Reading 8: Probability Concepts

Learning Outcome Statements

• Covered
• 8a, 8b, 8c, 8d, 8e, 8f, 8g, 8h, 8i, 8j, 8k, 8l, 8m, 8n

• Not Covered
• 8o
 Properties, Types of Probability
For any event E, P(E) is between zero and 1:

0 ≤ P (E ) ≤ 1

For any collection of mutually exclusive and exhaustive events Ei,

∑E i =1

Empirical probability is based on an analysis of data.

Subjective probability is based on personal perception (and biases).

A priori probability is based on reasoning in the absence of data.

 Odds
Odds represent the payoff on a fair bet (one where the expected payoff is zero), given the
probability of an event P(E),

Odds for (or in favor of) E: P(E)/[1 – P(E)]

Odds a ga inst E: [1 – P(E)]/P(E)

Example: Suppose that the probability of A is 25%. Then the odds in favor of A are 25%/75%, or 1/3
(sometimes written 1:3), and the odds against A are 75%/25%, or 3/1 (or 3:1).
A
If the odds in favor of an event E are A:B, then: P (E ) =
A+B

B
If the odds against an event E are A:B, then: P (E ) =
A+B
 Practice Question
Analysts have quoted the odds against Syzygy Unlimited meeting its quarterly
earnings target at 2:3. The analysts’ estimate of the probability that Syzygy
meets its earnings target is closest to:

A. 40%
B. 60%
C. 67%
 Unconditional and Conditional Probability
The unconditional probability of A—P(A)—is the probability of A irrespective of the outcome of
other events (or without the knowledge of the outcome of other events).

Example: The probability that the economy will expand by more than 2%.

The conditional probability of A given B—P(A|B)—is the probability of A knowing that event B has
occurred.

Example: The probability that the economy will expand by more than 2% given that the Fed has
reduced interest rates by 50 basis points

Two events A and B are independent if:

P(A|B) = P(A) and P(B|A) = P(B)

 Rules for Probability—I
Addition Rule
P(A or B) = P(A) + P(B) – P(AB)

A AB B

Multiplication Rule

P(AB) = P(A|B) × P(B) = P(B|A) × P(A)

For independent events:

P(AB) = P(A) × P(B)

 Rules for Probability —II
Total Probability Rule
If S1, S2, . . ., Sn are mutually exclusive and exhaustive events (scenarios), then
P(A) = P(AS1) + P(AS2) + . . . + P(ASn)
= P(A|S1)P(S1) + P(A|S2)P(S2) + . . . + P(A|Sn)P(Sn)
 Rules for Probability—III
Example: The probability of an increase in interest rates is 70%. If interest rates increase, the
probability that the economy grows is 30%, while if interest rates don’t increase, the probability
that the economy grows is 60%. What is the (unconditional) probability that the economy grows?

P(I) = 70%, P(IC) = 1 – 70% = 30%

P(G|I) = 30%, P(G|IC) = 60%

P(G) = P(GI) + P(GIC) = P(G|I)P(I) + P(G|IC)P(IC)

= (0.3 × 0.7) + (0.6 × 0.3)

= 0.21 + 0.18 = 0.39 = 39%

 Tree Diagram
Whether interest rates decrease or EPS = $3.50
increase, company performance can be P = 0.14
good or poor P = 0.20
Interest Rates
Decrease
P= EPS = $3.10
0.80 P = 0.56
P = 0.70

E(EPS) = EPS = $3.00

$3.11 P= P = 0.27
P=
Interest Rates 0.90
0.30
Increase
P = 0.10 EPS = $2.60
P = 0.03
E(EPS) = 0.14($3.50) + 0.56($3.10) + 0.27($3.00) + 0.03($2.60) = $3.11
 Expected Value, Variance, Standard Deviation —I
Given a set of (numerical) outcomes {X1, X2, . . ., Xn} and probabilities P(Xi) for each of those
outcomes, the expected value of X is:
n
E ( X ) = ∑ P ( Xi ) Xi
i =1

The variance of X is:

n

∑ P ( X i )  X i − E ( X )
2
=σ 2
X
i =1

The standard deviation of X is:

n

∑ P ( X )  X − E ( X ) 
2
σX
= σ
= 2
X i i
i =1
 Expected Value, Variance, Standard Deviation —II
Example: You’re given the following data:

E(X) = 0.1(4%) + 0.2(3%) + 0.3(–1%) + 0.4(2%) = 1.5%

σ2 X = 0.1(4% – 1.5%) + 0.2(3% – 1.5%)

+ 0.3(–1% – 1.5%) + 0.4(2% – 1.5%)

= 0.000305

σX = √0.000305 = 1.746%
 Covariance —I
Given a population of pairs of observations {(X1, Y1), . . ., (Xn, Yn)},and mean values μX, μY for the Xs
and Ys, respectively, the covariance of X and Y is:
n

