On the uniqueness of S-functionals and M-functionals under nonelliptical distributions
نویسندگان
چکیده
منابع مشابه
Specifying Prior Distributions of Functionals
Many Bayesian analyses rely heavily on Markov Chain Monte Carlo (MCMC) techniques. MCMC techniques work fastest when the prior distribution of the parameters is chosen conveniently , usually a conjugate prior. However, this is sometimes at odds with the prior desired by the investigator. We describe two motivating examples where nonconjugate priors are preferred. One is a Dirichlet Process wher...
متن کاملUniqueness properties of functionals with Lipschitzian derivative
Let X be a real Hilbert space and J a C functional on X . For x0 ∈ X , r > 0, set S(x0, r) = {x ∈ X : ‖x− x0‖ = r}. Also on the basis of the beautiful theory developed and applied by Schechter and Tintarev in [2], [3], [4] and [5], it is of particular interest to know when the restriction of J to S(0, r) has a unique maximum. The aim of the present paper is to offer a contribution along this di...
متن کاملAlmost multiplicative linear functionals and approximate spectrum
We define a new type of spectrum, called δ-approximate spectrum, of an element a in a complex unital Banach algebra A and show that the δ-approximate spectrum σ_δ (a) of a is compact. The relation between the δ-approximate spectrum and the usual spectrum is investigated. Also an analogue of the classical Gleason-Kahane-Zelazko theorem is established: For each ε>0, there is δ>0 such that if ϕ is...
متن کاملOn Liapunov-Krasovskii functionals under Carathéodory conditions
In this paper, a basic property that a Liapunov-Krasovskii functional must have when used for studying the stability of time delay systems under Carath¶eodory conditions is studied. This property concerns the equality, almost everywhere, of the upper right-hand Dini derivative of the Liapunov-Krasovskii functional evaluated at the solution, and of the Liapunov-Krasovskii derivative (computed by...
متن کاملInference on Functionals under First Order Degeneracy
This paper presents an unified second order asymptotic framework for conducting inference on parameters of the form φ(θ0), where θ0 is unknown but can be estimated by θ̂n, and φ is a known map that admits null first order derivative at θ0. The Delta method implies that the asymptotic distribution of the plug-in estimator φ(θ̂n) is zero, which creates substantial challenges for inferential purpose...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: The Annals of Statistics
سال: 2000
ISSN: 0090-5364
DOI: 10.1214/aos/1015956714