A1668
Title: A family of nonparametric tests for DMTTF alternatives based on moment inequality
Authors: Shyamal Ghosh - Indian Institute of Science Education and Research Thiruvananthapuram (India) [presenting]
Abstract: Based on a moment inequality, a family of test statistics for testing exponentiality against DMTTF alternatives is proposed. The asymptotic distribution of the test statistics is derived under the null and alternative hypothesis, and the consistency of the test is shown by exploiting the U-statistics theory. Comparisons with competing tests are made in terms of Pitman asymptotic relative efficiency (PARE). Additionally, an adapted version of the test under random censorship is explored. The performance of the proposed test has been accessed by means of a simulation study and through application to some real-life data sets.
