0
$\begingroup$

Does "standard Markowitz approach" include only mean-variance approach or does it also include other approach such as minimum-variance approach?

$\endgroup$
  • 1
    $\begingroup$ The standard Markowitz approach (known as modern portfolio theory (MPT)) indeed deals with the mean-variance optimisation as estabilished by Markowitz (1952). What else should it include? $\endgroup$ – KeSchn Nov 22 '19 at 20:18
6
$\begingroup$

The Markowitz mean-variance model is the basis for many extensions and portfolio solutions that have been discovered over the years:

The standard model (Markowitz, 1952, 1959) originally only considered:

  • Constrained model where short sales are forbidden
  • Only risky assets considered for investment (no risk-free asset)

Scenarios that the mean-variance model can be extended to include one, or a combination of, the following:

  • Unconstrained model where short sales are allowed (Black, 1972)
  • Inclusion of a risk-free asset (Tobin, 1958, 1965)
  • Dynamic model that looks at multi-period rebalancing of portfolios
  • Inclusion of transaction costs

To deal with estimation error in the mean-variance model, the following techniques are popular:

  • Resampled efficient frontier (Michaud and Michaud, 1998)
  • Covariance shrinkage (Ledoit-Wolf, 2003, 2004 and Jagannathan-Ma, 2003)
  • Robust portfolio optimization that uses uncertainty of inputs (Goldfarb and Iyengar, 2003)
  • Portfolio regularization (de Miguel et al, 2009 and Brodie et al, 2009)
  • replacing variance with Value-at-risk: these are mean-VaR and mean-CVaR models

Classical portfolios that can be solved using different objective functions (equations) for many combinations of the scenarios above, including obviously the standard model, are:

  • the Global Minimum Variance portfolio (GMV)
  • the Tangency portfolio that has the highest reward-to-risk Sharpe ratio
  • all other frontier portfolios that lie on the efficient frontier

Portfolio risk optimization, a subfield of modern portfolio theory, further revealed equations for the mean-variance model that use different objective functions to provide:

  • the Maximum Diversification portfolio
  • the Risk Parity portfolio
  • the Volatility Targeting portfolio

while common benchmarks (for comparing new strategies with) that don't require optimization but have profound performance in mean-variance space are:

  • the equally-weighted portfolio that weights each risky asset $1/N$
  • the inverse-volatility weighted portfolio

Common active strategies that modify the optimization problem are:

  • the Treynor-Black model (1973)
  • the Black-Litterman model (1992)

Although all of the above tend to focus on the optimization approach, there are alternative approaches to obtain equivalent solutions to the optimization approach:

  • the optimization approach
  • analytical closed-form solutions (Merton, 1972)
  • the regression approach (Britten-Jones, 1999 and Kempf and Memmel, 2006)
  • system of linear equations
$\endgroup$
  • $\begingroup$ Thank you for your answer. In a academic paper, would it be appropriate to refer to "minimum variance approach" as being included in "mean-variance approach"? $\endgroup$ – Aqqqq Nov 24 '19 at 15:07
  • 1
    $\begingroup$ An efficient portfolio is one that has the lowest portfolio risk for a given level of expected return. In the mean-variance model, all portfolios, including the GMV, tangency and other portfolios along the efficient frontier have the lowest variance for their respective levels of expected return. Therefore, mean-variance speaks to the overall trade-off the model tries to affect, by defining portfolios by their mean and variance, while minimum variance is an optimal criterion of this trade-off. no reason to separate these concepts into approaches because they are both inherent $\endgroup$ – develarist Nov 24 '19 at 15:27

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.