INSTITUTE OF ACTUARIES OF INDIA

EXAMINATIONS
08th November 2011

Subject CT3 Probability & Mathematical Statistics

Time allowed: Three Hours (15.00 18.00)

Total Marks: 100

INSTRUCTIONS TO THE CANDIDATES

1. Please read the instructions on the front page of answer booklet and instructions to
examinees sent along with hall ticket carefully and follow without exception

2. Mark allocations are shown in brackets.

3. Attempt all questions, beginning your answer to each question on a separate sheet.
However, answers to objective type questions could be written on the same sheet.

4. In addition to this paper you will be provided with graph paper, if required.

5. Please check if you have received complete Question Paper and no page is missing. If
so kindly get new set of Question Paper from the Invigilator

AT THE END OF THE EXAMINATION

Please return your answer book and this question paper to the supervisor separately.
 IAI CT3- 1111

Q. 1) Let X be a discrete random variable taking values 0, 1 and 2 with probabilities p, 1-2p and p
respectively with 0 < p < 0.5.

Find the value of p for which Var (X) will be maximum.

[3]

Q. 2) Verify whether f(x), as defined below, is a probability density function:

3 2 2 4
0
(2)
If yes, find P[ 2 < X < 3 ]. (2)
[4]

Q. 3) The joint density function of X and Y is given by

, . , , 0

a) State the probability density functions and hence identify the statistical distributions of
i) Y (1)
ii) X conditional on Y = y. (1)

b) Compute E(Y) and Var(Y). (2)

c) Compute E(X|Y = y) and Var(X|Y = y). (2)
d) Hence, compute E(X) and Var(X). (4)
[10]

Q. 4) You are the producer for the television show Actuarial Idol. Each year, 1000 actuarial clubs
audition for the show. The probability of a club being accepted is 0.20.

The number of members of an accepted club has a distribution with mean 20 and variance 20.
Club acceptances and the number of club members are mutually independent.

Your annual budget for persons appearing on the show equals 10 times the expected total
number of persons plus 10 times the standard deviation of the total number of persons.

Calculate your annual budget for persons appearing on the show.

[5]

Page 2 of 7
 IAI CT3- 1111

Q. 5) Food packages, after filling, are weighed on an automatic device which rejects all packages
below 5.155 kg as they are considered under-weight. All rejected packages are carefully
weighed and their weights recorded. The table below represents the frequency distribution
obtained from a sample of 200 such weights:

Weights of rejected
Frequency
packages (kg)
5.075 - 5.085 1
5.085 - 5.095 3
5.095 - 5.105 3
5.105 - 5.115 7
5.115 - 5.125 10
5.125 - 5.135 23
5.135- 5.145 56
5.145 - 5.155 97
200

a) Determine the mean and standard deviation of this sample (6)

Assume the following:
The distribution of weights of the filled packets are normal
The distribution of weights of the rejected packets are normal
The standard deviation of the whole distribution may be estimated as 4 times the
standard deviation of this sample

b) Using the fact that the overall probability to reject a package is 0.05:
i) Show that an estimate of the mean weight of the whole distribution is 5.246 kg. (3)
ii) Hence, estimate the mean weights of the packages which are not rejected. (1)
[10]

Q. 6) A lamp requires a particular type of light bulb whose lifetime has a distribution with mean
3 (months) and variance 1. As soon as a bulb burns out, it is replaced with a new one.

What is the smallest number of bulbs you need to purchase so that, with probability at least
0.9772, the lamp burns for at least 40 months?

[Hint: Use Central Limit Theorem; (2) = 0.9772]

[5]

Page 3 of 7
 IAI CT3- 1111

Q. 7) Suppose you roll 10 four-faced dice, with faces labeled 1, 2, 3, 4, and each equally likely to
appear on top.
Let Xi denote the number showing up on the ith die when rolled for i = 1, 2 10. Assume Xi-s
are independent. Let S = X1 + X2 + + X10 denote the sum of the 10 numbers obtained.
Show that the moment generating function, MS(t), of S is given by:

[3]

Q. 8) Ayush and Shriya play a game as follows:

Ayush selects a positive integer { 1, 2, 3 } at random and writes it down on a piece of

paper
Shriya has two chances to ask Ayush what the number is.
Each time Ayush tosses a biased coin secretly, and reports to Shriya the number - 1 if a
head comes up and the number + 1 if a tail comes up.
Shriya has to guess the true value of based on the two numbers reported by Ayush after
two independent tosses of the coin.

It is known to Shriya that the coin has a probability 1/3 of showing a head. Let X and Y be the
two numbers which Ayush reported.

Shriya considers the following two estimators of :

if X Y

if X Y

a) Show that:

, , . (4)

b) Calculate the bias of S as an estimator of . Is S unbiased? (2)

c) Calculate the mean squared error of S as an estimator of . (2)
It can be shown that T is an unbiased estimator of with variance .

d) Which of the estimators T or S should Shriya use then if she wants to minimize the error of
her estimation? (2)
[10]

Page 4 of 7
 IAI CT3- 1111

Q. 9) The table below contains information about the annual inflation rates (averaged over an past
decade) of 22 countries, where for i = 1, 2, ,11

= loge(inflation rate) for the ith developing country,

= loge(inflation rate) for the ith developed country.

