Licensed to Ngoc Le at ngocmnb314@gmail.com. Downloaded January 11, 2021.

The information provided in this document is intended solely for you. Please do not freely distribute.

P1.T2. Quantitative Analysis

Bionic Turtle FRM Practice Questions

Chapter 2: Random Variables

This is a super-collection of quantitative practice questions. It represents several years of
cumulative history mapped to the current reading. Previous readings include Miller, and
Gujarati, which we have retained in this practice question set.

By David Harper, CFA FRM CIPM

www.bionicturtle.com
Licensed to Ngoc Le at ngocmnb314@gmail.com. Downloaded January 11, 2021.
The information provided in this document is intended solely for you. Please do not freely distribute.

Note that this pertains to Chapters 1-6 in Topic 2, Quantitative Analysis. We will include
this introduction in each of those practice question sets for reference.

Within each chapter, our practice questions are sequenced in reverse chronological order
(appearing first are the questions written most recently). For example, consider Miller’s Chapter
2 (Probabilities), you will notice there are fully three (3) sets of questions:

 Questions T2.708 to 709 (Miller Chapter 2) were written in 2017. The 7XX denotes 2017.
 Questions T2.300 to 301 (Miller Chapter 2 were written in 2013. The 3XX denotes 2103.

The reason we include the prior questions is simple: although the FRM’s econometrics readings
have churned in recent years (specifically, for Probabilities and Statistics, from Gujarati to Stock
and Watson to Miller and now to GARP), the learning objectives (AIMs) have remained
essentially unchanged. The testable concepts themselves, in this case, are generally quite
durable over time.

Therefore, do not feel obligated to review all of the questions in this document! Rather,
consider the additional questions as merely a supplemental, optional resource for those who
want to spend additional time with the concepts.

The major sections are:

 Fundamentals of Probabilities (current QA-1, Chapter 1)

o Most Recent BT questions, (20.1 and 20.2)
o Previous BT questions, Miller Chapter 2 (T2.708 & T2.709)
o Previous BT questions, Miller Chapter 2 (T2.300 & T2.301)
o Previous BT questions, Stock & Watson Chapter 2 (T2.201 & T2.204)
o Previous BT questions, Gujarati (T2.59 to T2.61, T2.65)

 This Chapter: Random Variables (current QA-2, Chapter 2)

o Most Recent BT questions (20.3 and 20.4)
o Previous BT questions, Miller Chapter 3 (T2.710 & T2.712)
o Previous BT questions, Miller Chapters 2 & 3 (T2.303 & T2.307)
o Previous BT questions, Gujarati (T2.58, T2.59, T2.62, T2.65 & T2.66 )

 Common Univariate Random Variables (current QA-3, Chapter 3)

o Most Recent BT questions, (20.5 to 20.7)
o Previous BT questions, Miller Chapter 4 (T2.309 to T2.312 & T2.713 to T2.716)
o Previous BT questions ,Stock & Watson Chapter 2 (T2.205)
o Previous BT questions, Rachev Chapters 2 & 3 (T2.110 to T2.126)
o Previous BT questions, Gujarati (T2.59, T2.68, T2.72 to T2.74, T2.82)

 Multivariate Random Variables (current QA-4, Chapter 4)

o Most Recent BT questions Chapter 4 (20.8 to 20.10)
o Previous BT questions, Miller Chapters 2, 3 & 4 (T2.304, T2.709, T2.711 & T2.716)
o Previous BT questions, Stock & Watson Chapters 2 & 3 (T2.202, T2.212 to T2.213 )
o Previous BT questions, Gujarati (T2.62, T2.64, T2.65 & T2.67)

2
Licensed to Ngoc Le at ngocmnb314@gmail.com. Downloaded January 11, 2021.
The information provided in this document is intended solely for you. Please do not freely distribute.

 Sample Moments (current QA-5, Chapter 5)

o Most Recent BT questions (20.11 to 20.13)
o Previous BT questions, Miller Chapter 3 (T2.303 to T2.308, T2.710 to T2.712)
o Previous BT questions, Stock & Watson Chapters 2 & 3 (T2.203,T2.206 to T2.208,
T2.213)
o Previous BT questions, Gujarati (T2.66, T2.67, T2.69 to T2.71)

 Hypothesis Testing & Confidence Intervals (current QA-6, Chapter 6)

o Most Recent BT questions (20.14 to 20.15)
o Previous BT questions, Miller Chapters 5 & 7 (T2.313 – T2.315, T2.718 & T2.719)
o Previous BT questions, Stock & Watson Chapter 3 (T2.209 to T2.212)
o Previous BT questions, Gujarati (T2.75, T2.77, T2.79 to T2.81)

3
Licensed to Ngoc Le at ngocmnb314@gmail.com. Downloaded January 11, 2021.
The information provided in this document is intended solely for you. Please do not freely distribute.

STATISTICS - KEY IDEAS ........................................................................................................ 5

Chapter 2: Random Variables

P1.T2.20.3. RANDOM VARIABLES (1ST OF 2)............................................................................... 6
P1.T2.20.4. RANDOM VARIABLES (2ND OF 2) .............................................................................. 9

Statistics (Miller, Chapter 3)

P1.T2.710. MEAN AND STANDARD DEVIATION ...........................................................................12
P1.T2.712. SKEW, KURTOSIS, COSKEW AND COKURTOSIS .........................................................15
P1.T2.303 MEAN AND VARIANCE OF CONTINUOUS PROBABILITY DENSITY FUNCTIONS (PDF).........18
P1.T2.307. SKEW AND KURTOSIS (MILLER)..............................................................................20

Statistics (Gujarati’s Essentials of Econometrics)

P1.T2.58. RANDOM VARIABLES ...............................................................................................22
P1.T2.59. GUJARATI’S INTRODUCTION TO PROBABILITIES ..........................................................24
P1.T2.62. EXPECTATION & VARIANCE OF VARIABLE ..................................................................27
P1.T2.65. VARIANCE AND CONDITIONAL EXPECTATIONS ............................................................29
P1.T2.66. SKEW & KURTOSIS .................................................................................................31

4
Licensed to Ngoc Le at ngocmnb314@gmail.com. Downloaded January 11, 2021.
The information provided in this document is intended solely for you. Please do not freely distribute.

