2.3 Common Univariate and Multivariate Random Variable
Question 1
Two extremely risky bonds have unconditional probabilities of default (Bernoulli PDs) of 10 % 10\% 10% and 20 % 20\% 20%. Their linear correlation is 0.35 0.35 0.35. What is the probability that both bonds default?
A.
2.0
%
2.0\%
2.0%
B.
4.6
%
4.6\%
4.6%
C.
6.2
%
6.2\%
6.2%
D.
9.7
%
9.7\%
9.7%
Answer: C
Let respective default be represented by
X
X
X and
Y
Y
Y
E [ X Y ] = E [ X ] E [ Y ] + C o v ( X , Y ) = E [ X ] E [ Y ] + ρ X , Y σ X σ Y E[XY] = E[X]E[Y] + Cov(X, Y)=E[X]E[Y]+\rho_{X,Y}\sigma_X\sigma_Y E[XY]=E[X]E[Y]+Cov(X,Y)=E[X]E[Y]+ρX,YσXσY
As X X X and Y Y Y follow Bernoulli distribution, σ = p × ( 1 − p ) \sigma=\sqrt{p\times(1-p)} σ=p×(1−p)
σ X = 10 % × 90 % = 0.3 \sigma_X=\sqrt{10\%\times90\%}=0.3 σX=10%×90%=0.3, σ Y = 20 % × 80 % = 0.4 \sigma_Y=\sqrt{20\%\times80\%} = 0.4 σY=20%×80%=0.4
E [ X Y ] = 10 % × 20 % + 0.35 × 0.3 × 0.4 = 6.2 % E[XY] = 10\%\times20\% + 0.35\times0.3\times0.4= 6.2\% E[XY]=10%×20%+0.35×0.3×0.4=6.2%
Please note: if the bonds were independent, then C o v ( X , Y ) = 0 Cov(X, Y)= 0 Cov(X,Y)=0, such that E [ X Y ] = 2 % E[XY] =2\% E[XY]=2%
Question 2
A company has a constant 30 % 30\% 30% per year probability of default. What is the probability the company will be in default within three years?
A.
34
%
34\%
34%
B.
44
%
44\%
44%
C.
66
%
66\%
66%
D.
90
%
90\%
90%
Answer: C
P
=
C
3
1
×
0.3
×
0.
7
2
+
C
3
2
×
0.
3
2
×
0.7
+
C
3
3
×
0.
3
3
=
65.7
%
P=C_3^1\times0.3\times0.7^2+C_3^2\times0.3^2\times0.7+C_3^3\times0.3^3=65.7\%
P=C31×0.3×0.72+C32×0.32×0.7+C33×0.33=65.7%
P = 1 − 0. 7 3 = 65.7 % P=1-0.7^3=65.7\% P=1−0.73=65.7%
Question 3
Consider the following five random variables:
- A standard normal random variable; no parameters needed.
- A student’s t distribution with 10 10 10 degrees of freedom; d f = 10 {df} = 10 df=10
- A Bernoulli variable that characterizes the probability of default (PD), where P D = 4 PD = 4% PD=4; p = 0.04 p = 0.04 p=0.04
- A Poisson distribution that characterizes the frequency of operational losses during the day, where λ = 5 \lambda = 5 λ=5
- A binomial variable that characterizes the number of defaults in a basket credit default swap (CDS) of 50 bonds, each with P D = 2 % PD = 2\% PD=2%; n = 50 n = 50 n=50, p = 2 % p = 2\% p=2%
Which of the above has, respectively, the lowest value and highest value as its variance among the set?
A. Standard normal (lowest) and Bernoulli (highest)
B. Binomial (lowest) and Student’s t (highest)
C. Bernoulli (lowest) and Poisson (highest)
D. Poisson (lowest) and Binomial (highest)
Answer: C
Standard normal distribution:
E
(
X
)
=
0
E(X)= 0
E(X)=0,
V
(
X
)
=
1
V(X) = 1
V(X)=1
Student’s t distribution: E ( X ) = 0 E(X)= 0 E(X)=0, V ( X ) = d f / ( d f − 2 ) = 10 / 8 = 1.25 V(X) = df/(df-2)=10/8=1.25 V(X)=df/(df−2)=10/8=1.25
Bernoulli distribution: E ( X ) = p = 0.04 E(X)=p=0.04 E(X)=p=0.04, V ( X ) = p ( 1 − p ) = 4 % × 96 % = 0.0384 V(X)= p(1 − p) = 4\% × 96\%=0.0384 V(X)=p(1−p)=4%×96%=0.0384
Poisson distribution: E ( X ) = λ = 5 E(X)=\lambda=5 E(X)=λ=5, V ( X ) = λ = 5 V(X)=\lambda = 5 V(X)=λ=5
Binomial distribution: E ( X ) = n p = 50 × 0.02 = 1 E(X)=np=50\times0.02=1 E(X)=np=50×0.02=1, V ( X ) = n p ( 1 − p ) = 50 × 0.02 × 0.98 = 0.98 V(X)=np(1 − p)=50\times0.02\times0.98=0.98 V(X)=np(1−p)=50×0.02×0.98=0.98
Question 4
Which of the following statements are TRUE?
