Tail asymptotic results for elliptical distributions (Q938049): Difference between revisions

Let \((S_1,S_2)\) be a bivariate spherical random vector with associate random radius \(R=\sqrt {S_1^2+S_2^2}\). Let \((X,Y)\) be a bivariate elliptical random vector with the stochastic representation \[ (X,Y) \overset {d}= (S_1,\rho S_1+\sqrt{1-\rho^2}S_2), \quad \rho \in [0,1). \] Assuming that the distribution function of the radius \(R\) is in the Gumbel max-domain of attraction, the author obtains a second order asymptotic expansion of the joint survival probability \(\mathbf P\{X>x,Y>y\}\) and the conditional probability \(\mathbf P\{X>x\mid Y>y\}\) for \(x,y\) large. Illustrating examples are also given.