E. O. Kantonistova, I. V. Rodionov, “Analogues of classical goodness-of-fit tests for distribution tails”, Dokl. RAN. Math. Inf. Proc. Upr., 2021, Volume 496,Pages <nobr>44

This article is cited in 2 papers

MATHEMATICS

Analogues of classical goodness-of-fit tests for distribution tails

E. O. Kantonistova^a, I. V. Rodionov^b

^a National Research University "Higher School of Economics", Moscow, Russian Federation
^b V. A. Trapeznikov Institute of Control Sciences of Russian Academy of Sciences, Moscow, Russian Federation

Abstract: We propose analogues of the classical Kolmogorov–Smirnov and omega-squared tests for goodness-of-fit testing of distribution tails. The consistency of the proposed tests on wide alternatives is proved both in the framework of censored data statistics and in the framework of statistics of extremes.

Keywords: distribution tail, goodness-of-fit tests, type-I censoring, type-II censoring, statistics of extremes, Kolmogoro–Smirnov test, omega-squared test.

UDC: 519.234.3

Presented: K. V. Rudakov
Received: 24.10.2020
Revised: 24.10.2020
Accepted: 28.10.2020

DOI: 10.31857/S2686954321010069