Robust Inference for One-Shot Device Testing Data Under Weibull Lifetime Model

Balakrishnan, Narayanaswamy; Castilla González, Elena María; Martín Apaolaza, Nirian; Pardo Llorente, Leandro

Robust Inference for One-Shot Device Testing Data Under Weibull Lifetime Model

Download

weibull_ieee_final2.pdf (662.82 KB)

Official URL

https://ieeexplore.ieee.org/document/8922869

Publication date

2020

Authors

Balakrishnan, Narayanaswamy

Castilla González, Elena María

Martín Apaolaza, Nirian

Pardo Llorente, Leandro

Publisher

Institute of Electrical and Electronics Engineers

Citations

Exportar

URI

https://hdl.handle.net/20.500.14352/93697

Citation

N. Balakrishnan, E. Castilla, N. Martín and L. Pardo, "Robust Inference for One-Shot Device Testing Data Under Weibull Lifetime Model," in IEEE Transactions on Reliability, vol. 69, no. 3, pp. 937-953, Sept. 2020, doi: 10.1109/TR.2019.2954385.

Abstract

Classical inferential methods for one-shot device testing data from an accelerated life-test are based on maximum likelihood estimators (MLEs) of model parameters. However, the lack of robustness of MLE is well-known. In this article, we develop robust estimators for one-shot device testing by assuming a Weibull distribution as a lifetime model. Wald-type tests based on these estimators are also developed. Their robustness properties are evaluated both theoretically and empirically, through an extensive simulation study. Finally, the methods of inference proposed are applied to three numerical examples. Results obtained from both Monte Carlo simulations and numerical studies show the proposed estimators to be a robust alternative to MLEs.