Statistics - Key Ideas

 We generally do not observe population parameters but instead infer them from sample
estimates which are values given by estimators such as sample mean and sample
variance. An estimator is a “recipe” for obtaining an estimate of a population parameter.
 The sample mean is BLUE: Best Linear Unbiased Estimator
 The t-statistic tests the null hypothesis that the population mean equals a certain value.
 If the sample (n) is large (e.g., greater than 30), the t-statistic has a standard normal
sampling distribution when the null hypothesis is true.
 A common test is to test the significance of a regression coefficient. While the specifics
vary, in many cases here the null is “the slope coefficient is zero.”
 The p-value is an “exact (aka, marginal) significance level:” it is the probability of
drawing a statistic at least as adverse to the null hypothesis as the one actually
computed (observed), assuming the null hypothesis is correct.
 p-value is the smallest significance level at which the null can be rejected
 If the p-value is very small (e.g., 0.00x), reject the null. If the p-value is large (e.g.,
0.19 or 19%), accept (fail to reject) the null.
 You will NOT be asked, on the FRM, to calculate a p-value (e.g., you cannot derive it on
the TI BA II+ or HP 12c). You may be asked to interpret a given p-value.
A 95% confidence interval for is an interval constructed so that it contains the true value
of in 95% of all possible samples:

90% CI for Y  Y  1.64SE Y  
95% CI for Y  Y  1.96SE Y 

99% CI for Y  Y  2.58SE Y 

 Where SE is the standard error = sample standard deviation / SQRT (n) = SQRT
(sample variance / n)
1
 Sample covariance: sample  XY   ( X i  X )(Yi  Y )
n 1
s XY
 Sample correlation sample   rXY 
s X sY
 Correlation (X,Y) = covariance (X,Y) / [Std Deviation(X)] * [Std Deviation(Y)]

5
Licensed to Ngoc Le at ngocmnb314@gmail.com. Downloaded January 11, 2021.
The information provided in this document is intended solely for you. Please do not freely distribute.

Chapter 2: Random Variables

P1.T2.20.3. Random variables (1st of 2)
P1.T2.20.4. Random variables (2nd of 2)

P1.T2.20.3. Random variables (1st of 2)

Learning objectives: Describe and distinguish a probability mass function from a
cumulative distribution function and explain the relationship between these two.
Understand and apply the concept of a mathematical expectation of a random variable.
Describe the four common population moments.

20.3.1. Assume a continuous random variable over the domain {6 < X < 10} is given by f(x) =
a*x where (a) is a constant; i.e., {f(x) = ax | x ∈ 6 < X < 10}. What is the Pr(X ≤ 8)?
Bonus: what is the variable's expected value?

a) 19.53%
b) 43.75%
c) 50.00%
d) 56.25%

20.3.2. A discrete random variable is characterized by the probability mass function (pmf) as
given by f(x) = x*a, and its domain is the set of integers {6, 7, 8., 9, and 10}. What is the
variable's expected value?

a) 6.67
b) 8.00
c) 8.25
d) 9.33

6
Licensed to Ngoc Le at ngocmnb314@gmail.com. Downloaded January 11, 2021.
The information provided in this document is intended solely for you. Please do not freely distribute.

20.3.3. Ralph is an analyst who wants to characterize a random variable with a discrete
probability distribution where the only outcomes are {0, 1, 2, 3, and 4}. The Poisson distribution
with a mean of 1.0 is a surprisingly good fit as it gives Pr(X = 0) = Pr(X = 1) = 36.8%. The
problem with the Poisson is that it has a long tail such that the Pr(X ≥ 5) = 0.366%; for example,
there is a very tiny possibility (1.0E-08) that the outcome could exceed ten given the Poisson's
support is the entire set of natural numbers. To enforce a true probability distribution that is
bounded at four, Ralph simply rounds the pmf densities and, due to sheer luck, when rounded
(to two digits) the first five outcomes (including zero) sum exactly to 100.0%. The ensuing
probability distribution is the following, which might be dubbed a "truncated Poisson" with λ =
1.0:

The exact mean (aka, expected value or weighted average) of this variable is 0.990, but let's
assume its average is a round 1.0. What is the skewness of this variable?

a) -0.774
b) Zero
c) +0.869
d) +2.440

7
Licensed to Ngoc Le at ngocmnb314@gmail.com. Downloaded January 11, 2021.
The information provided in this document is intended solely for you. Please do not freely distribute.

Answers:

0.3.1. B. True: 43.75%

The (indefinite) integral evaluated over (6,10) must equal one such that a*(10^2/2 - 6^2/2) = 1.0
--> a = 1.0/(10^2/2 - 6^2/2) = 1/(100/2 - 36/2) = 1/32. Because a = 1/32, the density function is
given by f(x) = x/32 over [6,10]

The cumulative distribution function is given by F(x) = x^2/64 - c, but F(6) must be zero and
F(10) must be 1.0; therefore the CDF is F(x) = x^2/64 - 0.5625. And F(8) = 8^2/64 - 0.5625 = 1.0
- 0.5625 = 0.43750 or 43.75%

In regard to the bonus question, we need to integrate x*f(x) or x*x/32 = x^2/32 which is x^3/32
* 1/3 = x^3/96, and evaluate this over [6,0] such that the mean is 10^3/96 - 6^3/96 = 10.41667 -
2.25 = 8.1667. See Absolutely continuous case at https://en.wikipedia.org/wiki/Expected_value.

By the way, what is the median? Given that the CDF F(X) = x^2/64 - 0.5625, we can solve for x
= sqrt([F(X) + 0.5625]*64) which solve for any quantile (ie., x) as a function of the CDF. The
median is the 50th percentile such that the associated quantile (aka, the median) is given by, x
= sqrt([0.50 + 0.5625]*64) = 8.24621. So this distribution has a mean of 8.1667 and a median of
8.2462.

20.3.2. C. True: 8.25

We know that 6a + 7a + 8a + 9a + 10a = 1.0 such that a = 1/40 = 0.0250 and the pmf is given
by f(x) = x/40 = 0.0250*x.
The expected value equals 1/40*(6^2 + 7^2 + 8^2 + 9^2 + 10^2) = 8.25

20.3.3. C. True: skewness = +0.869

The third central moment = 37.0%*(0 - 1)^3 + 37.0%*(1 - 1)^3 + 18.0%*(2 - 1)^3 + 6.0%*(3 -
1)^3 + 2.0%*(4 - 1)^3 = 0.830.
Skewness standardizes the third central moment by dividing by the standard deviation cubed,
σ^3, or equivalently, variance raised to the 2/3-rd power because σ^3 = (σ^2)^(3/2).

