-
Fakultät Statistik
-
Research
-
Public Lectures
Statistical Colloquium
a standard normal with large mixture weight and a point mass in μ far a way from 0. The expectation then lies between 0 and μ , failing to capture neither the location of the standard normal nor the location [...] function D_P : R^d → [0, D_max]. It measures how deep a point x lies within P. A large value of D_p(x) close to D_max = sup_x∈R^d D_P(x) indicates that x is near to the center whereas D_P(x) ≈ 0 corresponds to [...] it. Define for any α ∈ (0, D_max), the α -slice of T(P) by T( α , P) = T(P_ α ), where P_ α denotes the distribution of X conditional on D_P(X) = α . The function T (·, P): (0, D_max) → R^k : α → T_ α …
