Percentiles of $Z=\max(X,Y)$, where X and Y are correlated normal random variables

by Dimitriy V. Masterov   Last Updated January 12, 2018 20:19 PM

Suppose $X \sim N(\mu_x,\sigma_x^2)$, $Y \sim N(\mu_y,\sigma_y^2)$, and $Corr(X,Y)=\rho$. I am interested in calculating percentiles of $Z = \max(X,Y)$.

I know how to find the pdf, mean, and variance of $Z$, but I am having trouble solving or finding an approximation for the percentiles. Has this been worked out somewhere in the literature?

Related Questions

Using Chebyshev's inequality to obtain lower bounds

Updated January 24, 2018 17:19 PM

Finding a hidden "heavy" subset of random variables

Updated August 17, 2015 17:08 PM