In this case, the variance (aka, second central moment = 37.0%*(0 - 1)^2 + 37.0%*(1 - 1)^2 +
18.0%*(2 - 1)^2 + 6.0%*(3 - 1)^2 + 2.0%*(4 - 1)^2 = 0.970. Therefore, the skewness = 0.830 ÷
0.970^1.5 = 0.8688

Discuss in the forum here: https://www.bionicturtle.com/forum/threads/p1-t2-20-3-

random-variables-first-of-two.23275/

8
Licensed to Ngoc Le at ngocmnb314@gmail.com. Downloaded January 11, 2021.
The information provided in this document is intended solely for you. Please do not freely distribute.

P1.T2.20.4. Random variables (2nd of 2)

Learning objectives: Explain the differences between a probability mass function and a
probability density function. Characterize the quantile function and quantile-based
estimators. Explain the effect of a linear transformation of a random variable on the
mean, variance, standard deviation, skewness, kurtosis, median and interquartile range.

20.4.1. Consider the probability mass function (pmf) below. For example, Pr(X = -1.0) = 20.0%.

As we can see, this distribution is symmetrical so we know that its skewness is zero without
performing any calculations. We are told the variance is 1.20 (although we can calculate the
variance). What is this distribution's kurtosis?

a) Zero
b) 2.50
c) 3.60
d) 4.40

9
Licensed to Ngoc Le at ngocmnb314@gmail.com. Downloaded January 11, 2021.
The information provided in this document is intended solely for you. Please do not freely distribute.

20.4.2. Peter decides that the payoff of his option straddle strategy can be approximated by the
probability density function (pdf) illustrated below. The function is: f(x) = a*x^2 over the real
domain {-3 < X < +3); i.e., {f(x) = a*x^2 | x ∈ -3.0 < X < 3.0}. He used x-squared because he
wants the shape of a parabola, but how does he determine the value of the constant, a? It
cannot be anything! Because this is a probability distribution, it must be true that the integral,
a*x^3/3, when evaluated over [3, -3] equals one: the area under the pdf curve must equal one,
and the integral of the pdf is the cumulative distribution function (CDF).

Given that a*3^3/3 - a*(-3)^3/3 = 1.0, we must have 9a - (-9a) = 1.0 such that a = 1/18.
Therefore, a is 1/18 and his probability density function is f(x) = x^2/18. But is x^3/54 the
integral? He notices that if F(x) = x^3/54 then F(3) = 27/54 = 0.5 and F(-3) = -0.5, but the CDF
requires that F(3) = 1.0 and F(-3.0) = zero. Seeing this, he realizes that the indefinite integral
includes a constant and is given by a*x^3 + c, or specifically, x^3/54 + c. Now it is possible for
3^3/54 + c = 1.0, if c = 1.0 - 0.5 = 0.5. Finally, he can specify the exact pdf, f(x) = x^2/18, as the
derivative of the correct CDF, F(x) = x^3/54 + 0.5, so that F(3) = 1.0 and F(-3) = 0.

Value-at-risk (VaR) is the distributional quantile

associated with a specified probability. The
inverse CDF (aka, quantile function) returns the
quantile implied by a probability, q = F^(-1)(p),
whereas the CDF returns the probability
associated with a quantile: p = F(q), or in this
case, p = F(X). In this distribution, losses are on
the left (negative payoffs), so the 95.0% VaR is
the quantile implied by a 5.0% probability: X =
F^(-1)(p) = F^(-1)(0.050). For this distribution,
what is the 95.0% VaR, in this case, the 0.050
quantile?

a) -2.90
b) -2.70
c) -1.50
d) +0.33

20.4.3. Let Z be a random variable that is a linear function of random variables X and Y, where
Z = 3*X + 7*Y? If the standard deviation of X and Y, respectively, are σ(X) = 4.0 and σ(Y) = 5.0
and the correlation between X and Y is ρ(X,Y) = 0.50, then what is the standard deviation of Z,
σ(Z)?

a) 6.40
b) 7.81
c) 37.00
d) 42.30

10
Licensed to Ngoc Le at ngocmnb314@gmail.com. Downloaded January 11, 2021.
The information provided in this document is intended solely for you. Please do not freely distribute.

Answers:

20.4.1. B. True: 2.50

(-2)^4*10.0% + (-1)^4*20.0% + 0^4*40.0% + 1^4*20.0% + 2^4*10.0% = 3.60, but we need to

standardize such that kurtosis = 3.60 / 1.20^2 = 2.50.

Kurtosis is the fourth central moment (aka, fourth moment about the mean) standardized by the
standard deviation raised to the fourth power (aka, square of the second moment). So, in the
numerator we have E[X - μ(x)]^4, which is the fourth central moment; and this is divided by
σ(X)^4 in order to standardize the moment. See
https://en.wikipedia.org/wiki/Standardized_moment

20.4.2. A. True: -2.90

p = 0.050 = x^3/54 + 0.5, such that x = [(0.050 - 0.50)*54]^(1/3)

= -2.8965.

In other words, if we want the 95.0% VaR, we want the

quantile (i.e., the value on the X-axis. In this case, it starts at -
3.0) such that on the pdf, the area to the left (under the curve)
is 5.0% which corresponds to 5.0% on the Y-axis of the CDF.
See below. But that is simply the CDF! The CDF F(x) is the
probability: at 5.0% --> 5.0% = x^3/54 + 0.5, and we can solve
for the implied quantile. We return with x = -2.8965 which
signifies, per X = F^(-1)(p), that q = -2.8965 = F^(-1)(5.0%).
The probability distribution is a mathematical description of a
random variable (e.g., the CDF must start at zero and end at
1.0). In this question, we've identified -2.8965 as the quantile
we expect to "do better than" 95.0% of the time. Or, put
another way, we expect to do worse than -2.8965 only 5.0% of
the time.

20.4.3. D. True: 42.30

σ(Z) = sqrt[σ^2(Z)], and σ^2(Z) = σ^2(3*X + 7*Y) = 3^2*σ^2(X) + 7^2*σ^2(Y) + 2*3*7*cov(X,Y) =

9*4^2 + 49*5^2 + 2*3*7*(4 * 5 * 0.5) = 1,789.0 and σ(Z) = sqrt(1,789.0) = 42.30.

