Skip to main content

TL;DR

A partial ordering on distributions. X first-order dominates Y if \( F_X(t) \leq F_Y(t) \) for all t (X is always at least as likely to exceed any threshold). Second-order dominance additionally accounts for risk aversion.

By Valenke Exam Prep Team·Last updated 2026-06-03

Stochastic Dominance

A partial ordering on distributions. X first-order dominates Y if \( F_X(t) \leq F_Y(t) \) for all t (X is always at least as likely to exceed any threshold). Second-order dominance additionally accounts for risk aversion.

Why it matters for interviews

Stochastic dominance provides model-free rankings of investments: if X dominates Y, all rational (or risk-averse) investors prefer X. It is a stronger statement than comparing means or Sharpe ratios.

Definition and Mathematical Foundation

A partial ordering on distributions. X first-order dominates Y if \( F_X(t) \leq F_Y(t) \) for all t (X is always at least as likely to exceed any threshold). Second-order dominance additionally accounts for risk aversion.

Application in Quantitative Finance

Stochastic dominance provides model-free rankings of investments: if X dominates Y, all rational (or risk-averse) investors prefer X. It is a stronger statement than comparing means or Sharpe ratios.

Related Terms

Ready to practice for the Quant Trading Interview?

Adaptive practice powered by Item Response Theory targets your weak areas. Start with 3 free sessions.

Start free practice →

Frequently Asked Questions

What is first-order stochastic dominance?
X FSD Y means \( P(X > t) \geq P(Y > t) \) for all t, with strict inequality somewhere. Equivalently, all investors who prefer more to less choose X. It implies \( E[u(X)] \geq E[u(Y)] \) for all increasing u.
What is second-order stochastic dominance?
X SSD Y means \( E[u(X)] \geq E[u(Y)] \) for all increasing concave u (all risk-averse investors prefer X). Equivalently, \( \int_{-\infty}^t F_X(s)ds \leq \int_{-\infty}^t F_Y(s)ds \) for all t.
How is stochastic dominance used in portfolio theory?
If portfolio A dominates portfolio B, B is inefficient -- no rational investor would hold it. This provides a model-free efficiency criterion that does not require specifying a utility function or assuming normality.