I The sum of two random normal variables is also a random normal variable.
II The product of two random normal variables is also a random normal variable.
III The sum of two random lognormal variables is also a random lognormal variable.
IV The product of two random lognormal variables is also a random lognormal variable.
A. I and II only
B. II and III only
C. III and IV only
D. I and IV only
Answer: D
Normal variables are stable under addition, so that (I) is true.
For lognormal variables
X
1
X_1
X1 and
X
2
X_2
X2, we know that their logs,
l
n
(
X
1
)
ln(X_1)
ln(X1) and
l
n
(
X
2
)
ln(X_2)
ln(X2) are normally distributed. Hence, the sum of their logs, or
l
n
(
(
X
1
)
+
l
n
(
X
2
)
=
l
n
(
(
X
1
×
X
2
)
ln((X_1) + ln(X_2) = ln((X_1 × X_2)
ln((X1)+ln(X2)=ln((X1×X2) must also be normally distributed. The product is itself lognormal, so that (IV) is true.
Question 5
Your firm uses a proprietary forecasting model that requires parameter estimates of random variables that are believed to follow the Poisson distribution. You are attempting to assess the probability of the number of defects in an assembly production process for a given company. Assume that there is a 0.005 0.005 0.005 probability of a defect for every production run. What is the probability of 7 7 7 defects in 1000 1000 1000 production runs?
A.
3.0
%
3.0\%
3.0%
B.
4.4
%
4.4\%
4.4%
C.
8.6
%
8.6\%
8.6%
D.
10.4
%
10.4\%
10.4%
Answer: D
The first step is to estimate the number of expected defects in
1000
1000
1000 runs as follows:
1000
×
0.005
=
5
1000\times0.005=5
1000×0.005=5 . Next the mathematical formula for the Poisson distribution for estimating
7
7
7 defects given that
5
5
5 are expected is:
P
(
x
=
7
)
=
5
7
7
!
×
e
−
5
=
0.1044
P(x=7)=\cfrac{5^7}{7!}\times e^{-5}=0.1044
P(x=7)=7!57×e−5=0.1044
Question 6
The joint probability distribution of random variables
X
X
X and
Y
Y
Y is given by
f
(
x
,
y
)
=
k
×
x
×
y
f(x, y) = k\times x\times y
f(x,y)=k×x×y for
x
=
1
,
2
,
3
x = 1,2,3
x=1,2,3,
y
=
1
,
2
,
3
y = 1,2,3
y=1,2,3, and
k
k
k is a positive constant. What is the probability
that
X
+
Y
X + Y
X+Y will exceed
5
5
5?
A.
1
/
9
1/9
1/9
B.
1
/
4
1/4
1/4
C.
1
/
36
1/36
1/36
D. Cannot be determined
Answer: B
The function
x
×
y
x\times y
x×y is described in the following table. The sum of the entries is
36
36
36. The scaling factor
k
k
k must be such that the total probability is one.
Therefore, we have k = 1 / 36 k = 1/36 k=1/36. The table shows one instance where x + y > 5 x + y>5 x+y>5, which is x = 3 , y = 3 x=3,y=3 x=3,y=3. The probability is p = 9 / 36 = 1 / 4 p = 9/36 = 1/4 p=9/36=1/4.
$x=1 | x = 2 x=2 x=2 | x = 3 x=3 x=3 |
---|---|---|
y = 1 y=1 y=1 | 1 1 1 | 2 2 2 |
y = 2 y=2 y=2 | 2 2 2 | 4 4 4 |
y = 3 y=3 y=3 | 3 3 3 | 8 8 8 |
Question 7
PE2018Q10 / PE2019Q10 / PE2020Q10 / PE2021Q10 / PE2022Q10
A fixed income portfolio manager currently holds a portfolio of bonds of various companies. Assuming all these bonds have the same annualized probability of default and that the defaults are independent, the number of defaults in this portfolio over the next year follows which type of distribution?
A. Bernoulli
B. Normal
C. Binomial
D. Exponential
Answer: C
Learning Objective: Distinguish the key properties and identify the common occurrences of the following distributions: uniform distribution, Bernoulli distribution, binomial distribution, Poisson distribution, normal distribution, lognormal distribution, Chi-squared distribution, Student’s t and F-distributions.
