News for hackers. Stuff that matters.
Re:Annual Returns on Stock, T.Bonds and T.Bills: 1928 – Current by blevin on Wednesday December 18, 2019 @03:43PM (#21829216)
The arithmetic vs. geometric mean distinction is a good one to note. Since you mention risk-adjusted return, do you favor any particular approaches to optimization? ReSolve makes a pretty strong case for numerical optimization, summarized by this decision tree based on prior beliefs:

https://twitter.com/gestaltu/status/1044977487556595714

Re:Annual Returns on Stock, T.Bonds and T.Bills: 1928 – Current by darawk on Wednesday December 18, 2019 @06:34PM (#21830625)
I generally prefer using something like scipy.minimize to maximize the expected sharpe ratio with returns de-magnified, which causes the optimization to be closer to a minimum variance portfolio.