Differentiability of t-functionals of location and scatter
R. M. Dudley, Sergiy Sidenko, Zuoqin Wang
The Annals of Statistics · 2009 · Volume 37 · Issue 2
Abstract
The paper aims at finding widely and smoothly defined nonparametric location and scatter functionals. As a convenient vehicle, maximum likelihood estimation of the location vector μ and scatter matrix Σ of an elliptically symmetric t distribution on ℝd with degrees of freedom ν>1 extends to an M-functional defined on all probability distributions P in a weakly open, weakly dense domain U. Here U consists of P putting not too much mass in hyperplanes of dimension <d, as shown for empirical measures by Kent and Tyler [Ann. Statist. 19 (1991) 2102–2119]. It will be seen here that (μ, Σ) is analytic on U for the bounded Lipschitz norm, or for d=1 for the sup norm on distribution functions. For k=1, 2, …, and other norms, depending on k and more directly adapted to t functionals, one has continuous differentiability of order k, allowing the delta-method to be applied to (μ, Σ) for any P in U, which can be arbitrarily heavy-tailed. These results imply asymptotic normality of the corresponding M-estimators (μn, Σn). In dimension d=1 only, the tν functional (μ, σ) extends to be defined and weakly continuous at all P.
Keywords
62G05, 62G35, 62GH20, Affinely equivariant, Fréchet differentiable, weakly continuous
Enable JavaScript for citation tools and additional paper interactions.