Mean-Variance Optimization Is Crazy?

“Dominant U.S. Stock Market?” summarizes a paper that (1) examines whether a 60%+ allocation to the U.S. in the MSCI All Country World Index (ACWI) is crazy high and (2) decides maybe not. In “How Much Is Too Much? Part 2: Why 60% in US Equities Might Be Just as Crazy as It Sounds”, the same authors reconsider by testing key assumptions in Part 1. Specifically, they quantify impacts of uncertainty in mean-variance optimization (MVO) via sensitivity analysis/simulations and look at alternative ways to construct long-term equity portfolios. Using monthly returns for U.S., Europe ex UK, UK, Japan, Pacific ex Japan and Emerging Markets in U.S. dollars during December 1987 through May 2025, they find that:

(more…)