or that the probability of success
(rather than the probability of hitting the target) was constant did not score any marks.
Examiner comment for Question 5 (Mark scheme) (Return to Question 5)
5. This was a good question for most candidates as they recognised it as a standard example of
this type of test. In part (a) most candidates now realise that some working has to be shown,
and few failed to score here. Part (b) was also well done. The test in part (c) was also done very
well, but there are still many candidates who are not aware of the fact that they should not state
inappropriate values of the parameters in their hypotheses. Only a minority of candidates failed
to group classes and a similarly small number failed to give the correct degrees of freedom.
Examiner comment for Question 6 (Mark scheme) (Return to Question 6)
6. A reasonable start for many meant full marks for the derivation of the given answer. The
calculus in part (c) was often confused and incomplete and many variations on the answer to
part (d) usually involved t/25 and so gained the first mark but not the second.
Examiner comment for Question 7 (Mark scheme) (Return to Question 7)
7. Most candidates used the negative binomial distribution here (only a small minority tried the
geometric) and the formula was usually quoted correctly although the 3 was sometimes missed.
There were few problems in manipulating the resulting equation into a quadratic in p and then
solving to find p = 15 . Part (b) was answered well, but part (c) caused difficulties. The
common approach was to use a negative binomial distribution with r = 2 and x taking values
from 2 to 8 but unfortunately the correct 7 cases were not always used. Some candidates used
a binomial distribution with n = 8 and p = 15 and then simply found P( X ≥ 2 ) which yielded
the answer quite simply.