STA256H5F Friday, May 31st, 2024 Duration - 90 minutes

1. Suppose A and B are two events, where P (A) = 0.7, and P (B) = 0.5. Briefly justify
each part.

(a) (1 point) P (A \ B)  0.5

(b) (1 point) P (A \ B) 0.2

Solution:

(a) By a theorem, if A ⇢ B, then P (A)  P (B). Since A \ B ⇢ B, we have

P (A \ B)  P (B) = 0.5

(b) By a theorem, if C is an event, P (C)  1. Also, by the additive law of probbaility,

P (A [ B) = P (A) + P (B) P (A \ B)

Thus, P (A [ B) = P (A) + P (B) P (A \ B)  1, which yields

P (A \ B) P (A) + P (B) 1 = 0.2

Page 2 of 8
STA256H5F Friday, May 31st, 2024 Duration - 90 minutes

2. Suppose that of the students who take STA256, 60% study major Statistics, 30%
study Computer Science, and the remainder study major Mathematics. Of those
studying major Statistics, 40% are international students, while 30% of those studying
Computer Science and 20% of those studying major Mathematics are international
students. Suppose that we randomly select a student in STA256.

(a) (2 points) Find the probability that the student is an international student.
(b) (2 points) Find the probability that the student studies major Statistics, given
that the student is an international student.

Solution:
Let S be the event that a random student is studying major Statistics, C be the event
that the student is studying Computer Science, and M be the event that the student
is studying major Mathematics. Also, let I be the event that a random student is
an international student. P (S) = 0.6, P (C) = 0.3, and P (M ) = 0.1. Further,
P (I|S) = 0.4, P (I|C) = 0.3, and P (I|M ) = 0.2.

(a) By the law of total probability, the probability that a random student is an
international student becomes

P (I) = P (I|S) ⇥ P (S) + P (I|C) ⇥ P (C) + P (I|M ) ⇥ P (M )

= 0.4 ⇥ 0.6 + 0.3 ⇥ 0.3 + 0.2 ⇥ 0.1
= 0.35

(b) Following the Bayes theorem, and part (a), if the student is an international
student, the probaility that he/she studies major Statistics becomes

P (I|S) ⇥ P (S) 0.4 ⇥ 0.6 24

P (S|I) = = = ⇡ 0.6857
P (I) 0.35 35

Page 3 of 8
STA256H5F Friday, May 31st, 2024 Duration - 90 minutes

3. A university employee is sampling without replacement n = 4 students to create a

student committee. The sample is to be selected from a pool of eight students, of
which five are male and three are female students. Let X denote the number of female
students among the four selected students.

(a) (2 points) Find the probability mass function (pmf) of X.

(b) (2 points) Find the probability that there is at least one female student in the
committee.

Solution:

(a) The probability mass function (pmf) of X is given by

3 5
x 4 x
pX (x) = 8 , x = 0, 1, 2, 3
4

Alternatively, the pmf is given by

x 0 1 2 3
3 5 3 5 3 5 3 5
( )( )
0 4 5 ( )( )
1 3 30 ( )( )
2 2 30 ( )( )
3 1 5
pX (x) = = = =
(84) 70 (84) 70 (84) 70 (84) 70

(b) From part (a), the probability that there is at least one female student in the
committee becomes
5 65
P (X 1) = 1 P (X = 0) = 1 = ⇡ 0.9286
70 70

Page 4 of 8
STA256H5F Friday, May 31st, 2024 Duration - 90 minutes

4. Let X be a random variable with the probability density function

( 2
2xe x if x > 0,
fX (x) =
0 otherwise.

Consider the new random variable Y = X 2 .

(a) (3 points) Find the probability density function of Y .

(b) (2 points) Find E(Y ).

Solution:

(a) First note that sine x > 0, the support of Y = X 2 is (0, 1). The cdf of Y is
given by
p p
FY (y) = P (Y  y) = P (X 2  y) = P ( y  X  y)
p p p p
= P (X  y) + P (X < y) = P (X  y) = FX ( y)

Since X is a continuous random variable, so is Y . Hence, the pdf of Y is obtained

by taking derivative of the cdf of Y .
d p 1 p 1 p p
( y)2
fY (y) = FY0 (y) = FX ( y) = p fX ( y) = p 2 ye = e y , y > 0.
dy 2 y 2 y

i.e., fY (y) = e y , for 0 < y < 1, and 0 elsewhere.

Second Method: Y = X 2 is a one-to-one function on (0, 1), y = g(x) = x2 , and

p dx 1
x = g 1 (y) = y, and = p
dy 2 y
Using the univariate transformation formula, we have
dx p p
( y)2 1
fY (y) = fX (g 1 (y))| | = 2 ye p = e y, y > 0.
dy 2 y

(b) From part (a) (the first method) and by U-substitution (u = x2 ) and integration
by part, we have
Z 1 Z 1 Z 1
2 2 3 x2
E(Y ) = E(X ) = x fX (x)dy = 2x e = ue u du = 1.
0 0 0

Second Method: From part (a) (the second method) and by integration by part
Z 1 Z 1 Z 1
y 1
E(Y ) = yfY (y)dy = y
ye = ye |0 + e y = 0 e y |10 = 1.
0 0 0

Page 5 of 8
STA256H5F Friday, May 31st, 2024 Duration - 90 minutes

5. Let X be a random variable with the probability density function

(
2e 2x if x 0,
fX (x) =
0 otherwise.

(a) (2 points) Find the moment generating function of X.

(b) (3 points) Find P (X 2) and use Markov’s inequality to find an upper bound
for this probability.

Solution:

(a) Since X is a continuous random variable, the moment generating function is

obtained by
Z 1 Z 1 Z 1
tX tx tx 2x
MX (t) = E(e ) = e fX (x)dx = e 2e dx = 2e x(2 t) dx
0 0 0
2 x(2 t) 1 2
= e |0 = , t < 2.
2 t 2 t

(b) We first find the probability as

Z 1 Z 1
2x 2x 1 4
P (X 2) = fX (x)dx = 2e dx = e |2 =e ⇡ 0.0183.
2 2

Recall that for a non-negative random variable X, and positive constant c, the
Markov inequality is P (X c)  E(X)c
. From part (a),

2 1
E(X) = MX0 (t)|t=0 = | =
2 t=0
(2 t) 2

Hence, an upper bound for the probability is

E(X) 1/2 1
P (X 2)  = = .
2 2 4

Note that we can find E(X) directly by integration by part as

Z 1 Z 1 Z 1
2x 2x 1 1 2x 1 1
E(X) = xfX (x)dx = 2xe dx = xe |0 + e 2x dx = 0 e |0 = .
0 0 0 2 2

Page 6 of 8