The result would follow a Binomial distribution as there is a fixed number of random variables, each with the same annualized probability of default.
It is not a Bernoulli distribution, as a Bernoulli distribution would describe the likelihood of default of one of the individual bonds rather than of the entire portfolio (i.e. a Binomial distribution essentially describes a group of Bernoulli distributed variables).
A normal distribution is used to model continuous variables, while in this case the number of defaults within the portfolio is discrete.
Question 8
A multiple choice exam has ten questions, with five choices per question. If you need at least three correct answers to pass the exam, what is the probability that you will pass simply by guessing?
A.
0.8
%
0.8\%
0.8%
B.
20.1
%
20.1\%
20.1%
C.
67.8
%
67.8\%
67.8%
D.
32.2
%
32.2\%
32.2%
Answer: D
The probability of an event is between
0
0
0 and
1
1
1. If these are mutually exclusive events, the probability of individual occurrences are summed. This probability follows a binomial distribution with a p-parameter of
0.2
0.2
0.2. The probability of getting at least three questions correct is
1
−
[
p
(
0
)
+
p
(
1
)
+
p
(
2
)
]
=
32.2
%
1- [p(0) + p (1) + p (2)] = 32.2\%
1−[p(0)+p(1)+p(2)]=32.2%.
Question 9
A call center receives an average of two phone calls per hour. The probability that they will receive 20 20 20 calls in an 8 8 8-hour day is closest to:
A.
5.59
%
5.59\%
5.59%
B.
16.56
%
16.56\%
16.56%
C.
3.66
%
3.66\%
3.66%
D.
6.40
%
6.40\%
6.40%
Answer: A
To solve this question, we first need to realize that the expected number of phone calls in an
8
8
8-hour day is
λ
=
2
×
8
=
16
\lambda = 2\times8 = 16
λ=2×8=16.
Using the Poisson distribution, we solve for the probability that x x x will be 20 20 20. P ( X = x ) = λ x x ! e − λ , P ( X = 20 ) = 0.0559 = 5.59 % P(X= x)=\cfrac{\lambda^x}{x!}e^{-\lambda}, P(X = 20) = 0.0559 = 5.59\% P(X=x)=x!λxe−λ,P(X=20)=0.0559=5.59%
Question 10
Suppose that a quiz consists of 20 20 20 true-false questions. A student has not studied for the exam and just randomly guesses the answers. How would you find the probability that the student will get 8 8 8 or fewer answers correct?
A. Find the probability that
X
=
8
X = 8
X=8 in a binomial distribution with
n
=
20
n = 20
n=20 and
p
=
0.5
p = 0.5
p=0.5.
B. Find the area between
0
0
0 and
8
8
8 in a uniform distribution that goes from
0
0
0 to
20
20
20.
C. Find the probability that
X
=
8
X = 8
X=8 for a normal distribution with mean of
10
10
10 and standard deviation of
5
5
5
D. Find the cumulative probability for
8
8
8 in a binomial distribution with
n
=
20
n = 20
n=20 and
p
=
0.5
p = 0.5
p=0.5.
Answer: D
A binomial distribution is a probability distribution, and it refers to the various probabilities associated with the number of correct answers out of the total sample.
The correct approach is to find the cumulative probability for 8 8 8 in a binomial distribution with n = 20 n = 20 n=20 and p = 0.5 p = 0.5 p=0.5.
Question 11
PE2018Q46 / PE2019Q46 / PE2020Q46 / PE2021Q46
A portfolio manager holds three bonds in one of his portfolios and each bond has a
1
1
1-year default probability of
15
%
15\%
15%. The event of default for each of the bonds is independent. What is the probability of exactly two bonds defaulting over the next year?
A. 1.9%
B. 5.7%
C. 10.8%
D. 32.5%
Answer: B
Learning Objective: Distinguish the key properties among the following distributions: uniform distribution, Bernoulli distribution, Binomial distribution, Poisson distribution, normal distribution, lognormal distribution, Chi-squared distribution, Student’s t, and F-distributions, and identify common occurrences of each distribution.
Since the bond defaults are independent and identically distributed Bernoulli random variables, the Binomial distribution can be used to calculate the probability of exactly two bonds defaulting.
The correet formula to use is: C n k × p k × ( 1 − p ) n − k C_n^k\times p^k\times(1-p)^{n-k} Cnk×pk×(1−p)n−k
Where n n n is the number of bonds in the portfolio, p p p is the probability of default of each individual bond, and k k k is the number of defaults for which you would like to find the probability. In this case n = 3 n = 3 n=3, p = 0.15 p = 0.15 p=0.15, and k = 2 k = 2 k=2.
