Skip to content
Get started

Kendall's tau of a bivariate normal

(X,Y)(X,Y) is bivariate normal with correlation 0.80.8. Draw two independent pairs (X1,Y1)(X_1,Y_1) and (X2,Y2)(X_2,Y_2) from this distribution. They are concordant if (X1−X2)(Y1−Y2)>0(X_1-X_2)(Y_1-Y_2)>0 and discordant if it is <0<0. Kendall's tau is τ=P(concordant)−P(discordant)\tau=P(\text{concordant})-P(\text{discordant}). What is τ\tau? Give a decimal to four places.

Show hints (2)+
  1. The differences (X1−X2, Y1−Y2)(X_1-X_2,\,Y_1-Y_2) are bivariate normal - with what correlation?
  2. Write the pair as a linear image of a rotation-invariant normal pair; each sign condition becomes a half-plane, and the quadrant becomes a wedge whose angle depends on ρ\rho.

Answer

Reveal answer →

0.5903 (± 0.0005)

Create a free account to see the full worked solution and track your progress.

Interview format: Hedge Fund Quant, Systematic & Data-Driven Trading

Related questions