Home           Contact us           FAQs           
 
   Journal Page   |   Aims & Scope   |   Author Guideline   |   Editorial Board   |   Search
    Abstract
2009 (Vol. 1, Issue: 1)
Article Information:

On Tests for Detecting More Nbu-ness Property of Life Distributions

Parameshwar V. Pandit and Nagaraj V. Gudaganavar
Corresponding Author:  Parameshwar V. Pandit 

Key words:  NBU, NBU-t0, Positive ageing, Pitman ARE, Two-sample test, U-statistic,
Vol. 1 , (1): Page No: 9-13
Submitted Accepted Published
2009 June, 08 2009 August, 05
Abstract:

A sim ple test procedure is proposed for testing the null hypothesis that two life distributions are equal against the alternative that one is more new better than used than the other. The proposed test is based on a sub sample of size two from each sample. The properties of the test procedure such as asymptotic normality, consistency etc., are established. The performance of the test procedure is evaluated by finding Pitman asymptotic relative efficiencies(ARE) for different distributions in comparison with the test procedure due to Hollander and Proschan(1986). A simple two-sam ple test statistic for testing the null hypothesis of equality of two life distributions against the alternative that one life distribution possesses more of New better than used property than does another life distribution at a specified age. The newly proposed test is based on a U-statistic whose kernel is based on minima of a sub sample of size two. The asymptotic normality of the proposed test is established. The Pitman ARE of the proposed test relative to the test proposed by Lim, Kim and Park(2005) are computed by considering the alternative distributions with location and scale parameters. The Pitman AREs show that the performance of the tests proposed here is better as compared to its competitors.
Abstract PDF HTML
  Cite this Reference:
Parameshwar V. Pandit and Nagaraj V. Gudaganavar, 2009. On Tests for Detecting More Nbu-ness Property of Life Distributions.  Research Journal of Mathematics and Statistics, 1(1): Page No: 9-13.
    Advertise with us
 
ISSN (Online):  2040-7505
ISSN (Print):   2042-2024
Submit Manuscript
   Current Information
   Sales & Services
   Contact Information
  Executive Managing Editor
  Email: admin@maxwellsci.com
  Publishing Editor
  Email: support@maxwellsci.com
  Account Manager
  Email: faisalm@maxwellsci.com
  Journal Editor
  Email: admin@maxwellsci.com
  Press Department
  Email: press@maxwellsci.com
Home  |  Contact us  |  About us  |  Privacy Policy
Copyright © 2009. MAXWELL Science Publication, a division of MAXWELLl Scientific Organization. All rights reserved