Portfolio Resampling and Parameter Uncertainty in Mean-Variance Optimization
Summary
The discussion distinguishes uncertainty in portfolio allocations from uncertainty in the inputs used to construct them. Mean-variance optimization can produce a precise allocation from estimated returns and covariances even when those parameters are poorly known. Historical estimates may not describe future relationships, so treating the optimizer’s output as uniquely reliable can create overconfidence.
Resampling can first serve as a way to show how allocations vary when inputs are perturbed, giving investors a range of plausible solutions rather than a single result. A more principled interpretation models parameter uncertainty explicitly, using a Bayesian framework and Monte Carlo draws to find a compromise allocation. The document does not specify a particular prior, sampling scheme, or objective function for that compromise. A second answer describes simulation more broadly as a way to examine outcome probabilities under chosen distributions, but does not resolve exactly what utility a resampled portfolio optimizes.
Key ideas
- Mean-variance allocations can be highly sensitive to uncertain return and covariance estimates.
- Resampling can illustrate how portfolio weights change when estimated inputs vary.
- A Bayesian treatment models parameter uncertainty explicitly and can use Monte Carlo sampling to form a compromise allocation.
- The document does not define a single universal objective optimized by every resampling procedure.
Tags
Full text
# What's the point of resampling? # What's the point of resampling? Resampling is a popular method for portfolio optimization. We repeatedly draw samples from a distribution, compute the optimal mean-variance portfolio and finally average over all allocations. However, from a mathematical point of view, I do not understand why we would gain anything from this procedure. Have we not put all of the uncertainty into our distribution already? Why would we distinguish between the risk of bad allocations and the risk of bad estimation? Perhaps more rigorously: If the mean-variance portfolio maximizes the utility of an investor with a risk aversion of $\lambda$, then what does a resampled portfolio optimize? ## Answer by nbbo2 (score 7) https://quant.stackexchange.com/a/70626 The "estimation problem" in Portfolio Optimization is a serious one. The parameters (returns and covariances) are known very imprecisely. For example the covariance between stocks and bonds for the next 10 years is going to be different from the one that we measure today using data from the past 10 years. And this is true even if the structure of the economy does not change, which is unlikely (think of the current inflation scare). The uncertainty in the parameters is substantial and calls into question the whole procedure. According to Richard Michaud (personal communication) the resampling procedure initially was just an attempt to illustrate the issue: by solving the problem several time with randomly varied inputs and comparing the solutions one can get a sense of how far from optimal the allocations will be ex-post. The client can be shown a few alternatives rather than a single one, avoiding overconfidence in a single result. In a second step Michaud realized that the proper approach to a problem where we do not know the parameters would be a Bayesian one, and he proposed modeling the uncertainty explicitly and using a Monte Carlo approach to find a compromisec solution. This is how resampling is understood today. ## Answer by Ralph Winters (score 0) https://quant.stackexchange.com/a/70627 True, Mean Variance gives you a mathematical solutions. But resampling, especially for Monte Carlo simulations allows you to specify any kind of distribution you want, and repeat for a large number of trials to see what an expected outcome would be. An important part of Monte Carlo simulation is computing a probability of success or achieving a specific outcome over a longer time frame. Both the mathematical and simulation methods are both useful. It's not that one is better than the other.
Shown in full with attribution under the source's licence. Licence: CC BY-SA 4.0 (Stack Exchange)
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.