This applies the basic variance properties that we need to know; see
https://en.wikipedia.org/wiki/Variance#Properties
In this case, σ^2(a*X + b*Y) = a^2*σ^2(X) + b^2*σ^2(Y) + 2*a*b*Cov(X,Y), where (a) and (b) are
constants.

Discuss here in the forum: https://www.bionicturtle.com/forum/threads/p1-t2-20-4-

random-variables-2nd-of-2.23281/

11
Licensed to Ngoc Le at ngocmnb314@gmail.com. Downloaded January 11, 2021.
The information provided in this document is intended solely for you. Please do not freely distribute.

Statistics (Miller, Chapter 3)

P1.T2.710. Mean and standard deviation
P1.T2.712. Skew, kurtosis, coskew and cokurtosis
P1.T2.303 Mean and variance of continuous probability density functions (pdf)
P1.T2.307. Skew and Kurtosis

P1.T2.710. Mean and standard deviation

Learning objectives: Interpret and apply the mean, standard deviation, and variance of a
random variable. Calculate the mean, standard deviation, and variance of a discrete
random variable. Interpret and calculate the expected value of a discrete random
variable.

710.1. The following probability matrix contains the joint probabilities for random variables X =
{2, 7, or 12} and Y = {1, 3, or 5}:

We are informed that (X) and (Y) are independent. What is the expected value of the product of
X and Y, E(X*Y)?

a) 15.0
b) 21.0
c) 30.5
d) 35.0

12
Licensed to Ngoc Le at ngocmnb314@gmail.com. Downloaded January 11, 2021.
The information provided in this document is intended solely for you. Please do not freely distribute.

710.2. Peter is running the first draft of a Monte Carlo simulation and he wants a simple random
variable to capture the loss frequency per week (i.e., the number of loss events) associated with
a operational process. As he is just experimenting with his model, he does not have a
probability density function in mind. Instead, he has a simple rule-based idea that he wants to
express in a probability function. The number of losses per week will be either zero, one, two or
three; X = {0, 1, 2, or 3}. An outcome of X = 3.0 is the least likely; an outcome of X = 2.0 is twice
as likely as X = 3.0; an outcome of X = 1.0 is twice as likely as X = 2.0, and finally an outcome
of X = zero is twice as likely as X = 1.0. This is illustrated below:

Assuming this qualifies as a probability distribution, which is NEAREST to the standard

deviation of this random variable?
a) a. Zero
b) b. 0.625
c) c. 0.750
d) d. 0.930

710.3. Consider a random variable that represents the loss severity of a risky asset and is given
by the continuous probability distribution f(x) = 3*x^2/64 on the domain from zero to four:

What are this variable's mean and variance?

a) µ = 1.0 and σ^2 = 3.50
b) µ = 2.0 and σ^2 = 2.75
c) µ = 3.0 and σ^2 = 0.60
d) µ = 3.6 and σ^2 = 0.25

13
Licensed to Ngoc Le at ngocmnb314@gmail.com. Downloaded January 11, 2021.
The information provided in this document is intended solely for you. Please do not freely distribute.

Answers:

710.1. B. Correct. 21.0. Although we can sum the product of f(x)*X*Y for all nine cells, it is
much easier to seize on the property of independence: if X and Y are independent, then by
definition E(X*Y) = E(X)*E(Y) = 3.0*7.0 = 21.0.

710.2. D. Correct is 0.930

Let a = constant such that 1*a + 2*a + 4*a + 8*a = 1.0 per a probability distribution, and
therefore a = 1/15.
The expected value of E(X) = (1/15)*3.0 + (2/15)*2.0 + (4/15)*1.0 + (8/15)*0 = (3 + 4 + 4)/15 =
11/15 = 0.7333.

The expected value of E(X^2) = (1/15)*3.0^2 + (2/15)*2.0^2 + (4/15)*1.0^2 + (8/15)*0^2 = (9 + 8

+ 4)/15 = 21/15 = 1.40.

The variance of X, σ^2(X) = E(X^2) - E(X)^2 = 1.40 - (11/15)^2 = 0.86222 and the standard
deviation equals sqrt[1.40 - (11/15)^2] = 0.92856.

710.3. C. Correct: µ = 3.0 and σ^2 = 0.60

 To retrieve the mean µ, we integrate x*f(x)
 To retrieve the variance, we integrate (x - µ)^2*f(x)

Discuss here in forum: https://www.bionicturtle.com/forum/threads/p1-t2-710-mean-and-

standard-deviation-miller-ch-3.11270/

14
Licensed to Ngoc Le at ngocmnb314@gmail.com. Downloaded January 11, 2021.
The information provided in this document is intended solely for you. Please do not freely distribute.

P1.T2.712. Skew, kurtosis, coskew and cokurtosis

Learning objectives: Describe the four central moments of a statistical variable or
distribution: mean, variance, skewness, and kurtosis. Interpret the skewness and
kurtosis of a statistical distribution, and interpret the concepts of coskewness and
cokurtosis. Describe and interpret the best linear unbiased estimator.

712.1. Consider the following discrete probability distribution of asset returns:

As shown, this asset's expected return is +2.55%. Which is NEAREST to this variable's skew;
aka, standardized third central moment?

a) -2.25
b) -0.96
c) +0.33
d) +1.06

15
Licensed to Ngoc Le at ngocmnb314@gmail.com. Downloaded January 11, 2021.
The information provided in this document is intended solely for you. Please do not freely distribute.

712.2. Consider the following discrete probability distribution of asset returns:

As shown, this asset's expected return is +3.95%. Which is NEAREST to this variable's kurtosis;
aka, standardized fourth central moment?

a) -1.47
b) +2.81
c) +4.10
d) +7.50

712.3. Portfolio manager Peter manages a large portfolio with 100 component positions. He is
interested in analyzing the non-trivial cross moments in the portfolio (trivial cross-moments are
the position's coskew/cokurtosis with itself, which is simply the position's standard skew or
kurtosis, so these are analogous to the diagonal of a covariance matrix which is mere variances.
Each of the following statements is true EXCEPT which is inaccurate?

a) Between any two (n = 2) positions in the portfolio, the number of non-trivial coskew
moments between them is two
b) Between any two (n = 2) positions in the portfolio, the number of non-trivial cokurtosis
moments between them is three
c) Given a sub-portfolio consisting of any two positions, lower coskew values (i.e., where
positives are gains and negatives are losses) imply greater risk for the sub-portfolio
d) Although it is easy to estimate this portfolio's set of higher-order cross moments,
standard skew and kurtosis are preferred because they are BLUE and the informational
utility of coskew and cokurtosis is negligible

16
Licensed to Ngoc Le at ngocmnb314@gmail.com. Downloaded January 11, 2021.
The information provided in this document is intended solely for you. Please do not freely distribute.

