You are on page 1of 5

ACTS 4304

Instructor: Natalia A. Humphreys


SOLUTION TO HOMEWORK 1
Lesson 1: Basic Probability. Lesson 3: Variance.
Problem 1
You are given the following joint distribution of two random variables X and Y :

(x, y) P r ((X, Y ) = (x, y)) (x, y) P r ((X, Y ) = (x, y))


(1, 1)

0.3

(1, 2)

0.23

(2, 2)

0.27

(2, 3)

0.2

Calculate the third central moment of Y .


Solution. The joint distribution of (X, Y) could be described as follows:

x=1 x=2
y=1

0.3

y=2

0.23

0.27

y=3

0.2

fY (y) =

f (x, y)

fY (1) =

f (x, 1) = 0.3 + 0 = 0.3

fY (2) =

f (x, 2) = 0.23 + 0.27 = 0.5

fY (3) =

f (x, 3) = 0 + 0.2 = 0.2

Check:

y fY (y)

= 0.3 + 0.5 + 0.2 = 1


X
E[Y ] =
yfY (y) = 1 0.3 + 2 0.5 + 3 0.2 = 0.3 + 1 + 0.6 = 1.9
y

E[Y ] =

E[Y 3 ] =

y 2 fY (y) = 1 0.3 + 4 0.5 + 9 0.2 = 0.3 + 2 + 1.8 = 4.1

y 3 fY (y) = 1 0.3 + 8 0.5 + 27 0.2 = 0.3 + 4 + 5.4 = 9.7

3 =

03

302 + 23 = 9.7 3 4.1 1.9 + 2 1.93 = 9.7 23.37 + 13.718 = 0.048

ACTS 4304. SP 2015. SOLUTION TO HOMEWORK 1.

Problem 2
The random variable X has the density function
f (x) =

5x2
, 0<x<
(2 + x3 )4

Determine the mode of X.


Solution. By definition, a mode of the distribution is x such that f (x) is maximized. Differentiating
f (x), we obtain:
f 0 (x) = 5

x(2 + x3 ) 6x4
x(2 5x3 )
2x(2 + x3 )4 x2 4(2 + x3 )3 3x2
=
10

=
10

(2 + x3 )8
(2 + x3 )5
(2 + x3 )5

Solving f 0 (x) = 0, we obtain:


"
x(2 5x3 ) = 0
Therefore, the mode is 0.7368.

x = 0q= xmin
2
5

x=

0.7368 = xmax

Problem 3
A doughnut shop has purchased a liability policy for its doughnut making machines from the same
insurance company for the past five years. The number of service calls by the company as the result
of machine malfunctions is shown below:
Year Service Calls
2010

2009

2008

2007

2006

Calculate the variance of the empirical distribution of the number of service calls per year.
Solution. By definition of a variance of the empirical distribution,
5

V ar(X) =

1X
2
(Xi X)
5
i=1

The sample mean is:


5

X
1
=1
X
Xi = (5 + 2 + 4 + 3 + 9) = 4.6
5
5
i=1

and
are : 0.4, 2.6, 0.6, 1.6, 4.4
Xi X
Therefore,
V ar(X) =

1
1
(0.16 + 6.76 + 0.36 + 2.56 + 19.36) = 29.2 = 5.84
5
5

Copyright Natalia A. Humphreys, 2015

Page 2 of 5

ACTS 4304. SP 2015. SOLUTION TO HOMEWORK 1.

Problem 4
For the random variable X you are given:
(i) E[X]=4
(ii) Var(X)=90
(iii) E[X 3 ] = 20
Calculate the skewness of X.
Solution. We have:
3 3
; = ( 2 )3/2 = (90)3/2 = 853.815
3
3 = 03 302 + 23

1 =

2 = 02 2 02 = 2 + 2 = 90 + 16 = 106
3 = 20 3 106 4 + 2 64 = 20 1272 + 128 = 1124
1124
= 1.3164 
1 =
853.815
Problem 5
By definition, a continuous random variable X has two-parameter Pareto distribution if its probability
density function f (x) is defined as follows:

f (x) =
, x > 0, > 0, > 1
(x + )+1
Using definition of expectation, show that

E[X] =
1
Solution. By definition of expectation:
Z
Z
E[X] =
xf (x)dx =

x
dx =
dx =
+1
(x + )
(x + )+1

0
0
Let us make a substitution: u = x + . Then x = u and dx = du. Getting back to our integral,
we have:

