Summary
Given i.i.d. random vectorsX 1,X 2,...,X n with continuous densityf(x), taking values in a bounded regionG⊂R p (p≧1), let
be their “maximum minimum distance”. Then, under the additional assumptions
the asymptotic theorem
holds. As a statistical application, one readily obtains a test of goodness of fit based onD n . The limiting power of this test with respect to approaching alternatives is derived. Analogous results apply to the case of random vectors on the surface of a sphere or even more general differentiable structures.
Similar content being viewed by others
Literaturverzeichnis
Galambos, J.: The asymptotic theory of extreme order statistics. New York 1978.
Levy, P.: Sur la division d'un segment par des points choisis au hazard. C.R. Acad. Sci. Paris208, 1950, 147–148.
Weiss, L.: A test of fit based on the largest sample spacing. J. Soc. Indust. Appl. Math.8, 1960, 295–299.
Author information
Authors and Affiliations
Additional information
Diese Arbeit stellt eine gekürzte Fassung der von der Fakultät für Mathematik und Naturwissenschaften der Universität Hannover angenommenen Dissertation des Verfassers dar.
Rights and permissions
About this article
Cite this article
Henze, N. Ein asymptotischer Satz über den maximalen Minimalabstand von unabhängigen Zufallsvektoren mit Anwendung auf einen Anpassungstest im Rp und auf der Kugel. Metrika 30, 245–259 (1983). https://doi.org/10.1007/BF02056931
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1007/BF02056931