Developing countries Developed countries

Nation Nation
COSTA RICA -1.4697 0.0223 GERMANY -3.5066 0.7195
BAHAMAS -2.8134 2.2288 FINLAND -2.6593 0.0000
ZAIRE -0.7985 0.2725 AUSTRALIA -2.5257 0.0176
BARBADOS -2.6593 1.7924 ITALY -2.2073 0.2035
UGANDA -0.3285 0.9840 DENMARK -2.6593 0.0000
URUGUAY -0.7985 0.2725 LUXEMBERG -2.9957 0.1138
TURKEY -0.8916 0.1839 FRANCE -2.6593 0.0000
TANZANIA -1.3093 0.0001 U. KINGDOM -2.6593 0.0000
PERU 0.0770 1.9530 S. AFRICA -1.9661 0.4793
EGYPT -0.3147 1.0116 IRELAND -2.4079 0.0627
ETHIOPIA -3.2189 3.6040 BELGIUM -2.9957 0.1138
Total -14.5254 12.3251 Total -29.2422 1.7101

Assume that ,..., and ,, are realizations of two independent normal random
samples, each of size 11, drawn from , and , respectively.
a) Calculate an unbiased estimate of and an unbiased estimate of . (2)
b) Calculate a 95% equal-tailed confidence interval for .

0.025 0.050 0.100 0.900 0.950 0.975

a=10,b=10 3.717 2.978 2.323 0.431 0.336 0.269
a=10,b=11 3.526 2.854 2.248 0.434 0.340 0.273
a=11,b=10 3.665 2.943 2.302 0.445 0.350 0.284
(5)
a=11,b=11 3.474 2.818 2.227 0.449 0.355 0.288

c) Describe how you would make use of the confidence interval found in (b) to test

: against : ,

for some specified constant c at the 5% level. (2)

What is your conclusion for the test if c = 30? (1)

[10]

Page 5 of 7
 IAI CT3- 1111

Q. 10) A model for the spread of a measles epidemic initiated by one infective in a household of size 3
predicts that the total number of people infected in the household has the following distribution:

Total number infected: 1 2 3

Probability : 1 2 1 3 2

Here , the probability of adequate contact, is an unknown parameter.

The following data gives the frequency distribution of 334 such measles epidemics.

Total number infected: 1 2 3

Frequency : 34 25 275

a) Show that the maximum likelihood estimate of is 0.728. (6)

b) Carry out a chi-square goodness of fit test at 5% level of significance to examine if the
model provides a good fit to these data. (6)
[12]

Q. 11) Six insurance companies were being compared with regards to premium being charged for
house contents insurance for houses in a particular city. Independent random samples of five
policies from each company are examined and the premiums were recorded.

2
Company PremiumAmounts(y) y y
A 151 168 128 167 134 748 113,254
B 152 141 129 120 115 657 87,251
C 175 155 162 186 148 826 137,394
D 149 148 137 138 169 741 110,479
E 123 132 142 161 152 710 101,742
F 145 131 155 172 141 744 111,676
4,426 661,796

a) Compute an ANOVA table for these data, and show that there are no significant
differences, at the 5% level, between mean premiums being charged by each company. (5)

b) A colleague points out that Company C has the largest mean premium of 165.2 and that
Company B has the smallest mean premium of 131.4 and suggests performing t-test to
compare these two companies.

i) Perform this t-test, using the estimate of variance from the ANOVA table, and in
particular show that there is a significant difference at the 1% level. (3)
ii) Your colleague states that there is therefore a significant difference between the six
companies. Discuss the apparent contradiction with your conclusion in part (a). (2)
[10]

Page 6 of 7
 IAI CT3- 1111

Q. 12) An experiment is being conducted to check the efficacy of a newly invented medicine on mice.
Let yi be the value of the response variable for ith mouse receiving a dose of
xi for i = 1, 2, , 12.
A linear regression model is proposed to examine the impact of this medicine and is assumed to
take the following form:
, 1, 2, ,12

Here: x and ei-s are independent normal variables with mean zero and unknown
variance 2.

You are given the following summarized values for the data:
y = 716
2
y = 43,827
x = 453
2
x = 17,372
xy = 27,503
a) Using the results given in the actuarial tables:
i) Show that the least square estimates for and are given by:
where

12
where
12 (3)

ii) Show that the estimate of 2 is given by:

where 12 (1)

b) Hence, deduce the equation for the regression line using the summarized data given above. (3)

c) Devise a t-test for testing the following hypotheses: Ho: = 0 against H1: > 0. State your
conclusion at 5% significance level. (4)

d) It has now been discovered that there was a mistake in recording the values of the response
variable. The correct value should have been 10yi

i) Show that the least square estimate of is 10 where is as defined in part

(a) earlier. (2)
ii) Show that the estimate of 2 is 100 where is as defined in part (a)
(2)
earlier
iii) Hence establish how your t-test for the problem given in part (c) will change as a
result? Restate your conclusion at the same 5% significance level. (3)
[18]
******************

Page 7 of 7