Statistics I - SOLUTIONS Exam Semester 1

Total time 2 hours

December 6, 2024

Question 1. Probability
(a) A bag contains 10 red balls, 8 blue balls, and 6 green balls. We successively draw 2 balls at random
without replacement. What is the probability that the first ball drawn is red and the second ball is
blue?
Answer: P (1st ball red) = 10/24, P (2nd ball blue|1st ball red) = 8/23. P (1st ball red and then 2nd ball b
(10/24)(8/23). We could also have used permutations: P110 P18 /P224 = 10 × 8/(24 × 23)

(b) A shelf has 5 science books, 4 history books, and 3 art books. Three books are selected at random
one after another without replacement. What is the probability that the first book is a science book,
the second is a history book, and the third is an art book?
Answer: P (1st book science) = 5/12, P (2nd book history|1st book science) = 4/11,
P (3rd book art|previous 2 books are science and history) = 3/10. So,
5 4 3
P (1st book is science, then the 2nd is history and the 3rd is art) = 12 11 10
.

(c) In a software application, two types of bugs may occur. Bug A occurs 11% of the time, and Bug B
occurs 8% of the time. Additionally, 14% of the time, either Bug A or Bug B occurs. Compute the
probability that a randomly encountered software issue involves both Bug A and Bug B.
Answer: P (A) = 0.11, P (B) = 0.08, P (A ∪ B) = 0.14,

P (A ∩ B) = P (A) + P (B) − P (A ∪ B) = 0.11 + 0.08 − 0.14 = 0.05

Question 2. Multivariate random variables

Let X and Y represent the daily distances (in kilometers) traveled by two delivery drivers, Driver A and
Driver B, working for a logistics company. Assume there are only three possible distances they can travel
in a day: 0 km, 10 km, and 20 km. The joint probability distribution, fX,Y (x, y), is:

X 0 10 20
Y
0 0.05 0.15 0.10
10 0.10 0.10 0.30
20 0.05 0.05 0.10

1
 (a) Calculate the marginal probability functions of X and Y , fX (x) and fY (y) respectively.
Answer:
X 0 10 20 P (Y = y)
Y
0 0.05 0.15 0.10 0.30
10 0.10 0.10 0.30 0.50
20 0.05 0.05 0.10 0.20
P (X = x) 0.20 0.30 0.50 1

(b) Calculate the joint cumulative probabilities FX,Y (10, 10) and FX,Y (0, 10).
Answer:

FX,Y (10, 10) = P (X = 0, Y = 0) + P (X = 0, Y = 10) + P (X = 10, Y = 0) + P (X = 10, Y = 10)

= 0.05 + 0.1 + 0.15 + 0.1 = 0.4
FX,Y (0, 10) = P (X = 0, Y = 0) + P (X = 0, Y = 10)
= 0.05 + 0.1 = 0.15

(c) Are X and Y independent?

Answer: P (X = 0, Y = 0) = 0.05 but P (X = 0)P (Y = 0) = 0.06, so X and Y are not independent.

(d) Compute P (Y = y|X = 10).

Answer:
P (Y = 0, X = 10) 0.15 1
P (Y = 0|X = 10) = = =
P (X = 10) 0.3 2
P (Y = 10, X = 10) 0.1 1
P (Y = 10|X = 10) = = =
P (X = 10) 0.3 3
P (Y = 20, X = 10) 0.05 1
P (Y = 20|X = 10) = = = .
P (X = 10) 0.3 6

(e) Derive (find) the conditional cumulative distribution function of Y given X = 10, FY |X=10 (y).
Answer: 

 0, y<0
1,

0 ≤ y < 10
FY |X=10 (y) = 12 1 .


 2
+ 3 = 56 , 10 ≤ y < 20
1 1 1
2
+ 3 + 6 = 1, y ≥ 20

Question 3. Moment generating function

Suppose X represents the number of hours spent on recreational activities per day by a student from a
particular university. The probabilities of spending specific amounts of time are as follows:


 0.2, x = 0, 3

0.5, x = 1
fX (x) =


 0.1, x = 2

0, otherwise

2
 (a) Derive (find) the moment generating function of the random variable X, MX (t).
Answer:
3
X
MX (t) = etx fX (x) = 0.2(1 + e3t ) + 0.5et + 0.1e2t .
x=0

(b) Using the moment generating function from (a), derive (find) E(X) and E(X 2 ).
Answer:

MX′ (t) = 0.6e3t + 0.5et + 0.2e2t ,

E(X) = MX′ (0) = 0.5e0 + 0.2e0 + 0.6e0 = 0.5 + 0.2 + 0.6 = 1.3.