Entering the variables into the equation, this simplifies to 3 × 0.1 5 2 × 0.85 = 0.0574 3\times 0.15^2\times 0.85 = 0.0574 3×0.152×0.85=0.0574.
Question 12
PE2018Q47 / PE2019Q47 / PE2020Q47 / PE2021Q47
A portfolio manager holds three bonds in one of his portfolios and each bond has a 1-year default probability of
15
%
15\%
15%. The event of default for each of the bonds is independent. What is the mean and variance of the number of bonds defaulting over the next year?
A. Mean =
0.15
0.15
0.15, variance =
0.32
0.32
0.32
B. Mean =
0.45
0.45
0.45, variance =
0.38
0.38
0.38
C. Mean =
0.45
0.45
0.45, variance =
0.32
0.32
0.32
D. Mean =
0.15
0.15
0.15, variance =
0.38
0.38
0.38
Answer: B
Learning Objective: Distinguish the key properties among the following distributions: uniform distribution, Bernoulli distribution, Binomial distribution, Poisson distribution, normal distribution, lognormal distribution, Chi-squared distribution, Student’s t, and F-distributions, and identify common occurrences of each distribution.
Letting n n n equal the number of bonds in the portfolio and p p p equal the individual default probability, the formulas to use are as follows:
Mean = n × p = 3 × 15 % = 0.45 = n\times p =3\times15\% = 0.45 =n×p=3×15%=0.45
Variance = n p ( 1 − p ) = 3 × 0.15 × 0.85 = 0.3825 = np(1-p) = 3\times0.15\times0.85 = 0.3825 =np(1−p)=3×0.15×0.85=0.3825
Question 13
An operational risk manager uses the Poisson distribution to estimate the frequency of losses in excess of USD 2 2 2 million during the next year. It is observed that the frequency of losses greater than USD 2 2 2 million is three per year on average over the last 10 10 10 years. Assuming that this observation is indicative of future occurrences and that the probability of one event occurring is independent of all other events, what is the probability of five losses in excess of USD 2 2 2 million occurring during the next two years?
A.
10.08
%
10.08\%
10.08%
B.
14.04
%
14.04\%
14.04%
C.
14.62
%
14.62\%
14.62%
D.
16.06
%
16.06\%
16.06%
Answer: D
To solve this question, we first need to realize that the expected number of losses in excess of USD
2
2
2 million occurring during the next two years is
λ
=
2
×
3
=
6
\lambda = 2\times3 = 6
λ=2×3=6.
Using the Poisson distribution, we solve for the probability that x x x will be 5 5 5. P ( X = x ) = λ x x ! e − λ , P ( X = 5 ) = 16.06 % P(X= x)=\cfrac{\lambda^x}{x!}e^{-\lambda}, P(X = 5) = 16.06\% P(X=x)=x!λxe−λ,P(X=5)=16.06%
Question 14
PE2018Q65 / PE2019Q65 / PE2020Q65 / PE2021Q65 / PE2022Q65
An analyst on the fixed-income trading desk observed that the number of defaults per year in the bond portfolio follows a Poisson process. The average number of defaults is four per year. Assuming defaults are independent, what is the probability that there is at most one default next year?
A.
6.58
%
6.58\%
6.58%
B.
7.33
%
7.33\%
7.33%
C.
9.16
%
9.16\%
9.16%
D.
25.00
%
25.00\%
25.00%
Answer: C
Learning Objective: Distinguish the key properties of the following distributions: uniform distribution, Bernoulli distribution, Binomial distribution, Poisson distribution, normal distribution, lognormal distribution, Chi-squared distribution, Student’s t, and F-distributions, and identify common occurrences of each distribution.
λ
=
4
\lambda=4
λ=4
P
=
P
(
one default
)
+
P
(
no default
)
=
4
1
e
−
4
1
!
+
4
0
e
−
4
0
!
