Top Banner
Portfolio Models MGT 4850 Spring 2007 University of Lethbridge
21

Portfolio Models MGT 4850 Spring 2007 University of Lethbridge.

Dec 21, 2015

Download

Documents

Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Page 1: Portfolio Models MGT 4850 Spring 2007 University of Lethbridge.

Portfolio Models

MGT 4850

Spring 2007

University of Lethbridge

Page 2: Portfolio Models MGT 4850 Spring 2007 University of Lethbridge.

Introduction

• Portfolio basic calculations

• Two-Asset examples– Correlation and Covariance– Trend line

• Portfolio Means and Variances

• Matrix Notation

• Efficient Portfolios

Page 3: Portfolio Models MGT 4850 Spring 2007 University of Lethbridge.

Review of Matrices• a matrix (plural matrices) is a rectangular

table of numbers, consisting of abstract quantities that can be added and multiplied.

Page 4: Portfolio Models MGT 4850 Spring 2007 University of Lethbridge.

Adding and multiplying matrices

• Sum

• Scalar multiplication

Page 5: Portfolio Models MGT 4850 Spring 2007 University of Lethbridge.

Matrix multiplication • Well-defined only if the number of columns of the left

matrix is the same as the number of rows of the right matrix. If A is an m-by-n matrix and B is an n-by-p matrix, then their matrix product AB is the m-by-p matrix (m rows, p columns).

Page 6: Portfolio Models MGT 4850 Spring 2007 University of Lethbridge.

Matrix multiplication

• Note that the number of of columns of the left matrix is the same as the number of rows of the right matrix , e. g. A*B →A(3x4) and B(4x6) then product C(3x6).

• Row*Column if A(1x8); B(8*1) →scalar

• Column*Row if A(6x1); B(1x5) →C(6x5)

Page 7: Portfolio Models MGT 4850 Spring 2007 University of Lethbridge.

Matrix multiplication properties:

• (AB)C = A(BC) for all k-by-m matrices A, m-by-n matrices B and n-by-p matrices C ("associativity").

• (A + B)C = AC + BC for all m-by-n matrices A and B and n-by-k matrices C ("right distributivity").

• C(A + B) = CA + CB for all m-by-n matrices A and B and k-by-m matrices C ("left distributivity").

Page 8: Portfolio Models MGT 4850 Spring 2007 University of Lethbridge.

The Mathematics of Diversification

• Linear combinations

• Single-index model

• Multi-index model

• Stochastic Dominance

Page 9: Portfolio Models MGT 4850 Spring 2007 University of Lethbridge.

Return

• The expected return of a portfolio is a weighted average of the expected returns of the components:

1

1

( ) ( )

where proportion of portfolio

invested in security and

1

n

p i ii

i

n

ii

E R x E R

x

i

x

Page 10: Portfolio Models MGT 4850 Spring 2007 University of Lethbridge.

Two-Security Case

• For a two-security portfolio containing Stock A and Stock B, the variance is:

2 2 2 2 2 2p A A B B A B AB A Bx x x x

Page 11: Portfolio Models MGT 4850 Spring 2007 University of Lethbridge.

portfolio variance

• For an n-security portfolio, the portfolio variance is:

2

1 1

where proportion of total investment in Security

correlation coefficient between

Security and Security

n n

p i j ij i ji j

i

ij

x x

x i

i j

Page 12: Portfolio Models MGT 4850 Spring 2007 University of Lethbridge.

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

Page 13: Portfolio Models MGT 4850 Spring 2007 University of Lethbridge.

Minimum Variance Portfolio (cont’d)

• For a two-security minimum variance portfolio, the proportions invested in stocks A and B are:

2

2 2 2

1

B A B ABA

A B A B AB

B A

x

x x

Page 14: Portfolio Models MGT 4850 Spring 2007 University of Lethbridge.

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

Page 15: Portfolio Models MGT 4850 Spring 2007 University of Lethbridge.

Single-Index Model

• Computational advantages

• Portfolio statistics with the single-index model

Page 16: Portfolio Models MGT 4850 Spring 2007 University of Lethbridge.

Computational Advantages

• The single-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

Page 17: Portfolio Models MGT 4850 Spring 2007 University of Lethbridge.

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:

2

2

( , )

where return on the market index

variance of the market returns

return on Security

i mi

m

m

m

i

COV R R

R

R i

Page 18: Portfolio Models MGT 4850 Spring 2007 University of Lethbridge.

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

Page 19: Portfolio Models MGT 4850 Spring 2007 University of Lethbridge.

Multi-Index Model (cont’d)

• The general form of a multi-index model:

1 1 2 2 ...

where constant

return on the market index

return on an industry index

Security 's beta for industry index

Security 's market beta

retur

i i im m i i in n

i

m

j

ij

im

i

R a I I I I

a

I

I

i j

i

R

n on Security i

Page 20: Portfolio Models MGT 4850 Spring 2007 University of Lethbridge.

Basic Mechanics of Portfolio calculations

• Two Asset Example p.132

• Continuously compounded monthly returns – mean variance std deviation

• Covariance and variance calculations p.133

• Correlation coefficient as the square root of the regression R2

• Portfolio mean and variance p.135

Page 21: Portfolio Models MGT 4850 Spring 2007 University of Lethbridge.

Portfolio Mean and Variance

• Matrix notation; column vector Γ for the weights transpose is a row vector ΓT

• Expected return on each asset as a column vector or E its transpose ET

• Expected return on the portfolio is a scalar

(row*column)

Portfolio variance ΓTS Γ (S var/cov matrix)