Midterm-Sample-Paper-2 Solution
Midterm-Sample-Paper-2 Solution
Suggested Solutions
I NSTRUCTIONS TO S TUDENTS
1. Please write your student number only. Do not write your name.
3. The total marks is 25; marks are equal distributed for all questions.
6. This is an OPEN BOOK assessment. Only HARD COPIES of materials are allowed.
ST2334
A ∪ (B ∩C) =?
S OLUTION
(a)
2. F ILL IN THE BLANK
How many ways are there to choose an arbitrary number of students (including the pos-
sibility of choosing 0 student) from 6 students?
(Provide your answer in numerical form.)
S OLUTION
For each student, there are 2 possibilities: “chosen” or “not chosen”. So the total number
of possibilities is 2 × 2 × 2 × 2 × 2 × 2 = 26 = 64.
3. F ILL IN THE BLANK
Suppose
3 1 3
P(B′ ∩ A) = P(B′ |A)P(A) = × = ,
4 2 8
1 3 1
P(B ∩ A) = P(A) − P(B′ ∩ A) = − = = 0.125.
2 8 8
2
ST2334
Let A and B be two events. Which of the following statements is/are true?
S OLUTION
Answer: (b), (c), (d).
Consider the following statements about Peter whom you have not met before.
You are to assign probabilities to these statements. Which answer below is consistent
with the laws of probability?
S OLUTION
Answer: (c).
7. T RUE /FALSE
Let A and B be mutually exclusive events. If P(A) = 0.1, P(B) = 0.01, then A and B are
not independent.
• TRUE
• FALSE
S OLUTION
TRUE; If otherwise, P(A ∩ B) = P(A)P(B) > 0, which contradicts that A and B are mu-
tually exclusive.
8. T RUE /FALSE
Cumulative distribution function can not take on values greater than 1 or smaller than 0.
• TRUE
3
ST2334
• FALSE
S OLUTION
TRUE
9. F ILL IN THE BLANK
Suppose that random variable X has the cumulative distribution function given by
0, x < 0
2
x
F(x) = , 0≤x≤3
1,9 x > 3
Compute E(X).
(Provide your answer in decimal form and round it to two decimal places if necessary.)
S OLUTION
X is a discrete RV, whose p.m.f. is given by f (x) = 0.2, 0.4, 0.1, 0.3, for x = 0, 2, 3, 5.
x 0 2 5 6
f (x) 0.3 0.5 0.1 0.1
Compute E(X).
(Provide your answer in decimal form and round it to two decimal places if necessary.)
S OLUTION
E(X) = 0(0.3) + 2(0.5) + 5(0.1) + 6(0.1) = 2.1.
4
ST2334
(a) If P(X = 1) = 0.1 and E(X) exists, then we must have E(X 2 ) > (E(X))2 .
(b) If V (X) > 0, then for any x, P(X = x) < 1.
(c) By the definition of the random variable, the range of X is a subset of R; therefore, it
is impossible that P(X = x) = 0 for any x ∈ R.
(d) There are cases under which E(X) does not exist.
S OLUTION
Answer: (c)
• (a) is correct because V (X) = E(X 2 ) − [E(X)]2 and P(X = 1) = 0.1 implies V (X) >
0 (since otherwise P(X = E(X)) = 1).
• (b) is correct with similar reason to (a).
• For any continuous RV, we must have P(X = x) = 0 for any x ∈ R.
• For example, X is a random variable with p.d.f.
1
(
, for |x| ≥ 1,
f (x) = 2x2
0, elsewhere
Then
Z 1
1 1
Z ∞
E(X) = x · 2 dx + x· dx = −∞ + ∞,
−∞ 2x 1 2x2
which implies E(X) does not exist.
y
x
0 1 2
0 0.10 0.04 0.02
1 0.08 0.20 0.06
2 0.06 0.14 0.30
5
ST2334
Focusing on the column of y = 1, the sum of these numbers leads to P(Y = 1) = 0.04 +
0.20 + 0.14 = 0.38. So, we obtain the conditional distribution of X|Y = 1:
Therefore, we obtain
Let f (x, y) be the joint probability function of a discrete random vector (X,Y ). If fX (1) =
0, then f (1, y) = 0 for any y being a real number.
• TRUE
• FALSE
S OLUTION
TRUE
fX (1) = 0 implies ∑ f (1, y) = 0, but f (1, y) ≥ 0; therefore f (1, y) = 0 for all y ∈ RY ,
y∈RY
and thus f (1, y) = 0 for all real numbers y.
6
ST2334
As a consequence
0.375
P(Y ≥ 1|X ≥ 1) = = 0.6.
0.625
E ND OF PAPER