=
9.16
%
P= P(\text{one default}) + P(\text{no default})=\cfrac{4^1e^{-4}}{1!}+\cfrac{4^0e^{-4}}{0!}=9.16\%
P=P(one default)+P(no default)=1!41e−4+0!40e−4=9.16%
Question 15
An investor holds a portfolio of stocks A and B. The current value, estimated annual expected return and estimated annual standard deviation of returns are summarized in the table below:
Stock A | Stock B | |
---|---|---|
Current Value | 40000 40000 40000 | 60000 60000 60000 |
Expected Return | 8 % 8\% 8% | 9 % 9\% 9% |
Standard Deviation | 16 % 16\% 16% | 20 % 20\% 20% |
If the correlation coefficient of the returns on stocks A and B is 0.3 0.3 0.3, then the expected value of the portfolio at the end of this year, within two standard deviation, will be between:
A. USD
6900
6900
6900 and USD
134400
134400
134400
B. USD
71800
71800
71800 and USD
145400
145400
145400
C. USD
78200
78200
78200 and USD
139000
139000
139000
D. USD
81400
81400
81400 and USD
135800
135800
135800
Answer: C
μ
p
=
0.4
×
0.08
+
0.6
×
0.09
=
0.086
\mu_p=0.4\times0.08+0.6\times0.09=0.086
μp=0.4×0.08+0.6×0.09=0.086
σ p = 0. 4 2 × σ A 2 + 0. 6 2 × σ B 2 + 2 × 0.4 × 0.6 × ρ σ A σ B = 0.152 \sigma_p=\sqrt{0.4^2\times \sigma_A^2+0.6^2\times\sigma_B^2+2\times0.4\times0.6\times\rho \sigma_A\sigma_B}=0.152 σp=0.42×σA2+0.62×σB2+2×0.4×0.6×ρσAσB=0.152
R p ∈ ( 0.086 − 2 × 0.152 , 0.086 + 2 × 0.152 ) = ( − 0.218 , 0.39 ) R_p\in(0.086-2\times0.152, 0.086+2\times0.152)=(-0.218, 0.39) Rp∈(0.086−2×0.152,0.086+2×0.152)=(−0.218,0.39)
V p = 1000 × ( 1 + R p ) ∈ ( 78200 , 13900 ) V_p=1000\times(1+R_p)\in(78200, 13900) Vp=1000×(1+Rp)∈(78200,13900)
Question 16
PE2018Q66 / PE2019Q66 / PE2020Q66 / PE2021Q66 / PE2022Q66
Assume that a random variable follows a normal distribution with a mean of
40
40
40 and a standard deviation of
14
14
14. What percentage of this distribution is not between
12
12
12 and
61
61
61?
A.
4.56
%
4.56\%
4.56%
B.
6.18
%
6.18\%
6.18%
C.
8.96
%
8.96\%
8.96%
D.
18.15
%
18.15\%
18.15%
Answer: C
Learning Objective: Distinguish the key properties of the following distributions: uniform distribution, Bernoulli distribution, Binomial distribution, Poisson distribution, normal distribution, lognormal distribution, Chi-squared distribution, Student’s t, and F-distributions, and identify common occurrences of each distribution.
P ( 12 ≤ X ≤ 61 ) = P ( 12 − 40 14 ≤ X − 40 14 ≤ 61 − 40 14 ) = P ( − 2 ≤ z ≤ 1.5 ) = 0.9104 P(12\leq X \leq 61)=P(\cfrac{12-40}{14}\leq \cfrac{X-40}{14}\leq \cfrac{61-40}{14})=P(-2\leq z\leq 1.5) = 0.9104 P(12≤X≤61)=P(1412−40≤14X−40≤1461−40)=P(−2≤z≤1.5)=0.9104
1 − 0.9104 = 8.96 % 1-0.9104=8.96\% 1−0.9104=8.96%
Question 17
The recent performance of Prudent Fund, with USD 50 50 50 million in assets, has been weak and the institutional sales group is recommending that it be merged with Aggressive Fund, a USD 200 200 200 million fund. The returns on Prudent Fund are normally distributed with a mean of 3 % 3\% 3% and a standard deviation of 7 % 7\% 7% and the returns on Aggressive Fund are normally distributed with a mean of 7 % 7\% 7% and a standard deviation of 15 % 15\% 15%. Senior management has asked you to estimate the likelihood that returns on the combined portfolio will exceed 26 % 26\% 26%. Assuming the returns on the two funds are independent, your estimate for the probability that the returns on the combined fund will exceed 26 % 26\% 26% is closest to:
A.
1.0
%
1.0\%
1.0%
B.
2.5
%
2.5\%
2.5%
C.
5.0
%
5.0\%
5.0%
D.
10.0
%
10.0\%
10.0%
Answer: C
The combined expected mean return is:
μ
=
0.2
×
3
%
+
0.8
×
7
%
=
6.2
%
\mu=0.2\times3\%+0.8\times7\% = 6.2\%
μ=0.2×3%+0.8×7%=6.2%
The combined volatility is: σ = 0. 2 2 × 0.0 7 2 + 0. 8 2 × 0.1 5 2 = 0.121 = 12.1 % \sigma =\sqrt{0.2^2\times0.07^2 + 0.8^2\times0.15^2} =0.121=12.1\% σ=0.22×0.072+0.82×0.152=0.121=12.1%
P ( X > 26 % ) = P ( X − 6.2 % 12.1 % > 26 % − 6.2 % 12.1 % ) = P ( z > 1.64 ) = 5 % P(X>26\%)=P(\cfrac{X-6.2\%}{12.1\%}>\cfrac{26\%-6.2\%}{12.1\%})=P(z>1.64)=5\% P(X>26%)=P(12.1%X−6.2%>12.1%26%−6.2%)=P(z>1.64)=5%
Question 18
An analyst is looking to combine two stocks with annual returns that are jointly normally distributed and uncorrelated. Stock A has a mean return of 7 % 7\% 7% and a standard deviation of returns of 20 % 20\% 20%; Stock B has a mean return of 12 % 12\% 12% and a standard deviation of returns of 15 % 15\% 15%. If the analyst combines the stocks into an equally weighted portfolio, what is the probability that the portfolio return over the next year will be greater than 12 % 12\% 12%?
A.
42.07
%
42.07\%
42.07%
B.
44.32
%
44.32\%
44.32%
C.
55.67
%
55.67\%
55.67%
D.
57.93
%
57.93\%
57.93%
Answer: A
The combined expected mean return is:
μ
=
0.5
×
0.07
+
0.5
×
0.12
=
9.5
%
\mu=0.5\times0.07+0.5\times0.12 = 9.5\%
μ=0.5×0.07+0.5×0.12=9.5%
The combined volatility is: σ = 0. 5 2 × 0. 2 2 + 0. 5 2 × 0.1 5 2 = 12.5 % \sigma =\sqrt{0.5^2\times0.2^2 + 0.5^2\times0.15^2}=12.5\% σ=0.52×0.22+0.52×0.152=12.5%
P ( X > 12 % ) = P ( X − 12 % 12.5 % > 9.5 % − 12 % 12.5 % ) = P ( z > − 0.2 ) = 42.07 % P(X>12\%)=P(\cfrac{X-12\%}{12.5\%}>\cfrac{9.5\%-12\%}{12.5\%})=P(z>-0.2)=42.07\% P(X>12%)=P(12.5%X−12%>12.5%9.5%−12%)=P(z>−0.2)=42.07%
Question 19
Assume that a random variable follows a normal distribution with a mean of 80 80 80 and a standard deviation of 24 24 24. What percentage of this distribution is not between 44 44 44 and 128 128 128?
A.
4.56
%
4.56\%
4.56%
B.
8.96
%
8.96\%
8.96%
C.
13.36
%
13.36\%
13.36%
D.
18.15
%
18.15\%
18.15%
Answer: B
P
(
44
<
X
<
128
)
=
P
(
44
−
80
24
<
z
<
128
−
80
24
)
=
P
(
−
1.5
<
z
<
2
)
=
0.9104
P(44<X< 128) = P(\cfrac{44-80}{24}<z<\cfrac{128-80}{24})=P(-1.5<z<2)=0.9104
P(44<X<128)=P(2444−80<z<24128−80)=P(−1.5<z<2)=0.9104
Then 1 − 0.9104 = 8.96 % 1-0.9104=8.96\% 1−0.9104=8.96%
Question 20
Suppose that the annual profit if twi firms, one an incumbent (Big Firm, X 1 X_1 X1) and the other a starup(Small Firm, X 2 X_2 X2), can be describe with the following probaility matrix:
Small Firm X2 | |||||
Big Firm X1 | USD -1M | USD 0 | USD 2M | USD 4M | |
USD -50M | 1.97% | 3.9% | 0.8% | 0.1% | |
USD 0 | 3.93% | 23.5% | 12.6% | 2.99% | |
USD 10M | 0.8% | 12.7% | 14.2% | 6.68% | |
USD 100M | 0% | 3.09% | 6.58% | 6.16% |
What are the conditional expected profit and conditional standard deciation of the profit of BIg Firm when Small Firm either has no profit or loses money( X 2 ≤ 0 X_2\leq 0 X2≤0)?
A.
3.01
3.01
3.01;
30.52
30.52
30.52
B.
3.01
3.01
3.01;
931
931
931
C.
1.03
1.03
1.03;
30.52
30.52
30.52
D.
