Testing behavior of the reversed hazard rate

Abstract The concept of reversed hazard rate of a random life is defined as the ratio between the life probability density to its distribution function. This concept plays a role in analyzing censored data and is applicable in such areas as Forensic Sciences. In this investigation, we address the question of testing the reversed hazard rate where the null is that the reversed hazard rate is an assigned function while the alternative is that it is decreasing but not equal to the null function. Two approaches are discussed: one is based on the empirical distribution function while the other is based on the celebrated kernel methods. The limiting distributions of the test statistics are given and its asymptotic Pittman efficiencies are evaluated for well-known alternatives when the null distribution is exponential. Some other related problems are also addressed.