∑( X i − µ X )(Yi − µY )
Cov ( X ,Y ) = i =1
n
If the observations form a sample, the covariance is:

∑( X )( )
n

i − X Yi − Y
Cov ( X ,Y ) = i =1
n −1
If there is a probability P(Xi, Yi) for each observation, the covariance is:
n
( X ,Y )
Cov= ∑ P ( X ,Y )( X
i =1
i i i − µ X )(Yi − µY )
 Covariance —II
Example: You’re given the following data:

μX = 0.1(4%) + 0.2(3%) + 0.3(–1%) + 0.4(2%) = 1.5%

μ Y = 0.1(2%) + 0.2(–2%) + 0.3(4%) + 0.4(3%) = 2.2%

Cov(X,Y) = 0.1(4% – 1.5%)(2% – 2.2%) + 0.2(3% – 1.5%)(–2% – 2.2%)

+ 0.3(–1% – 1.5%)(4% – 2.2%) + 0.4(2% – 1.5%)(3% – 2.2%)

= -0.00025
 Covariance—III
Example: You’re given the following table of joint probabilities for all possible pairs of returns r1 and r2:

E(r 1) = 0.30(5%) + 0.35(7%) + 0.35(9%) = 7.1%

E(r 2) = 0.30(2%) + 0.40(4%) + 0.30(7%) = 4.3%
Cov(r 1,r 2) = 0.10(5% – 7.1%)(2% – 4.3%) + . . .
+ 0.05(9% – 7.1%)(7% – 4.3%) = –0.000083
σ (r 1 ) = 0.30(5% – 7.1%)2 + 0.35(7% – 7.1%)2 + 0.35(9% – 7.1%)2 = 0.000259
2

σ(r 1 ) = √0.000259 = 1.609%

σ (r 2 ) = 0.30(2% – 4.3%) + 0.40(4% – 4.3%)2 + 0.30(7% – 4.3%)2 = 0.000381
2 2

σ(r 2 ) = √0.000381 = 1.952%

ρ(r 1 , r 2 ) = –0.000083/[(1.609%)(1.952%)]
= –0.2642
 Covariance—IV
Properties of covariance:
• Values can range from –∞ to +∞.
• Positive values suggest that when X is above its mean, Y is above its mean,
and when X is below its mean, Y is below its mean.
• Negative values suggest that when X is above its mean, Y is below its mean,
and when X is below its mean, Y is above its mean.
• The units are the product of the units on X and the units on Y; e.g., if X is
interest rate and Y is EPS, then the units on Cov(X,Y) are % × $/share.
 Correlation—I
The correlation of two variables X and Y is:
Cov ( X ,Y )
Corr ( X ,Y ) =
σ XσY
Properties of correlation:
• Measures the strength of the linear relationship of X, Y.
• Values can range from –1 to +1.
• Positive values suggest that X and Y are above their means together,or below their
means together.
• Negative values suggest that when X is above its mean, Y is below its mean, and vice
versa.
• Correlation is just a number; it has no units.
• Population correlation is denoted by ρ, sample correlation by r; r is always equal to ρ.
 Correlation—II
Example: You’re given the following data:

μX = 1.5%, μ Y = 2.2%

σ X = 1.746%, σ Y = 2.182%

Cov(X, Y) = –0.00025

Cov ( X ,Y ) −0.00025
ρ X ,Y = = = −0.6561
σ XσY (1.746% )( 2.182% )
 Practice Question
Given the variance of X is 1.4, the variance of Y is 2.1, and the covariance of X and Y is
–0.429, the correlation of X and Y is closest to:

A. –0.250
B. –0.146
C. –0.050
 Scatter Plots and Correlation Analysis
A scatter plot is a graph that illustrates the relationship between observations
of two data series in two dimensions.
Correlation analysis expresses the relationship between two data series in a
single number. The correlation coefficient measures the strength and direction
of the linear relationship between two random variables.
• A correlation coefficient greater than 0 means that when one variable increases
(decreases), the other tends to increase (decrease) as well.
• A correlation coefficient less than 0 means that when one variable increases
(decreases), the other tends to decrease (increase).
• A correlation coefficient of 0 indicates that no linear relation exists between the
two variables.
 Portfolio Returns
Given a portfolio with two assets having weights w1 and w2 (w1 + w2 = 1), expected returns r1 and r2,
standard deviations of returns σ1 and σ2, respectively, and correlation of returns ρ1,2, the expected
portfolio return is:
E ( rport
= ) w1r1 + w 2r2
The expected variance of portfolio returns is:

σ r2 = w12σ 12 + w 22σ 22 + 2w1w 2 ρ1,2σ 1σ 2

port

= w12σ 12 + w 22σ 22 + 2w1w 2Cov ( r1, r2 )

