Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd
Upload
25 views

BSC (Hons) Actuarial Science: Cohort: Bas/11/Ft

This document contains instructions for a 2-hour exam on Probability and Statistics 2. It consists of 4 questions worth 25 marks each, for a total of 100 marks. The exam contains both theoretical and application-based probability and statistics problems. Students are instructed to show their work, use 3 significant figures, start new questions on fresh pages, and use the provided statistical tables.

Uploaded by

HaniyaAngel
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
25 views

BSC (Hons) Actuarial Science: Cohort: Bas/11/Ft

This document contains instructions for a 2-hour exam on Probability and Statistics 2. It consists of 4 questions worth 25 marks each, for a total of 100 marks. The exam contains both theoretical and application-based probability and statistics problems. Students are instructed to show their work, use 3 significant figures, start new questions on fresh pages, and use the provided statistical tables.

Uploaded by

HaniyaAngel
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 9

BSc (Hons) Actuarial Science

Cohort: BAS/11/FT

Examinations for 2011 - 2012 / Semester 2


MODULE: PROBABILITY AND STATISTICS 2
MODULE CODE: MATH1155C
Duration: 2 Hours
Instructions to Candidates:
1. Answer all FOUR (4) Questions.
2. Questions may be answered in any order but your answers must show
the question number clearly.
3. Give non-exact numerical answers correct to 3 significant figures.
4. Always start a new question on a fresh page.
5. All questions carry equal marks.
6. Statistical tables are appended at the end of the paper.
7. Total marks: 100.

This question paper contains 4 questions and 9 pages.


Page 1 of 9

ANSWER ALL FOUR (4) QUESTIONS


Question 1: (25 Marks)
(a) The random variable X follows the binomial distribution B(10, 0.15).
Find the probability that the mean of a random sample of 50 observations of X is greater than 1.4.
[5 marks]
(b) The random variable X has density function
{
(k + 1)xk , 0 x 1,
f (x) =
0,
otherwise.
Given n independent observations x1 , x2 , ..., xn of X, nd the maximum
likelihood estimator of k.
[7 marks]
(c) The weights, x grams, of 30 randomly chosen rabbits are summarised
as:

x = 31 500,
x2 = 33 141 816.
(i) Prove that the sample mean is an unbiased estimate of the population mean.
(ii) Calculate unbiased estimates of the population mean and variance
of the weights.
A random sample of n rabbits is taken.
(iii) Estimate the value of n for which it is approximately 95% certain
that the sample mean weight does not dier from the population
mean weight by more than 6 grams.
(iv) Estimate the value of n that would be required in order for a 98%
condence interval for the mean weight to have width 20.
[4+3+3+3=13 marks]

Page 2 of 9

Question 2: (25 Marks)


(a) An insurance company has a certain type of policy which can be claimed
only 3 or more years after the policy is bought. The policy expires once
the claim is made. It is proposed to model the duration, X years, of
such a policy by the distribution with density function
f (x) = e(3x) ,

3 x < ,

> 0.

The durations of n such policies which have expired and which may
be assumed to be independent are denoted by x1 , x2 , ..., xn . Using the
method of moments, nd an estimate for .
[6 marks]
(b) A survey was carried out among a random sample of men and women to
know whether they wear a watch on the left wrist, on the right wrist or
do not wear a watch. The table shows the number of men and women
in each category.
left wrist
men
85
women 118

right wrist do not wear


78
37
61
25

Perform a 2 test, at 5% signicance level, to determine whether there


is association between men and women regarding the wearing of watch.
[9 marks]
(c) In the past, the number of daily sales of a store has been modelled
by a random variable with distribution Po(0.8). Following a publicity
campaign, the manager hopes that the mean number of daily sales will
increase. To test, at 5% signicance level, whether this is the case,
the total number of sales during the rst 3 days after the campaign is
noted.
(i) Given that the total number of sales during the rst 3 days after
the campaign is 5, carry out the test.
(ii) Explain what is meant by a Type I error in this context and nd
the probability it occurs.

Page 3 of 9

(iii) State what further information is required in order to nd the


probability of a Type II error.
[5+4+1=10 marks]

Question 3: (25 Marks)


(a) The weights of 12 mothers, x kg, and of their eldest daughters, y kg,
are as shown below.
x
y

65 63 67 64 68 62 70 66 68 67 69 71
68 66 68 65 69 66 68 65 71 67 68 70

(i) Perform a linear regression analysis to obtain the equation of the


least-squares line in the form y = a + bx.
(ii) Calculate the correlation coecient and the standard error estimate.
(iii) Test, at 5% signicance level, the null hypothesis that the regression coecient, b, is as low as 0.18.
(iv) Calculate a 95% condence interval for b.
[6+4+4+3=17 marks]
(b) The thickness of washers produced by a machine since it started operating is known to follow a normal distribution with mean 2 mm and
standard deviation 0.3 mm. Due to a recent mechanical problem, an
engineer claims that the mean thickness has changed. A random sample of 100 washers was taken and the mean thickness was found to be
1.9475 mm.
(i) Test, at 10% signicance level, the engineers claim.
(ii) This result is signicant at % level. Find the smallest possible
integer value of .
[5+3=8 marks]

Page 4 of 9

Question 4: (25 Marks)


(a) Some students were divided into four groups, and each group was subjected to one of four teaching techniques A, B, C and D. Due to
dropouts, the number of students varied at the end of the teaching
period when an assessment was carried out. The marks of the students
in each group are as shown below.
A
B
C
D

65
75
59
94

87
69
78
89

73
83
67
80

79 81 69
81 72 79 90
62 83 76
88

(i) Conduct an analysis of variance test, at 5% signicance level, to


determine whether the data indicate a signicant dierence in the
mean achievements of the four groups.
(ii) Calculate a 95% condence interval for the mean mark of group
A.
(iii) Calculate a 95% condence interval for the dierence between the
mean marks of groups A and D. In light of this interval containing
zero or not, comment on the mean marks of groups A and D.
[9+3+5=17 marks]
(b) 600 people having an infection are divided equally into 2 groups A and
B. A pill is given to group A, but not to group B; otherwise, the two
groups are treated identically. One week later, it is found that 225
people in group A and 195 people in group B have recovered from the
infection.
(i) Test, at 5% signicance level, the hypothesis that the pill helps to
cure the infection.
(ii) Find the P-value of the test.
[6+2=8 marks]
***END OF QUESTION PAPER***

Page 5 of 9

Page 6 of 9

Page 7 of 9

Page 8 of 9

Page 9 of 9

You might also like