Answers:

712.1. B. -0.96. Because -947.1/99.3^(3/2) = -0.957; i.e., negative or skewed to the left. We can
eyeball this by noticing that the third central moment (displayed as -947.1) is divided by
approximately 10^3 as the standard deviation is approximately 10 ≈ sqrt(99.3).

712.2. C. 4.10. Because 32,769.7/89.4^2 = 4.1001; i.e., heavy-tailed with "excess kurtosis" of
4.10 - 3.0 = 1.10.

712.3. D. False. This is actually not easy because for 100 positions there exist fully
171,600 coskew cross moments and 4,421,175 cokurtosis cross moments!

Also, according to Miller, three is indeed often information utility in coskew and cokurtosis (alas
there is an formidable curse of dimensionality in accessing them). The reference to BLUE is a
red herring; BLUE refers to estimator properties.

In regard to (A), (B) and (C), each is TRUE.

In regard to true (A) and (B), the number of non-trivial cross moments is given by k = (m+n-
1)!/[m!(n-1)!] - n. But in the case of only two variables, say (X) and (Y), the total number of
coskew cross moments is four, which includes two trivial: S(XXX), S(XXY), S(XYY), S(YYY).
The total number of cokurtosis cross moments is five, which includes two trivial: K(XXXX),
K(XXXY), K(XXYY), K(XYYY), K(YYYY).

Discuss here in forum: https://www.bionicturtle.com/forum/threads/p1-t2-712-skew-kurtosis-

coskew-and-cokurtosis-miller-chapter-3.12190/

17
Licensed to Ngoc Le at ngocmnb314@gmail.com. Downloaded January 11, 2021.
The information provided in this document is intended solely for you. Please do not freely distribute.

P1.T2.303 Mean and variance of continuous probability density

functions (pdf)
AIMs: Define, calculate, and interpret the mean, standard deviation, and variance of a
random variable.

303.1. Assume a continuous probability density function (pdf) is given by f(x) =a*x such that 0 ≤
x ≤ 12, where (a) is a constant (we can retrieve this constant, knowing this is a probability
density function):
( )= . . 0≤ ≤ 12
What is the mean of (x)?
a) 5.5
b) 6.0
c) 8.0
d) 9.3

303.2. Assume a continuous probability density function (pdf) be given by f(x) = a*x^2 such that
0 ≤ x ≤ 3, where (a) is a constant (that we can find).

( )= . . 0≤ ≤3
Let us arbitrarily define the unexpected loss (UL) as the difference between this distribution's
mean and its 5.0% quantile function; i.e., UL(X) = mean (X) - inverse CDF (5%)(X). We could
call this a 95% relative VaR since it is relative to the mean. What is this UL?
a) 0.62
b) 1.14
c) 2.05
d) 3.37

303.3. Assume the following probability density function (pdf) for a random variable X:

( )= . . 0≤ ≤6
18
What is the variance of X?
a) a. 2.0
b) b. 3.3
c) c. 4.1
d) d. 5.7

18
Licensed to Ngoc Le at ngocmnb314@gmail.com. Downloaded January 11, 2021.
The information provided in this document is intended solely for you. Please do not freely distribute.

Answers:

303.1. C. 8.0
If this is a valid probability (pdf) then a*(1/2)*x^2 evaluated over [0,12] must equal one:
a*(1/2)*12^2 = 1.0, and a = 1/72.

Therefore the pdf function is given by f(x) = x/72 over the domain of [0,12].
The mean = Integral of x*f(x) = x*(1/72)*x = Integral of x^2/72 over [0,12] = x^3/216 over [0,12] =
12^3/216 = 8.0

303.2. B. 1.14
If this is a valid pdf then a^2*(1/3)*x^3 evaluated over [0,3] must equal one: a*(1/3)*x^3 = 1.0,
and a = 3/27 = 1/9.

Therefore the pdf function is given by f(x) = x^2/9 over the domain of [0,3]
The mean (mu) = Integral of x*f(x) = x*x^2/9 = Integral of x^3/9 over [0,3] = (1/9)*(1/4)*x^4 over
[0,3] = 3^4/36 = 9/4.

For 5% quantile, we need value of (m) such that the integral of f(x)*dx over [0,m] = 0.05.
So, we need (m) so that x^2/9*dx over [0,m] = 0.05, and
x^3/27 over [0,m] = 0.05, and
m^3/27 = 0.05, therefore m = (27*0.05)^(1/3) = 1.11
UL(5%) = mean - 1.11 = 9/4 - 1.11 = 1.14

303.3. A. 2.0
Mean (mu) = Integral of x*f(x) = x*x/18 =x^2/18 evaluated from [0,6]
= (1/54)*x^3 from [0,6] = 6^3/54 = 4.0

Variance = Integral of (x - mu)^2*f(x)*dx evaluated from [0,6]

= (1/18)*[x^4/4 - 8*x^3/3 + 8*x^2] from [0,6] = (1/18)*[6^4/4 - 8*6^3/3 + 8*6^2] = 2.0

Discuss in forum here: http://www.bionicturtle.com/forum/threads/p1-t2-303-mean-and-

variance-of-continuous-probability-density-functions-pdf.6783/

19
Licensed to Ngoc Le at ngocmnb314@gmail.com. Downloaded January 11, 2021.
The information provided in this document is intended solely for you. Please do not freely distribute.

P1.T2.307. Skew and Kurtosis (Miller)

AIMs: Describe the four central moments of a statistical
variable or distribution: mean, variance, skewness and
kurtosis.