′′
MX (t) = 1.8e3t + 0.5et + 0.4e2t ,

′′
E(X 2 ) = MX (0) = 0.5e0 + 0.4e0 + 1.8e0 = 0.5 + 0.4 + 1.8 = 2.7.

(c) Let Y be another random variable independent of X having the same moment generating function
as X, MX (t) = MY (t). Define Z = X + Y . Derive (find) the moment generating function of the new
random variable Z, FZ (z).
Answer: MZ (t) = [MX (t)]2 = 0.04e0t + 0.2e1t + 0.29e2t + 0.18e3t + 0.21e4t + 0.04e5t + 0.04e6t

(d) Find the probability function of the random variable Z defined in question (c), fZ (z).
Answer: The probability function is given by the coefficients of the exponential ezt from (c): P (Z =
0) = 0.04, P (Z = 1) = 0.2, P (Z = 2) = 0.29, P (Z = 3) = 0.18, P (Z = 4) = 0.21, P (Z = 5) = 0.04,
P (Z = 6) = 0.04.

Question 4. Expected value

Let X and Y represent two continuous random variables. X represents the amount of rainfall (in cm) in a
day, and Y represents the cloud coverage percentage on the same day (in arbitrary units). The conditional
probability density function of X is:
(
1
, y <x<y+3
fX|Y =y (x) = 3
0, otherwise.

The marginal probability function of Y is:

(
2(1 − y), 0 < y < 1
fY (y) =
0, otherwise.

(a) Compute E(2Y + 2).

R1
Answer: 0 y 2(1 − y)dy = 31 . So E(2Y + 2) = 2/3 + 2.

3
(b) Compute E(X).
Answer: From the law of iterated expectations (alsoR y+3 known as the tower property) we have: E(X) =
1
E(E(X|Y )). First we calculate E(X|Y = y) = y x 3 dx = y + 3/2. So E(X|Y ) = Y + 3/2 which
is a random variable. The expectation of this random variable is E(Y + 3/2) = E(Y ) + 3/2 =
1/3 + 3/2 = 11/6 = E(X), where E(Y ) was calculated in (a). Another possibility is to calculate the
joint density fX,Y (x, y) and use it to calculate E(X).

(c) Derive (find) the marginal probability function of the new random variable Z = Y 2 , fZ (z).
Answer: Since Y ∈ (0, 1), it follows that Z ∈ (0, 1). We need the cumulative distribution function
of Z:

FZ (z) = P (Z ≤ z) = P (Y 2 ≤ z)
√ √
= P (− z ≤ Y ≤ z)
√ √ √
= FY ( z) − FY (− z) + P (Y = − z)

for z ≥ 0.
So we need FY (y). Given the the density of Y , fY (y) = 2(1 − y) for y ∈ (0, 1), the CDF of Y is:
Z y y
2(1 − t) dt = 2t − t2 0 = 2y − y 2 .

FY (y) =
0
√ √
from where we can see that P (Y = − z) = 0 (because Y is continuous), and FY (− z) = 0. So,
√ √
FZ (z) = P (Y ≤ z) = FY ( z).
√
Substituting y = z into FY (y):

√ √ √ √
FZ (z) = FY ( z) = 2 z − ( z)2 = 2 z − z.

Thus, the CDF of Z is:

 √
2 z − z, 0 < z < 1,

FZ (z) = 0, z ≤ 0,

1, z ≥ 1.


We are asked to find fZ (z). To find the density fZ (z), differentiate FZ (z) with respect to z:

d √

fZ (z) = 2 z−z .
dz
The derivative is:

d √ d 2 1
fZ (z) = (2 z) − (z) = √ − 1 = √ − 1.
dz dz 2 z z
Therefore, the PDF of Z = Y 2 is:
(
√1 − 1, 0 < z < 1,
z
fZ (z) =
0, otherwise.