Beyond Monte Carlo: A Replacement for a Misunderstood Technology

From Planipedia

Jump to: navigation, search

Author: Shawn Brayman

Publication Journal of Financial Planning, 2007-10

Abstract

Section One demonstrates that MCS returns the same results as an algorithmic test. It summarizes deficiencies and misunderstandings in the application of MCS in financial planning tools, including:

  • MCS is used to model multiple asset classes despite research indicating this is inaccurate.
  • Entering comparable assumptions in MCS as in algorithmic solutions is almost impossible.
  • Variations attributed to MCS are due to differences in underlying assumptions.
  • Monte Carlo does not test the order of good or bad years and timing of the client’s goals as advertised.
  • As utilized, Monte Carlo does not test higher and lower rates of returns.
  • Randomizing life expectancy does not effectively test for longevity.
  • Randomizing inflation resulted in no variation from the single point assumption.

Section Two summarizes the creation of an algorithmic model using multivariate histograms that allowed for the calculation of the same partial probabilities as generated with MCS. Its benefits were:

  • A dozen iterations calculated the same probability distribution as MCS does using 10,000 simulations.
  • There is no possibility for mismatched assumptions.
  • A matrix illustrating multiple success factors – not just a single success factor.
  • The methodology requires no alteration to a sophisticated algorithmic model.
Retrieved from "http://www.planipedia.org/index.php/Beyond_Monte_Carlo:_A_Replacement_for_a_Misunderstood_Technology"
Personal tools