1.03
1.03
1.03;
931.25
931.25
931.25
Answer: C
We need to compute the conditional distribution given
X
2
≤
0
X_2\leq0
X2≤0. The relevant rows of the probability matrix are
X1|X2≤0 | USD -1M | USD 0 |
USD -50M | 1.97% | 3.9% |
USD 0 | 3.93% | 23.5% |
USD 10M | 0.8% | 12.7% |
USD 100M | 0% | 3.09% |
The conditional distribution can be constructed by summing across rows and the normalizing to sum to unity. The non-normalizd sum and the normailized version are
X1|X2≤0 | USD -1M | USD 0 |
USD -50M | 5.87% | 11.77% |
USD 0 | 27.43% | 54.98% |
USD 10M | 13.5% | 27.06% |
USD 100M | 3.09% | 6.19% |
Finally, the conditional expectation is E [ X 1 ∣ X 2 ≤ 0 ] = 11.77 % × − 50 + 54.98 % × 0 + 27.06 % × 10 + 6.19 % × 100 = 3.01 million E[X_1|X_2\leq0]=11.77\%\times-50+54.98\%\times0+27.06\%\times10+6.19\%\times100=3.01\;\text{million} E[X1∣X2≤0]=11.77%×−50+54.98%×0+27.06%×10+6.19%×100=3.01million
The conditional expectation squared is E [ [ X 1 2 ∣ X 2 ≤ 0 ] = 940.31 E[[X_1^2|X_2\leq0]=940.31 E[[X12∣X2≤0]=940.31
The conditional variance is V [ X 1 ] = E [ X 1 2 ] − E [ X 1 ] 2 = 940.31 − 3.0 1 2 = 931.25 V[X_1]=E[X_1^2]-E[X_1]^2=940.31-3.01^2=931.25 V[X1]=E[X12]−E[X1]2=940.31−3.012=931.25
So, the conditional stadard deviation is 30.52 million 30.52 \;\text{million} 30.52million
Question 21
The probability that a standard normally distributed random variable will be less than one standard deviation above its mean is:
A.
0.6827
0.6827
0.6827
B.
0.8413
0.8413
0.8413
C.
0.3173
0.3173
0.3173
D.
0.1587
0.1587
0.1587
Question 22
Let f ( x ) f(x) f(x) represent a probability function (which is called a probability mass function, p.m.f., for discrete random variables and a probability density function, p.d.f., for continuous variables) and let F ( x ) F(x) F(x) represent the corresponding cumulative distribution function (CDF); in the case of the continuous variable, F ( x ) F(x) F(x) is the integral (aka, anti-derivative) of the pdf. Each of the following is true about these probability functions EXCEPT which is false?
A. The limits of a cumulative distribution function (CDF) must be zero and one; i.e.,
F
(
−
∞
)
=
0
F(−\infin) = 0
F(−∞)=0 and
F
(
+
∞
)
=
1.0
F(+\infin) = 1.0
F(+∞)=1.0
B. For both discrete and continuous random variables, the cumulative distribution function (CDF) is necessarily a non-decreasing function.
C. In the case of a continuous random variable, we cannot talk about the probability of a specific value occurring; e.g.,
P
r
(
R
=
+
3.00
%
)
Pr(R = +3.00\%)
Pr(R=+3.00%) is meaningless
D. Bayes Theorem can only be applied to discrete random variables, such that continuous random variables must be transformed into their discrete equivalents
Answer: D
Bayes Theorem applies to both, although practicing application are almost always using simple discrete random variables.
Question 23
X X X and Y Y Y are discrete random variables with the following joint distribution. What is the conditional standard deviation of Y Y Y given X = 7 X=7 X=7?
Value of Y | |||||
20 | 20 | 30 | 40 | ||
Value of X | 1 | 0.04 | 0.06 | 0.13 | 0.04 |
4 | 0.12 | 0.17 | 0.07 | 0.05 | |
7 | 0.05 | 0.03 | 0.13 | 0.11 |
A.
10.3
10.3
10.3
B.
14.7
14.7
14.7
C.
21.2
21.2
21.2
D.