307.1. A bond has a default probability of 5.0%. Which is nearest, respectively, to the skew (S)
and kurtosis (K) of the distribution?

a) S = 0.0, K = 2.8
b) S = 0.8, K = -7.5
c) S = 4.1, K = 18.1
d) S = 18.9, K = 4.2

307.2. Assume a discrete uniform random variable (X) can assume one of three outcomes {1, 2,
or 6} with equal probability of 1/3rd each; which is to say, this is not a sample but a
(population's) probability distribution. Which is nearest to this distribution's skew?

a) -0.37
b) +0.60
c) +1.44
d) +2.79

307.3. Let (X) be a random variable with three outcomes: Prob[X=1] = 25%, Prob[X=2] = 50%,
and Prob[X=3] = 25%. Which is nearest to the kurtosis of this distribution?

a) 0.33
b) 2.00
c) 3.50
d) 4.75

20
Licensed to Ngoc Le at ngocmnb314@gmail.com. Downloaded January 11, 2021.
The information provided in this document is intended solely for you. Please do not freely distribute.

Answers:

307.1. C. S = 4.1, K = 18.1

Let X = 0 with prob 95.0% and X = 1 with prob 5.0%, such that mean (X) = 0.050:
3rd central moment = (1-0.05)^3*5% + (0-0.05)^3*95% = 0.04275, such that skew =
0.04275/(5%*95%)^(3/2) = 4.1295 (or -4.1295)
4th central moment = (1-0.05)^4*5% + (0-0.05)^4*95% = 0.04073, such that kurtosis =
0.04073/(5%*95%)^2= 18.053
i.e., excess kurtosis = 18.053 - 3.0 = 15.053

307.2. B. +0.60
The mean is (1+2+6)/3 = 3.0.
The 3rd central moment = [(1-3)^3 + (2-3)^3 + (6-3)^3]/3 = 6.0. As the variance is 4.67,
The skewness = 3rd moment/variance^(3/2) = 6.0/4.67^(3/2) = 0.5952.

Note we can also apply Miller's Equation 3.45 for the 3rd central moment:
= E[X^3] - 3*mu*variance - mu^3 = 75 - 3*3*4.667 - 3^3 = 6.00

307.3. B. 2.00
The mean of X = 1*25% + 2*50% + 3*25% = 2.0.
The variance of X = (1-2)^2*25% + (2-2)^2*50% + (3-2)^2*25% = 0.50
The 4th central moment = (1-2)^4*25% + (2-2)^4*50% + (3-2)^4*25% = 0.50
The kurtosis of X = 4th central moment/variance^2 = 0.50/0.50^2 = 2.00

Discuss in forum here: http://www.bionicturtle.com/forum/threads/p1-t2-307-skew-and-

kurtosis-miller.6825/

21
Licensed to Ngoc Le at ngocmnb314@gmail.com. Downloaded January 11, 2021.
The information provided in this document is intended solely for you. Please do not freely distribute.

Statistics (Gujarati’s Essentials of Econometrics)

P1.T2.58. Random variables
P1.T2.59. Gujarati’s introduction to probabilities
P1.T2.62. Expectation & variance of variable
P1.T2.65. Variance and conditional expectations
P1.T2.66. Skew & Kurtosis

P1.T2.58. Random variables

AIM: Define random variables and distinguish between continuous and discrete random
variables.

58.1. Which of the following is typically NOT treated as a random variable?

a) Drift component of geometric Brownian motion (GBM)
b) Volatility component of GBM
c) Probability of default (PD)
d) Exogenous bid-ask spread in liquidity-adjusted value at risk (LVaR)

58.2 Each of the following random variables tends to be characterized by a CONTINUOUS

random variable EXCEPT for (bonus if you can identify the most common applicable
distribution!):
a) Operational loss severity
b) Exceptions in a VaR backtest
c) Loss given default (or recovery rate)
d) Waiting time until next default

58.3 Each of the following random variables tends to be characterized by a DISCRETE random
variable EXCEPT for (bonus if you can identify the most common applicable distribution!):
a) Operational loss frequency
b) Defaults in a basket credit default swap (basket CDS)
c) Bond Default
d) Asset returns

22
Licensed to Ngoc Le at ngocmnb314@gmail.com. Downloaded January 11, 2021.
The information provided in this document is intended solely for you. Please do not freely distribute.

Answers:

58.1 A. GBM: dS(t)/S(t) = u*dt + sigma *dz where u = drift and sigma = volatility dW(t) is
the stochastic (random) term such that Brownian motion, which underlies BSM, is
symbolically:

Log return = drift*time + volatility * SQRT(time) * randomized (stochastic) i.e., the process is
random/stochastic due to the second term, but the drift is deterministic

In regard to (D), we can treat the bid-ask spread, as the liquidity risk input into LVaR, as either
a constant or a random variable under the “exogenous spread approach”

58.2 B. VaR backtest applies binomial as losses EITHER exceed or do not exceed the
VaR; a series of yes/no (Bernoulli) is a binomial.
 In regard to (A), OpLoss severity has many forms but for the tail, extreme value theory
(EVT) which contains POT is popular
 In regard to (C), beta distribution is popular for LGD/recovery due to its flexibility
 In regard to (D), “time” should betray a continuous idea. The exponential is used here.
Interestingly, the discrete Poisson (e.g., number of losses) maps to the continuous
exponential (time until the next loss).

58.3 D. (Asset returns are typically assumed to be continuous; e.g., lognormal)

 In regard to (A), OpLoss frequency is often characterized by Poisson
 In regard to (B), really basic is binomial (but assumes i.i.d., so probably need better)
 In regard to (C), default is a Bernoulli.
Discrete variables can be counted (0, 1, 2 ...). Think coin flip, die roll
Continuous variables must be measured. Think time, distance, asset returns

Discuss in forum here: https://www.bionicturtle.com/forum/threads/l1-t2-58-random-

variables.3603/

23
Licensed to Ngoc Le at ngocmnb314@gmail.com. Downloaded January 11, 2021.
The information provided in this document is intended solely for you. Please do not freely distribute.

P1.T2.59. Gujarati’s introduction to probabilities

AIM: Define the probability of an event. Describe the relative frequency or empirical
definition of probability. Describe and interpret the probability mass function, probability
density function, and cumulative density function for a random variable. Distinguish
between univariate and multivariate probability density functions.

