Let x and y follow a normal bivariate probability function with means $\bar X, \bar Y$, standard deviations σ1, σ2, respectively, r the coefficient of correlation, and $\rho_1 = \bar X/\sigma_1, ...

This is a preview. Log in through your library . Abstract Jensen gave a lower bound to Eρ(T), where ρ is a convex function of the random vector T. Madansky has obtained an upper bound via the theory ...