The Korean Journal of Applied Statistics (응용통계연구)

The Korean Statistical Society (한국통계학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on Test for NBU Class

NBU CLASS에 관한 검정법 연구

  • 김환중 (우석대학교 전산정보학부 전산통계전공)
  • Published : 2003.09.01
Download PDF
⟨ Previous Next ⟩

Abstract

In this thesis, we propose a test statistic for testing exponentiality against NBU alternatives. Our test statistics is based on a linear function of the order statistics and is readily applied in the case of small sample as well as large sample. The exact and asymptotic distribution of the test statistics is derived and asymptotic efficiencies are studied. Our new test is easier to compute and performs better for several alternatives than test of Hollander and Proschan(1972).

본 논문에서는 신뢰성분석에서 고려되는 NBU class에 관한 새로운 검정법을 제안하였다. 제안된 검정통계량은 순서통계량의 선형함수의 형태로 이루어져있고 대표본 뿐만 아니라 소표본에서도 쉽게 적용될 수 있음을 보였다. 소표본인 경우에는 Monte Carlo 시뮬레이션을 통하여 제안된 검정통계량의 검정력을, 대표본인 경우에는 점근상대효율을 Hollander와 Proschan(1972)의 검정통계량과 비교하여 보았으며 검정통계량의 일치성도 보였다.

Keywords

References

  1. 박사논문, 서울대학교 A Study on Tests for Exponentiality against Decreasing Mean Residual Life Alternatives 김환중
  2. Statistical Theory of Reliability and Life Testing: Probability Models Barlow,R.E.;Proschan,F.
  3. Ann. Math. Statist. v.25 Some theorems on quadratic forms applied in the study of analysis of variance problems, I. Effect of inequality of variance in the one-way classification Box,G.E.P. https://doi.org/10.1214/aoms/1177728786
  4. Ph.D. dissertation, The George Washington University Some contributions to the theory of restricted classes of distributions with applications to reliability theory Haines,A.
  5. The Annals of Mathematical Statistics v.43 Testing whether New is Better than Used Hollander;Proschan https://doi.org/10.1214/aoms/1177692466
  6. Biometrika v.66 Null distribution of the Hollander and Proschan statistic for decreasing mean residual life Langenberg,P.;Srinivasan,R. https://doi.org/10.1093/biomet/66.3.679
  7. The Annals of Statistics v.2 Linear functions of order statistics with smooth weight function Stigler,S.M. https://doi.org/10.1214/aos/1176342756