Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
1148811 | Journal of Statistical Planning and Inference | 2012 | 8 Pages |
Abstract
In this paper, first we consider the problem of testing that two unknown distributions are identical against the alternative that one is more IFRA than the other and propose a new test that is asymptotically normal and consistent. Next, we prove that beta family of distributions is ordered according to more IFRA ordering. The empirical power of the proposed test is simulated for some specific families of distributions like beta, gamma and Weibull that are ordered with respect to more IFRA order. Finally, we apply our test to some real data sets in the context of reliability.
Related Topics
Physical Sciences and Engineering
Mathematics
Applied Mathematics
Authors
Muhyiddin Izadi, Baha-Eldin Khaledi,