59.1 If each outcome has an equal chance of occurring and the outcomes are mutually
exclusive, the P(outcome A) = number of outcomes favorable to A / total number of outcomes.
Which type of probability is this?
a) A priori
b) A posterior
c) Bayes Theorem
d) Relevant frequency

59.2 If a bank’s 99% daily value at risk (VaR) is determined by simple historical simulation (HS),
which probability is used?
a) Classical
b) A priori
c) Relative frequency (empirical)
d) Parametric (analytical)

59.3 Consider the statement: “Our bank’s 99% daily VaR is $1 million.” This reflects which
generic probability function?
a) PMF
b) PDF
c) CDF
d) None of the above

59.4 Consider the statement: Each SINGLE ROW of a credit migration (transition) matrix is itself
an empirical probability distribution.
a) True because the outcomes sum to 1.0 (100%)
b) True because the outcomes are exclusive
c) True because the probabilities are empirical
d) True because all of the above are true

24
Licensed to Ngoc Le at ngocmnb314@gmail.com. Downloaded January 11, 2021.
The information provided in this document is intended solely for you. Please do not freely distribute.

59.5 Which of the following necessarily implies a multivariate probability distribution (while the
others can imply a univariate probability distribution)?
a) Poisson to model frequency of an operational loss
b) Copula to model default dependence in a CDO/basket CDO
c) Binomial to model probability of defaults reaching mezzanine tranche in a basket CDS
where the credits are i.i.d.
d) Exponential to model (waiting) time until default for a single credit given hazard rate
(a.k.a., default intensity)

59.6 Bayes Theorem says that P(A|B) is given by:

a) Conditional (A|B) / Marginal (B)
b) Conditional (B|A) / Marginal (B)
c) Joint P(AB) / Marginal (A)
d) Joint P(AB) / Marginal (B)

25
Licensed to Ngoc Le at ngocmnb314@gmail.com. Downloaded January 11, 2021.
The information provided in this document is intended solely for you. Please do not freely distribute.

Answers:

59.1 A. (A priori)

We can deduce the probability prior to any experience; e.g., in the case of rolling a die, or
picking a card from a deck, we can imagine the odds without the need for running experiments
and collecting observations

59.2 C. (empirical)

Historical simulation calibrates confidence% VaR (e.g., 99%) based on the (1-confidence%;
e.g., 1%) worst loss experienced in the historical sample. This is the essence of an empirical
distribution.
 In regard to (A) and (B), which are the same, this is after (posterior) data is observed,
not before
 In regard to (D), there is no parametric/statistical distribution assumed. This is the key
ADVANTAGE of HS: it does not make an assumption about a (parametric) distribution
and therefore, arguably, lends itself more easily to heavy tails.

59.3 C. (VaR is a CDF quantile)

In this case, the statement is equivalent to “1% of the time, we expect to lose at least $1 million;”
i.e., P[ ABS(loss) >= $1 million] =1% is the same as P[x loss <= -$1million] = 1%, which is a
CDF

59.4 D. (all of the above are true)

Each single row contains exclusive probabilities that a credit/obligor will end the period with a
certain rating; the probabilities sum to 1.0 and are empirical.

59.5 B. (copula is multivariate)

A copula is a function that “joins” marginal distributions together, using the function to
incorporate the dependence, into a multivariate probability function.

In regard to (C), the i.i.d. assumption is key to the binomial and enables the univariate
distribution: If i.i.d. applies, the all defaults are characterized by the same, single variable,
P[default] which is a Bernoulli. The collection of i.i.d Bernoullis (each with the same p = ?) is a
binomial.

59.6 D. Joint P(AB) / Marginal (B)

P(A|B) = P(B|A)P(A) / P(B) = P(AB)/P(B) = joint(AB)/marginal(B)

Discuss in forum here: https://www.bionicturtle.com/forum/threads/l1-t2-59-

gujarati%E2%80%99s-introduction-to-probabilities.3606/

26
Licensed to Ngoc Le at ngocmnb314@gmail.com. Downloaded January 11, 2021.
The information provided in this document is intended solely for you. Please do not freely distribute.

P1.T2.62. Expectation & variance of variable

AIM: Define, calculate and interpret the variance of a random variable.

62.1 A random variable (r.v.) has the following PMF: f(X) = bX over the domain X = [0, 1, 2, 3,
4]; e.g., f(1) = b, f(2)= 2b. What is the expected value of X?
a) 2.0
b) 2.2
c) 2.5
d) 3.0

62.2 What is the variance of X?

a) 1.00
b) 1.33
c) 1.50
d) 2.00

62.3 Assume a $100 par bond has a probability of default (PD) of 10%, where default is
characterized by a Bernoulli distribution, and if there is a default, no recovery is expected such
that loss given default (LGD) is a non-random 100%. What is the standard deviation of,
respectively, the loss of (i) the one bond and (ii) ten of the bonds under an i.i.d. assumption?
a) $10 and $100.00
b) $10 and $300.00
c) $30 and $300.00
d) $30 and $94.87

62.4 What is the standard deviation of the sum of a roll of, respectively, (i) 10 six-sided dice and
(ii) 20 six-sided dice?
a) 2.92 and 29.2
b) 3.16 and 4.47
c) 5.4 and 7.6
d) 5.4 and 58.3

27
Licensed to Ngoc Le at ngocmnb314@gmail.com. Downloaded January 11, 2021.
The information provided in this document is intended solely for you. Please do not freely distribute.

Answers:

62.1 D. (EV = 3.0)

Since r.v. is a PDF, the sum of f(x) must be 1.0 such that 0+b+2b+3b+4b=1.0. Therefore, b =
1/10 = 0.1.
E[X] = 0 + 1*0.1 + 2*0.2 + 3*0.3 + 4*0.4 = 3.0; or 30/10 = 3.0

62.2 A. (Variance and standard deviation = 1.0)

Variance(X) = E(X^2) - [E(X)]^2
E(X^2) = 0 + 0.10*1^2 + 0.20*2^2 + 0.30*3^2 + 0.40*4^2 = 10; such that
Variance (X) = 10 - 3^2 = 1.0

62.3 D. $30 and $94.87

The standard deviation of the Bernoulli = SQRT[p(1-p)] = SQRT[10%*90%] = 0.30.
In this case, $100 * 0.3 = $30.00
A series of i.i.d. Bernoulli variables is, by definition, a binomial. The standard deviation = $100 *
SQRT[n*p*(1-p)] = $100* SQRT[10*10%*90%] = $100 * SQRT(0.9)
= $100 * 0.949 = $94.87
… note per i.i.d., the variance scales by 10x, but the standard deviation scales by the SQRT(10)
= 3.16 = $94.87/$30.00

62.4 C. 5.4 and 7.6

The point of this is to give further practice to the key formula: Variance(X) = E[X^2] - [E(X)]^2.
The variance of single six-sided die = E[X^2] - [E(X)]^2 = 15.17 - 3.5^2 ~= 2.9167
The variance of n i.i.d. rolls = n*2.9167;
Standard deviation of sum of 10 die = SQRT(10*2.9167) = 5.40;
Standard deviation of sum of 20 die = SQRT(20*2.9167) = 7.64;

Discuss in forum here: https://www.bionicturtle.com/forum/threads/l1-t2-62-expectation-

variance-of-variable.3614/

28
Licensed to Ngoc Le at ngocmnb314@gmail.com. Downloaded January 11, 2021.
The information provided in this document is intended solely for you. Please do not freely distribute.

