Bahadur-Kiefer Approximation for Spatial Quantiles
Let F be the uniform distribution on [0,1], (X 1, …,X n) be a sample from the distribution F, and F n be the empirical distribution based on this sample. Let F -1 be the quantile function of F (which, of course, coincides with F in the case of uniform distribution F) and let F n -1 be the empirical quantile function. Let us define r n(t):= F n -1(t)- F n-1(t) + F n(t)- F(t),t ∈ [0,1]. Bahadur (1966) and Kiefer (1967), 1970) (see also Shorack and Wellner (1986) for further references) investigated the asymptotic behavior of the process r n. It appeared that for any t ∈ (0,1) n 3/4 r n(t) converges weakly to a certain limit distribution.
KeywordsUnit Ball Oscillation Behavior Empirical Process Iterate Logarithm Quantile Function
Unable to display preview. Download preview PDF.
- Arcones, M.A. and Mason, D.M. (1992) A general approach to Bahadur-Kiefer representations for M—estimators. Preprint.Google Scholar
- Dudley, R.M. and Koltchinskii, V.I. (1992) The spatial quantiles. Preprint.Google Scholar
- Gine, E. and Zinn, J. (1986) Lectures on the central limit theorem for empirical processes. Lect. Notes in Math. 1221, 50–112. Springer, New York.Google Scholar
- Kiefer, J. (1970) Deviations between the sample quantile process and the sample d.f. In: Nonparametric Techniques in Statistical Inference (M.L. Puri, Ed.) 299–319. Cambridge Univ. Press.Google Scholar
- Koltchinskii, V. (1993) Nonlinear transformations of empirical processes: functional inverses and Bahadur-Kiefer representations. Submitted to the Proc. of the 6-th International Vilnius Conference on Probability Theory and Mathematical Statistics.Google Scholar
- Koltchinskii, V. and Dudley, R.M. (1992) Differentiability of inverse operators and asymptotic properties of inverse functions (preprint).Google Scholar