Asymptotic expansion of the joint distribution of sample mean vector and sample covariance matrix from an elliptical population (Q1370803): Difference between revisions

Let \(\overline X\) and \(S\) be the sample mean vector and the sample covariance matrix based on the i.i.d. sample of size \(n\) from a \(p\) dimensional probability distribution with mean vector \(\mu\) and covariance matrix \(\Omega\). Let \[ Z= n^{1/2} \Omega^{-1/2} (S-\Omega) \Omega^{-1/2} \quad \text{and} \quad Y=n^{1/2} \Omega^{-1/2} (\overline X-\mu). \tag{1} \] Then the limiting distribution of \(Z\) and \(Y\) is mutually independent normal. The author [ibid. 24, No. 2, 257-298 (1994; Zbl 0806.62048)] derived an asymptotic expansion for the joint distribution of \(Z\) and \(Y\) up to the order of \(n^{-1/2}\) when the underlying distribution is an elliptical distribution. Unfortunately, the result included some miscalculations. The purposes of this paper are to correct them and to extend the result to an asymptotic expansion up to the order \(n^{-1}\).