P1.T2.65. Variance and conditional expectations

AIMs: Define, calculate and interpret the mean and variance of a set of random variables.
Describe the difference between conditional and unconditional expectation.
65.1 Assume a two-asset portfolio where the weight of the first asset is (w) and the weight of the
second asset is (1-w). The first asset has return volatility of 10%, the second asset has return
volatility of 20%, and their returns have a correlation of +0.25. Take the first derivative of the
formula for portfolio variance to find the weight of the first asset that produces the minimum
variance portfolio; i.e., the local minimum is where the first derivative with respect to (w) is equal
to zero. What is the weight (w) that produces the minimum variance portfolio?
a) 50.0%
b) 67.5%
c) 75.0%
d) 87.5%

65.2 Three of the following concepts imply a conditional expectation or probability. Which one is
the exception and implies an unconditional expectation?
a) Expected shortfall
b) GARCH(1,1)
c) P(AB) / P (A | B)
d) Hazard rate (a.k.a., default intensity)

29
Licensed to Ngoc Le at ngocmnb314@gmail.com. Downloaded January 11, 2021.
The information provided in this document is intended solely for you. Please do not freely distribute.

Answers:

65.1. D. 87.5%
Portfolio variance (V) = 10%^2*w^2 + 20%^2*(1-w)^2 + 2*w*(1-w)*10%*20%*0.25, such that
V = 0.01*w^2 + 0.04*(1-w)^2 + 0.01*w*(1-w),
V = 0.01w^2 + 0.04 - 0.08w + 0.04w^2 + 0.01w - 0.01w^2,
V = 0.04w^2 - 0.07w + 0.04.
First derivative with respect to (w) gives:
dV/dw = 0.08w - 0.07, and set that equal to zero for local minimum such that
0 = 0.08w - 0.07 and w = 7/8 = 0.875 or 87.5%
And we can check: For w = 87.5%, portfolio volatility = SQRT (portfolio variance) = 9.683%,
which is the minimum variance portfolio.

65.2 C.
Conditional P (A | B) = joint P(AB) / unconditional P (B), such that:
Unconditional P(B) = joint P(AB) / Conditional P (A|B)
 In regard to (A), expected shortfall (aka, conditional tail loss) is a conditional: E (L | L >
VaR).
 In regard to (B), the “C” in GARCH(1,1) refers to conditional as this process modes a
conditional variance.
 In regard to (D), hazard rate is a conditional probability of default: P(D) | survival
through previous periods.

Discuss in forum here: https://www.bionicturtle.com/forum/threads/l1-t2-65-variance-and-

conditional-expectations.3633/

30
Licensed to Ngoc Le at ngocmnb314@gmail.com. Downloaded January 11, 2021.
The information provided in this document is intended solely for you. Please do not freely distribute.

P1.T2.66. Skew & Kurtosis

AIMS: Define, calculate and interpret the skewness and kurtosis of a random variable.
Describe and identify a platykurtic and leptokurtic distribution. Define the skewness and
kurtosis of a normally distributed random variable.

66.1 Assume random variable (r.v.) has the following PMF:

What is the skewness of X?

a) 0.0
b) 0.2
c) 0.4
d) 0.6

66.2 What is the kurtosis of X?

a) 2.2
b) 2.6
c) 3.2
d) 3.8

66.3 Which of the following distributions is necessarily platykurtic?

a) Normal
b) Empirical based on historical simulation
c) Uniform distribution
d) Student’s t

31
Licensed to Ngoc Le at ngocmnb314@gmail.com. Downloaded January 11, 2021.
The information provided in this document is intended solely for you. Please do not freely distribute.

66.4 Which of the following distributions is necessarily leptokurtic?

a) Normal
b) Empirical based on historical simulation
c) Uniform
d) Student’s t

66.5 If the daily loss (L) is normally distributed such that L ~ N(mean = $20, variance = $16),
what is the probability on a given day that the loss will exceed $30?
a) 0.62%
b) 0.92%
c) 1.32%
d) 2.62%

32
Licensed to Ngoc Le at ngocmnb314@gmail.com. Downloaded January 11, 2021.
The information provided in this document is intended solely for you. Please do not freely distribute.

Answers:

66.1 D (skew = 0.6)

Please note that because 4b + 3b + 2b + 1b + 0 = 1.0, 10b = 1.0 such that b = 0.10.
Skew = Third moment /StdDev^3 = E[X - mu(X)]^3 / StdDev(X)^3 = 0.60 / 1^3 = 0.60

66.2 A (kurtosis = 2.2)

Kurtosis = Fourth moment /StdDev^4 = E[X - mu(X)]^4 / StdDev(X)^4 =2.2 / 1^4 = 2.20

66.3 C. (Kurtosis of uniform = 1.8)

In regard to (B), an empirical distribution can be either light- or heavy-tailed.

66.4 D (student’s t)
Student’s t has excess kurtosis = 6/(d.f. - 4) so that as d.f. increases and it tends toward normal,
the heavy-tails are tending toward normal but are always, even if slightly, heavy-tailed.(But the
student’s T not going to give us meaningfully heavy tails. For meaningfully heavy-tails, we look
to other distributions)

66.5 A (0.62%)
Z = (30 - 20)/SQRT(16) = 2.5 standard deviations
P (Z > 2.5) = 1 - NORM.S.DIST(2.5) = 0.62%

Discuss in forum here: https://www.bionicturtle.com/forum/threads/l1-t2-66-skew-

kurtosis.3619/

33