Global Asset Allocation and Stock Selection

Estimation Error and

Portfolio Optimization
Campbell R. Harvey
Duke University, Durham, NC USA
National Bureau of Economic Research, Cambridge MA USA

Cam.harvey@duke.edu
+1 919.660.7768 office || +1 919.271.8156 mobile
http://www.duke.edu/~charvey
 Motivation
• The Markowitz Mean-Variance Efficiency is the standard
optimization framework for modern asset management.
• Given the expected returns, standard deviations and
correlations of assets (along with constraints), the
optimization procedure solves for the set of portfolio
weights that has the lowest risk for a given level of
portfolio expected returns.
• Standard algorithms (linear programming/quadratic
programming) are available to compute the efficient
frontier with or without short-selling/borrowing
constraints.
 Motivation
• A number of objections to MV Efficiency have been
raised:
1. Investor Utility: Utility might involve preferences for more than
means and variances and might be a complex function.
2. Multi-period framework: The one-period nature of static
optimization does not take dynamic factors into account.
3. Liabilities: Little attention is given to the liability side.
4. Instability and Ambiguity: Small changes in input assumptions
often imply large changes in the optimized portfolio. The MVE
procedure overuses statistically estimated information and
magnifies estimation errors.
• Jorion (1992, Financial Analyst Journal) addresses
“Portfolio Optimization in Practice” and proposes the
first resampling method.
 Motivation
• Richard Michaud (1998) has built a business around
resampling. Implemented in Northfield optimizers.
• Ibbotson Associates also uses a resampling technique
 The Procedure
The procedure described below has U.S. Patent #6,003,018 by Michaud et
al., December 19, 1999.

• Estimate the expected returns and the variance-covariance

matrix () [say, the MLE (average) or using Bayesian
techniques]. Suppose there are m assets.

• Solve for the minimum-variance portfolio. Call the expected

return of this portfolio L. Solve for the maximum return
portfolio. Call the expected return of this portfolio H.

• Choose the number of discrete increments, in returns, for

characterizing the frontier. That is, for the purpose of the
Monte Carlo analysis, one can think of looking at a series of
points on the frontier - rather than every point on the frontier.
 The Procedure
• Suppose for L=.05 and H=.20 and we choose the number
of increments, K=16. This means that we evaluate the
frontier at expected return={.05, .06, ..., .19, .20}, that is
16 different points.

• We will represent the ‘frontier’ as ak, where ‘a’

represents weights. So for m assets, ak is Kxm (rows
represent the number of points on the frontier and
columns are the assets). The pair (ak, ) then represents
the efficient frontier. In our example, we would have 16
rows (discrete increments) and m columns (number of
assets).
E[r]
The Procedure
0.20 H
0.19
0.18
0.17
0.16
0.15
0.14
0.13
0.12
0.11
0.10
0.09
0.08
0.07
0.06
0.05 L
0.04
0.03
0.02
0.01
0.00
0 0.2 0.4 0.6 0.8 1 1.2


 The Procedure
Columns are Asset Weights
Row E[r] Asset 1 Asset 2 Asset 3 Asset 4 Asset 5
1 0.05
2 0.06
3 0.07
4 0.08
5 0.09
6 0.1
7 0.11
8 0.12 Matrix = ak k=16 rows
9 0.13
10 0.14
11 0.15
12 0.16
13 0.17
14 0.18
15 0.19
16 0.2

m=5 columns
 The Procedure
• Now begin the Monte Carlo analysis. Generate i from the
likelihood function L(). Hence i and  are statistically equivalent.

• For example, suppose we have m=5 assets and T=200 observations.

Give a random number generator,  (means, and variance-
covariance matrix), assume a multivariate normal (not necessary but
simplest), and draw five returns 200 times. With the generated data,
calculate the simulated means and variance-covariance matrix, i.
Note that i and  are “statistically equivalent”.

• Using i, calculate the minimum variance portfolio (expected return

Li) and the maximum expected return portfolio (expected return Hi).
Use these to determine the size of the expected return increments.
 The Procedure
• Following our example of K=16, suppose using i, Li=.03
and Hi=.25. Hence, the discrete points would be expected
returns of {.030, .044, .058, ..., .236, .250}.

• Calculate the efficient portfolio weights at each of these

K points. (Solve for the minimum variance weights given
expected returns of .030, ...).

• With this information, we now have ak,i. This is the same

dimension, Kxm.

• Repeat the simulations, so that we have 1,000 ak,is.

 The Procedure
• Average the 1000 ak,is. For each increment, this gives us
average portfolio weights. Call this ak*

• We can redraw the efficient frontier, by using the

original means and variances, i.e.  combined with the
new weights, ak*
 The Procedure
• Note, the new efficient frontier is inside the original frontier.
Why?

• If we look at any particular Monte Carlo draw, say i, we could

draw a frontier (which could be to the right or left of the original
frontier). However, we are keeping track of the weights at the
discrete increments. We average the weights (not the frontiers) -
and then apply these average weights to the original .

• We know that the efficient weights for , are ak. If we apply, ak*,
then we must be to the right of the original frontier. In other
words, if ak is the best, then ak* cannot be the best. However,
importantly, ak* is taking estimation error into account.
 Variations
• Instead of using K increments for the indexation based
on the high and low returns, assume a quadratic utility
function is used.

• A function of the form  = 2 –is minimized. Each

value of ranging from zero to infinity defines a
portfolio on the mean-variance and simulated frontiers.
Decide on the values of the s and then use for the
indexation.
 Does the resampled frontier outperform?
• Based on simulations, yes. Here is the evaluation.

• Given the first draw of i, do another Monte Carlo exercise to

determine the resampled frontier defined by ak,i* (notice difference
in notation).

• Do this extra Monte Carlo on each i - so we will have 1,000

different ak,i*

• Compare the average of ak,i* to the average of the ak,i,(that is,

compare the average of the simulated portfolios based on the
“true” value of i to the average of the portfolios that do not
incorporated any allowance for estimation error). Simply draw
frontiers based on .
 Is Resampling What We Want to Do?
• Resampling provides an improvement over
traditional methods
• However, there are issues:
– Average of maximums is not the maximum
– Hence, allocation will be suboptimal and we should
be able to improve on this work
• New research on the horizon that provides an
alternative.
– See Harvey, Liechty, Liechty and Muller (2010)
article in Quantitative Finance.