Monte Carlo Simulation

Combining Portfolio Asset Classes

By Dr. David Edward Marcinko; MBA, CMP™

Publisher-in-Chief 

dem2

Combining the disparate information of a physician’s investment portfolio, into a workable asset allocation strategy, is as much art as it is science; perhaps even more so.  

Most doctors, investors or endowment fund managers will use a combination of quantitative and qualitative analyses to develop their allocations.  

The quantitative portion of the analyses generally uses a variety of statistical techniques to develop a top-down approach to the general allocation.  

After developing a general sense of their desired range of returns, many doctors and investors will then use one of several “optimizer” techniques to assist in constructing such an allocation.  

Commonly used optimization techniques include Mean Portfolio Variance Optimization (MPVO) – discussed elsewhere in the Executive Post – and Monte Carlo Simulation (MCS). 

Monte Carlo Simulation [MCS] 

Named after Monte Carlo, Monaco, which is famous for its games of chance, MCS is a technique that randomly changes a portfolio variable over numerous iterations in order to simulate an outcome and develop a probability forecast of successfully achieving an outcome. 

In institutional and individual portfolio management, MCS is used to demonstrate the probability of “success” as defined by achieving the endowment’s asset growth and payout goals. 

In other words, MCS can provide the physician, investor or endowment fund manager with a comfort level that a given payout policy and asset allocation success will not deplete the real value of the endowment. 

Beware the Divorce from Judgment 

Nevertheless, the problem with many quantitative tools is the divorce of judgment from their use. And, although useful, both MPVO and MCS have limitations that make it so they should not supplant physician insight, investor experience, or portfolio manager judgment.  

For example, MPVO generates an efficient frontier by relying on several inputs, like expected rate-of-return, expected volatility and correlation coefficients. These variables are commonly input using historical measures as proxies for estimated future performance; which is not ascertainable.  

Assessment 

These facts alone may present a variety of problems:  

  1. First, the MPVO will generally assume that returns are normally distributed and that this distribution is stationary. As such, asset classes with high historical returns are assumed to have high future returns; and this may or may not be true.  
  2. Second, an MPVO optimizer is not generally time sensitive. In other words, the optimizer may ignore current environmental conditions that would cause a secular shift in a given asset class returns.  
  3. Finally, an MPVO optimizer may be subject to selection bias for certain asset classes. For example, private equity firms that fail, as was prominently noted in 2007 and 2008, will no longer report results and will be eliminated from the index used to provide the optimizer’s historical data-base.  

Conclusion 

And so, do you consider MPVO and Monte Carlo Simulation [MCS] when constructing your own investment portfolio? Why or why not? 

Speaker: If you need a moderator or a speaker for an upcoming event, Dr. David Edward Marcinko; MBA – Editor and Publisher-in-Chief – is available for speaking engagements. Contact him at: MarcinkoAdvisors@msn.com

Your thoughts are appreciated.

BUSINESS, FINANCE AND INSURANCE TEXTS FOR DOCTORS:

1 – https://lnkd.in/ebWtzGg

2 – https://lnkd.in/ezkQMfR

3 – https://lnkd.in/ewJPTJs

THANK YOU

 

Leave a Reply

Please log in using one of these methods to post your comment:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

%d bloggers like this: