Standard

Tests of exponentiality based on Arnold-Villasenor characterization, and their efficiencies. / Jovanovi, M.; Milo evi, B.; Nikitin, Ya.Yu.; Obradovi, M.; Volkova, K.Y.

в: Computational Statistics and Data Analysis, Том 90, 2015, стр. 100-113.

Результаты исследований: Научные публикации в периодических изданияхстатьяРецензирование

Harvard

APA

Vancouver

Author

Jovanovi, M. ; Milo evi, B. ; Nikitin, Ya.Yu. ; Obradovi, M. ; Volkova, K.Y. / Tests of exponentiality based on Arnold-Villasenor characterization, and their efficiencies. в: Computational Statistics and Data Analysis. 2015 ; Том 90. стр. 100-113.

BibTeX

@article{995a947464bc4db0bc90283f065e4e2b,
title = "Tests of exponentiality based on Arnold-Villasenor characterization, and their efficiencies",
abstract = "Two families of scale-free exponentiality tests based on the recent characterization of exponentiality by Arnold and Villasenor are proposed. The test statistics are constructed using suitable functionals of U-empirical distribution functions. The family of integral statistics can be reduced to V- or U-statistics with relatively simple non-degenerate kernels. They are asymptotically normal and have reasonably high local Bahadur efficiency under common alternatives. This efficiency is compared with simulated powers of new tests. On the other hand, the Kolmogorov type tests demonstrate very low local Bahadur efficiency and rather moderate power for common alternatives, and can hardly be recommended to practitioners.The conditions of local asymptotic optimality of new tests are also explored and for both families special {\textquoteleft}{\textquoteleft}most favourable{\textquoteright}{\textquoteright} alternatives for which the tests are fully efficient are described.",
keywords = "exponential distribution, characterization, U-empirical measure, Bahadur efficiency, large deviations",
author = "M. Jovanovi and {Milo evi}, B. and Ya.Yu. Nikitin and M. Obradovi and K.Y. Volkova",
year = "2015",
doi = "10.1016/j.csda.2015.03.019",
language = "English",
volume = "90",
pages = "100--113",
journal = "Computational Statistics and Data Analysis",
issn = "0167-9473",
publisher = "Elsevier",

}

RIS

TY - JOUR

T1 - Tests of exponentiality based on Arnold-Villasenor characterization, and their efficiencies

AU - Jovanovi, M.

AU - Milo evi, B.

AU - Nikitin, Ya.Yu.

AU - Obradovi, M.

AU - Volkova, K.Y.

PY - 2015

Y1 - 2015

N2 - Two families of scale-free exponentiality tests based on the recent characterization of exponentiality by Arnold and Villasenor are proposed. The test statistics are constructed using suitable functionals of U-empirical distribution functions. The family of integral statistics can be reduced to V- or U-statistics with relatively simple non-degenerate kernels. They are asymptotically normal and have reasonably high local Bahadur efficiency under common alternatives. This efficiency is compared with simulated powers of new tests. On the other hand, the Kolmogorov type tests demonstrate very low local Bahadur efficiency and rather moderate power for common alternatives, and can hardly be recommended to practitioners.The conditions of local asymptotic optimality of new tests are also explored and for both families special ‘‘most favourable’’ alternatives for which the tests are fully efficient are described.

AB - Two families of scale-free exponentiality tests based on the recent characterization of exponentiality by Arnold and Villasenor are proposed. The test statistics are constructed using suitable functionals of U-empirical distribution functions. The family of integral statistics can be reduced to V- or U-statistics with relatively simple non-degenerate kernels. They are asymptotically normal and have reasonably high local Bahadur efficiency under common alternatives. This efficiency is compared with simulated powers of new tests. On the other hand, the Kolmogorov type tests demonstrate very low local Bahadur efficiency and rather moderate power for common alternatives, and can hardly be recommended to practitioners.The conditions of local asymptotic optimality of new tests are also explored and for both families special ‘‘most favourable’’ alternatives for which the tests are fully efficient are described.

KW - exponential distribution

KW - characterization

KW - U-empirical measure

KW - Bahadur efficiency

KW - large deviations

U2 - 10.1016/j.csda.2015.03.019

DO - 10.1016/j.csda.2015.03.019

M3 - Article

VL - 90

SP - 100

EP - 113

JO - Computational Statistics and Data Analysis

JF - Computational Statistics and Data Analysis

SN - 0167-9473

ER -

ID: 3933667