Zero to One: Notes on Startups, or How to Build the Future · chapter 7 · id zero-to-one-c7-09-modern-portfolio-theory-markow
“Modern Portfolio Theory (Markowitz) is wrong for startups because MPT assumes normally distributed returns with finite variance, but VC returns follow a power law with unbounded mean.”
holdsconfidence: high⚠ extracted by pipeline, re-audit pending
Receipts
AngelList -- Empirical VC Power-Law Datasource alive
VC return multiples follow power-law with alpha=2.42. After 5 years, winning seed-stage investments draw from alpha < 2 (unbounded mean) -- fundamentally incompatible with MPT's finite-variance assumption.
Post-Modern Portfolio Theory -- Wikipediasource alive
PMPT was created to address MPT's limitations by using downside risk and accommodating non-normal distributions -- implicitly acknowledging MPT's normal-distribution assumption is insufficient.
This claim is a stable, citable object. If you can falsify a verdict, tell us — corrections are loud here.