29.4
29.4
29.4
Answer: A
E
(
Y
∣
X
=
7
)
=
10
×
0.05
0.32
+
20
×
0.03
0.32
+
30
×
0.13
0.32
+
40
×
0.11
0.32
=
29.375
E(Y|X = 7) = 10\times\cfrac{0.05}{0.32} + 20\times\cfrac{0.03}{0.32} + 30\times\cfrac{0.13}{0.32} + 40\times\cfrac{0.11}{0.32} = 29.375
E(Y∣X=7)=10×0.320.05+20×0.320.03+30×0.320.13+40×0.320.11=29.375
E ( Y 2 ∣ X = 7 ) = 1 0 2 × 0.05 0.32 + 2 0 2 × 0.03 0.32 + 3 0 2 × 0.13 0.32 + 4 0 2 × 0.11 0.32 = 968.75 E(Y^2|X=7)=10^2\times\cfrac{0.05}{0.32} + 20^2\times\cfrac{0.03}{0.32} + 30^2\times\cfrac{0.13}{0.32} + 40^2\times\cfrac{0.11}{0.32}=968.75 E(Y2∣X=7)=102×0.320.05+202×0.320.03+302×0.320.13+402×0.320.11=968.75
V ( Y ∣ X = 7 ) = E ( Y 2 ∣ X = 7 ) − E ( Y ∣ X = 7 ) 2 = 968.75 − 29.3752 = 105.8594 V(Y|X = 7) =E(Y^2|X=7)-E(Y|X = 7)^2=968.75 − 29.3752 =105.8594 V(Y∣X=7)=E(Y2∣X=7)−E(Y∣X=7)2=968.75−29.3752=105.8594
Std. Dev ( Y ∣ X = 7 ) = 105.8594 = 10.289 \text{Std. Dev}(Y|X = 7) = \sqrt{105.8594 }= 10.289 Std. Dev(Y∣X=7)=105.8594=10.289
Question 24
Assume the probability density function(pdf) of a zero-coupon bond with a notional value of USD 10 10 10 is give by f ( x ) = x 8 − 0.75 f(x)=\cfrac{x}{8}-0.75 f(x)=8x−0.75 on the domain [ 6 , 10 ] [6,10] [6,10] where X X X is the price of the bond. What is the probability that the price of the bond is between USD 8 8 8 and USD 9 9 9?
A.
25.750
%
25.750\%
25.750%
B.
28.300
%
28.300\%
28.300%
C.
31.250
%
31.250\%
31.250%
D.
44.667
%
44.667\%
44.667%
Answer: C
The anti-derivative is
F
(
X
)
=
x
2
8
−
0.75
x
+
c
F(X)=\cfrac{x^2}{8}-0.75x+c
F(X)=8x2−0.75x+c
P [ 8 ≤ x ≤ 9 ] = F ( 9 ) − F ( 8 ) = 31.250 % P[8\leq x \leq 9]=F(9)-F(8)=31.250\% P[8≤x≤9]=F(9)−F(8)=31.250%
Question 25
For a certain operational process, the frequency of major loss events during a one period year varies form 0 0 0 to 5 5 5 and is characterized by the following discrete probability mass function (pmf) which is the exhaustive probability distribution and where b b b is a constant
Loss event (X) | 0 | 1 | 2 | 3 | 4 | 5 |
PMF(f(x)) | 12b | 7b | 5b | 3b | 2b | 1b |
Which is nearest to the probability that next year LESS THAN two major loss events will happen?
A.
5.3
%
5.3\%
5.3%
B.
22.6
%
22.6\%
22.6%
C.
63.3
%
63.3\%
63.3%
D.
75.0
%
75.0\%
75.0%
Answer: C
The sum of pmf probabilities must be
1
1
1, so
30
b
=
1
→
b
=
1
30
30b=1 \to b=\cfrac{1}{30}
30b=1→b=301
Therefore the P [ X < 2 ] = P [ X = 0 ] + P [ X = 1 ] = 12 30 + 7 30 = 63.33 % P[X<2]= P[X = 0] + P[X = 1] = \cfrac{12}{30} + \cfrac{7}{30} = 63.33\% P[X<2]=P[X=0]+P[X=1]=3012+307=63.33%
Question 26
A certain low-servity adminstrative(operational) process tends to produce an average of eight errors per week(where each week is five workdays). If this loss frequency process an be characterized by a Poisson distribution, which is NEAREST to the probability that more than one error will be produced tommorrow; i.e., P ( X > 1 ∣ λ = 8 / 5 ) P(X>1|\lambda=8/5) P(X>1∣λ=8/5) ?
A.
20.19
%
20.19\%
20.19%
B.
32.30
%
32.30\%
32.30%
C.
47.51
%
47.51\%
47.51%
D.
66.49
%
66.49\%
66.49%
Answer: C
P
(
X
>
1
)
=
1
−
P
(
X
=
0
)
−
P
(
X
=
1
)
P(X>1)=1-P(X=0)-P(X=1)
P(X>1)=1−P(X=0)−P(X=1), where
P
(
X
=
x
)
=
λ
x
e
−
λ
x
!
P(X=x)=\cfrac{\lambda^xe^{-\lambda}}{x!}
P(X=x)=x!λxe−λ and
P
(
X
>
1
)
=
1
−
20.19
%
−
32.30
%
=
47.51
%
P(X>1)=1-20.19\%-32.30\%=47.51\%
P(X>1)=1−20.19%−32.30%=47.51%.
Notice we need to translate the mean frequency from eight per week to 8 / 5 8/5 8/5 per day because we are seeking the probability of the number of occurrences in a single day.