The expected standard deviation of portfolio returns is:

σrport
= σ r2 =
port
w12σ 12 + w 22σ 22 + 2w1w 2 ρ1,2σ 1σ 2

= w12σ 12 + w 22σ 22 + 2w1w 2Cov ( r1, r2 )

 Practice Question
A portfolio comprises 70% security A and 30% security B. A’s expected return is 5% while B’s is 9%.
A’s standard deviation of returns is 4%, B’s is 12%, and the correlation of returns between A and B
is +0.4. The expected return and standard deviation of returns for the portfolio are closest to:

E(rp) σ(rp)
A. 6.20% 5.37%
B. 6.20% 8.95%
C. 7.80% 8.95%
 Bayes’ Formula—I
For any events A and B:
P (B | A) P ( A)
P ( A | B) =
P (B )

This is a straightforward consequence of the rules for conditional probability:

P ( A | B )=
P ( B ) P=
( AB ) P ( B | A ) P ( A )
Simply divide each side by P(B).

Problems that can be solved using Bayes’ formula are often easier to solve using a tree
diagram.
 Bayes’ Formula—II
Example: You’re given the following information:
• D = Decrease in interest rates
• E = Economic expansion
• P(D) = 60%
• P(E|D) = 90%
• P(EC|DC) = 80%

What is the probability that interest rates decreased, given an economic expansion?

P(E) = P(E|D)P(D) + P(E|DC)P(DC)

= (0.90)(0.60) + (0.20)(0.40) = 0.62

P (E | D ) P (D ) (=
0.90 )( 0.60 )
P (D | E )
= = 87.1%
P (E ) 0.62
 Bayes’ Formula —III
Economy
Expands P = 0.60 × 0.90 = 0.54
Interest Rates
Decrease
Economy
Contracts P = 0.60 × 0.10 = 0.06

Economy
Expands P = 0.40 × 0.20 = 0.08
Interest Rates
Increase
Economy
Contracts P = 0.40 × 0.80 = 0.32
0.54
P (D | E )
= = 87.1%
0.54 + 0.08
 Practice Question
Alpha Beta Gamma (ΑΒΓ) Corporation hopes to sign a large contract in a new market it’s been
pursuing; ΑΒΓ puts the probability of signing at 75%. If they’re successful, there’s an 80%
chance they’ll meet next quarter’s earnings goal, while if they fail, there’s only a 15% chance of
meeting the goal. If they meet the goal, the probability that they signed the contract is closest to:

A. 60%
B. 75%
C. 94%
Practice Questions and Solutions
 Practice Question
Analysts have quoted the odds against Syzygy Unlimited meeting its quarterly
earnings target at 2:3. The analysts’ estimate of the probability that Syzygy
meets its earnings target is closest to:

A. 40%
B. 60%
C. 67%

Correct answer: B. 60%

P(E) = 3/(2 + 3) = 3/5 = 0.60

 Practice Question
Given the variance of X is 1.4, the variance of Y is 2.1, and the covariance of X and Y is –
0.429, the correlation of X and Y is closest to:

A. –0.250
B. –0.146
C. –0.050

Correct answer: A. –0.250

σX = √1.4 = 1.183, σ Y = √2.1 = 1.449

ρ X,Y = –0.429/(1.183 × 1.449)

= –0.250
 Practice Question
A portfolio comprises 70% security A and 30% security B. A’s expected return is 5% while B’s is 9%.
A’s standard deviation of returns is 4%, B’s is 12%, and the correlation of returns between A and B
is +0.4. The expected return and standard deviation of returns for the portfolio are closest to:

E(rp) σ(rp)
A. 6.20% 5.37%
B. 6.20% 8.95%
C. 7.80% 8.95%

Correct answer: A. 6.20% 5.37%

E(r p ) = 0.7(5%) + 0.3(9%) = 6.2%

σ 2 (r p ) = 0.7 2 (4%)2 + 0.3 2 (12%)2 + 2(0.7)(0.3)(0.4)(4%)(12%)(0.3) = 0.002685

σ(r p ) = √0.002685 = 5.37%
 Practice Question
Alpha Beta Gamma (ΑΒΓ) Corporation hopes to sign a large contract in a new market it’s been
pursuing; ΑΒΓ puts the probability of signing at 75%. If they’re successful, there’s an 80%
chance they’ll meet next quarter’s earnings goal, while if they fail there’s only a 15% chance of
meeting the goal. If they meet the goal, the probability that they signed the contract is closest to:

A. 60%
B. 75%
C. 94%

Correct answer: C. 94%

P(meeting goal) = 0.75(0.80) + 0.25(0.15) = 0.6375

P(signing contract and meeting goal) = 0.75(0.80) = 0.60
P(signing contract | goal is met) = 0.60/0.6375 = 0.9412