Premium
Robust inference for one‐shot device testing data under exponential lifetime model with multiple stresses
Author(s) -
Balakrishnan Narayanaswamy,
Castilla Elena,
Martín Nirian,
Pardo Leandro
Publication year - 2020
Publication title -
quality and reliability engineering international
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.913
H-Index - 62
eISSN - 1099-1638
pISSN - 0748-8017
DOI - 10.1002/qre.2665
Subject(s) - estimator , robustness (evolution) , exponential function , m estimator , mathematics , context (archaeology) , inference , maximum likelihood , statistics , computer science , artificial intelligence , mathematical analysis , paleontology , biochemistry , chemistry , biology , gene
Introduced robust density‐based estimators in the context of one‐shot devices with exponential lifetimes under a single stress factor. However, it is usual to have several stress factors in industrial experiments involving one‐shot devices. In this paper, the weighted minimum density power divergence estimators (WMDPDEs) are developed as a natural extension of the classical maximum likelihood estimators (MLEs) for one‐shot device testing data under exponential lifetime model with multiple stresses. Based on these estimators, Wald‐type test statistics are also developed. Through a simulation study, it is shown that some WMDPDEs have a better performance than the MLE in relation to robustness. Two examples with multiple stresses show the usefulness of the model and, in particular, of the proposed estimators, both in engineering and medicine.