Chapter 6

The Mathematics of Diversification

1
O! This learning, what a thing it is!

- William Shakespeare

2
 Outline
 Introduction
 Linear combinations
 Single-index model
 Multi-index model

3
 Introduction
 Thereason for portfolio theory
mathematics:
• To show why diversification is a good idea

• To show why diversification makes sense

logically

4
 Introduction (cont’d)
 Harry Markowitz’s efficient portfolios:
• Those portfolios providing the maximum return
for their level of risk

• Those portfolios providing the minimum risk

for a certain level of return

5
 Linear Combinations
 Introduction
 Return
 Variance

6
 Introduction
A portfolio’s performance is the result of
the performance of its components
• The return realized on a portfolio is a linear
combination of the returns on the individual
investments

• The variance of the portfolio is not a linear

combination of component variances
7
 Return
 The expected return of a portfolio is a
weighted average of the expected returns of
the components:
n
E ( R p )    xi E ( Ri ) 
i 1

where xi  proportion of portfolio

invested in security i and
n

x
i 1
i 1
8
 Variance
 Introduction
 Two-security case
 Minimum variance portfolio
 Correlation and risk reduction
 The n-security case

9
 Introduction
 Understanding portfolio variance is the
essence of understanding the mathematics
of diversification
• The variance of a linear combination of random
variables is not a weighted average of the
component variances

10
 Introduction (cont’d)
 Foran n-security portfolio, the portfolio
variance is:
n n
   xi x j ij i j
2
p
i 1 j 1

where xi  proportion of total investment in Security i

ij  correlation coefficient between
Security i and Security j

11
 Two-Security Case
 Fora two-security portfolio containing
Stock A and Stock B, the variance is:

  x   x   2xA xB  AB A B
2
p
2
A
2
A
2
B
2
B

12
 Two Security Case (cont’d)
Example

Assume the following statistics for Stock A and Stock B:

Stock A Stock B
Expected return .015 .020
Variance .050 .060
Standard deviation .224 .245
Weight 40% 60%
Correlation coefficient .50
13
 Two Security Case (cont’d)
Example (cont’d)

What is the expected return and variance of this two-

security portfolio?

14
 Two Security Case (cont’d)
Example (cont’d)

Solution: The expected return of this two-security

portfolio is: n
E ( R p )    xi E ( Ri ) 
i 1

  x A E ( RA )    xB E ( RB ) 
  0.4(0.015)    0.6(0.020) 
 0.018  1.80%
15
 Two Security Case (cont’d)
Example (cont’d)

Solution (cont’d): The variance of this two-security

portfolio is:

 2p  xA2 A2  xB2 B2  2 xA xB  AB A B

 (.4) (.05)  (.6) (.06)  2(.4)(.6)(.5)(.224)(.245)
2 2

 .0080  .0216  .0132

 .0428 16
 Minimum Variance Portfolio
 The minimum variance portfolio is the
particular combination of securities that will
result in the least possible variance

 Solving for the minimum variance portfolio

requires basic calculus

17
 Minimum Variance
Portfolio (cont’d)
 Fora two-security minimum variance
portfolio, the proportions invested in stocks
A and B are:
   A B  AB
2
xA  2 B

 A   B  2 A B  AB
2

xB  1  x A
18
 Minimum Variance
Portfolio (cont’d)
Example (cont’d)

Assume the same statistics for Stocks A and B as in the

previous example. What are the weights of the minimum
variance portfolio in this case?

19
 Minimum Variance
Portfolio (cont’d)
Example (cont’d)

Solution: The weights of the minimum variance portfolios

in this case are:

 B2   A B  AB .06  (.224)(.245)(.5)
xA  2   59.07%
 A   B  2 A B  AB .05  .06  2(.224)(.245)(.5)
2

xB  1  xA  1  .5907  40.93%

20
 Minimum Variance
Portfolio (cont’d)
Example (cont’d)
1.2

0.8
Weight A

0.6

0.4

0.2

0
0 0.01 0.02 0.03 0.04 0.05 0.06

Portfolio Variance 21
 Correlation and
Risk Reduction
 Portfolio risk decreases as the correlation
coefficient in the returns of two securities
decreases
 Risk reduction is greatest when the
securities are perfectly negatively correlated
 If the securities are perfectly positively
correlated, there is no risk reduction

22
 The n-Security Case
 For an n-security portfolio, the variance is:

n n
   xi x j ij i j
2
p
i 1 j 1

where xi  proportion of total investment in Security i

ij  correlation coefficient between
Security i and Security j

23
 The n-Security Case (cont’d)
 The equation includes the correlation
coefficient (or covariance) between all pairs
of securities in the portfolio

24
 The n-Security Case (cont’d)
A covariance matrix is a tabular
presentation of the pairwise combinations of
all portfolio components
• The required number of covariances to compute
a portfolio variance is (n2 – n)/2

• Any portfolio construction technique using the

full covariance matrix is called a Markowitz
model
25
 Single-Index Model
 Computational advantages
 Portfolio statistics with the single-index
model

26
 Computational Advantages
 Thesingle-index model compares all
securities to a single benchmark
• An alternative to comparing a security to each
of the others

• By observing how two independent securities

behave relative to a third value, we learn
something about how the securities are likely to
behave relative to each other
27
 Computational
Advantages (cont’d)
A single index drastically reduces the
number of computations needed to
determine portfolio variance
• A security’s beta is an example:
COV ( Ri , Rm )
i 
 m2
where Rm  return on the market index
 m2  variance of the market returns
Ri  return on Security i
28
 Portfolio Statistics With the
Single-Index Model
 Beta of a portfolio:
n
 p   xi  i
i 1

 Variance of a portfolio:
 2p   p2 m2   ep2
  p2 m2

29
 Portfolio Statistics With the
Single-Index Model (cont’d)
 Variance of a portfolio component:

    
i
2
i
2 2
m
2
ei

 Covariance of two portfolio components:

 AB   A  B m2

30
 Multi-Index Model
A multi-index model considers independent
variables other than the performance of an
overall market index
• Of particular interest are industry effects
– Factors associated with a particular line of business

– E.g., the performance of grocery stores vs. steel

companies in a recession

31
 Multi-Index Model (cont’d)
 The general form of a multi-index model:
Ri  ai   im I m   i1 I1   i 2 I 2  ...   in I n
where ai  constant
I m  return on the market index
I j  return on an industry index
 ij  Security i's beta for industry index j
 im  Security i's market beta
Ri  return on Security i
32