Z
Z
Z
u

u du
u
du =
du =
=
u+1

 +1



u
1
1

=
| +
| =

=

1

1
Problem 6
Two numbers are drawn independently from a uniform distribution on [0, 5]. What is the variance of
their product?
Solution. By definition of the variance: V ar(XY ) = E[X 2 Y 2 ] E(XY )2 . We have E[X] =
E[Y ] = 2.5. Since X and Y are independent, E(XY ) = E[X] E[Y ] = 2.52 = 6.25. Next, E[X 2 ] =
25
V ar(X) + E[X]2 = 12
+ 2.52 = 8.3333. Similarly, E[Y 2 ] = 8.3333. Since X and Y are independent,
2
2
2
E(X Y ) = E[X ] E[Y 2 ] = 8.33332 = 69.4444. Therefore,
V ar(XY ) = 69.4444 6.252 = 30.3819

Copyright Natalia A. Humphreys, 2015

Page 3 of 5

ACTS 4304. SP 2015. SOLUTION TO HOMEWORK 1.

Problem 7
You are given the following information about the random variables X and Y :
(i) Var(X)=16
(ii) Var(Y)=25
(iii) Var(3X-7Y)=550
Determine the correlation coefficient of X and Y .
Solution.
2
V ar(3X 7Y ) = 9X
42XY X Y + 49Y2 XY =

9 16 + 49 25 550
= 0.975
42 4 5

Problem 8
For a health insurance policy, trended claims will be equal to the product of the claims random
variable X and a trend random variable Y .
You are given:
(i) E[X]=12
(ii) Var(X)=169
(iii) E[Y]=1.3
(iv) Var(Y)=0.02
(v) X and Y are independent
Determine the variance of trended claims.
Solution. We need to find the variance of Z = XY : V ar(XY ) = E[X 2 Y 2 ] E(XY )2 . Since X and
Y are independent, E(XY ) = E[X] E[Y ] and E(X 2 Y 2 ) = E[X 2 ] E[Y 2 ].
E(XY ) = 12 1.3 = 15.6
E(X 2 Y 2 ) = V ar(X) + E[X]2


V ar(Y ) + E[Y ]2 = (169 + 144)(0.02 + 1.69) = 313 1.71 = 535.23

V ar(XY ) = 535.23 15.62 = 291.87

Problem 9
For a one-year term life insurance policy of 2000:
(i) The probability of death during the year is 0.03
(ii) If the insured survives to the end of the year, the company pays a dividend of 5.
Ignore the interest. Calculate the variance in the amount of cost the company has on this policy.
Solution. The cost to the insurance company is:

2000 q = 0.03
C=
5
1 q = 0.97
This is a Bernoulli variable, scaled and translated.
V ar(C) = (2000 5)2 0.03 0.97 = 115,818.73

Copyright Natalia A. Humphreys, 2015

Page 4 of 5

ACTS 4304. SP 2015. SOLUTION TO HOMEWORK 1.

Problem 10
A life insurance company has determined that the present value of profit on selling one contract is
uniformly distributed on [-45, 72]. Using normal approximation, calculate the probability of making
a profit on a portfolio of 55 policies.
Solution. Let Xi be the
P random variable representing the present value of profit on selling the i-th
contract. And let X = 55
i=1 Xi . We need to find P r(X > 0).
72 45
E[X] =
= 13.5, E[X] = 55 13.5 = 742.5
2
(72 + 45)2
= 1140.75, V ar(X) = 55 1140.75 = 62,741.25, X = 250.482
V ar(X) =
12





X E[X]
E[X]
E[X]
742.5
P r(X > 0) = P r
>
=
=
2.96 = 0.9985 
p
p
p
250.482

Copyright Natalia A. Humphreys, 2015

Page 5 of 5

You might also like