We consider here the general class of distributions proposed by Sankaran and Gupta (2005) by zeroing in on two measures of reliability, R(t) = P(X > t) and P = P(X > Y). Thereafter, we develop point estimation for R(t) and ‘P’ and develop uniformly minimum variance unbiased estimators (UMVUES). Then we derive testing procedures for the hypotheses related to different parametric functions. Finally, we compare the results using the Monte Carlo simulation method. Using real data set, we illustrate the procedure clearly.
5 January 2018 in Communications in Statistics - Theory and Methods
This paper presents the extension of the inferences on the stress-strength reliability in more than two states to the system depending on the ratio of the strength and stress values when the stress and strength follow independent exponential distributions. The main objective of present paper is to consider different method of estimation, under Type II censoring, for the stress-strength models and to compare them, in more than two states, to the system depending on the ratio of the strength and stress values, when the stress and strength follow independent Weibull distributions, sharing the common shape parameter α.
We consider here the generalized inverted scale family of distributions proposed by Potdar and Shirke [Inference for the parameters of generalized inverted family of distributions. ProbStat Forum. 2013;06:18-28] by zeroing in on two measures of reliability, R(t) = P(X > t) and P = P(X > t), based on Type II censoring and the sampling scheme of Bartholomew [The sampling distribution of an estimate arising in life testing. Technometrics. 1963;5:361-374]. Thereafter, we develop point estimators of powers of alpha, R(t) and P; and develop uniformly minimum variance unbiased (UMVU) estimators and maximum likelihood (ML) estimators. A new technique of obtaining these estimators is introduced. Exact confidence intervals for the parameter alpha, R(t) and P are also constructed based on Type II censoring. Then we derive testing procedures for the hypotheses related to different parametric functions. Finally, we compare these results using the Monte Carlo simulation method.
1 June 2017 in Statistics, Optimization & Information Computing