Examinando por Autor "Castilla, Elena"

Mostrando 1 - 5 de 5

A new estimation approach based on phi-divergence measures for one-shot device accelerated life testing
(Wiley, 2024-02-12) Castilla, Elena
One-shot device testing data are used only once and they get destroyed when tested. As these products usually have large mean times to failure under normal operating conditions, accelerated life tests are commonly used to infer their lifetime distribution. While much work has been done to determine the maximum likelihood estimates (MLEs) of model parameters for one-shot device accelerated life testing, the efficiency of these methods may not be guaranteed for small to moderate sample sizes. In this paper, we develop new estimators and confidence intervals based on phi-divergences, we show that they outperform the conventional MLE under different lifetime distributions and present an example to illustrate all the inferential methods developed here
A New Robust Approach for Multinomial Logistic Regression With Complex Design Model
(IEEE, 2022-06-29) Castilla, Elena; Chocano, Pedro J.
Robust estimators and Wald-type tests are developed for the multinomial logistic regression based on φ-divergence measures. We compute the influence function of the proposed estimators and tests and discuss some consequences. Their robustness is illustrated by an extensive simulation study and two real examples.
Robust inference for nondestructive one-shot device testing under step-stress model with exponential lifetimes
(Wiley, 2023-02-01) Balakrishnan, Narayanaswamy; Castilla, Elena; Jaenada, María; Pardo, Leandro
One-shot devices analysis involves an extreme case of interval censoring, wherein one can only know whether the failure time is either before or after the test time. Some kind of one-shot devices do not get destroyed when tested, and so can continue within the experiment, providing extra information for inference, if they did not fail before an inspection time. In addition, their reliability can be rapidly estimated via accelerated life tests (ALTs) by running the tests at varying and higher stress levels than working conditions. In particular, step-stress tests allow the experimenter to increase the stress levels at prefixed times gradually during the life-testing experiment. The cumulative exposure model is commonly assumed for step-stress models, relating the lifetime distribution of units at one stress level to the lifetime distributions at preceding stress levels. In this paper, we develop robust estimators and Z-type test statistics based on the density power divergence (DPD) for testing linear null hypothesis for nondestructive one-shot devices under the step-stress ALTs with exponential lifetime distribution. We study asymptotic and robustness properties of the estimators and test statistics, yielding point estimation and confidence intervals for different lifetime characteristic such as reliability, distribution quantiles, and mean lifetime of the devices. A simulation study is carried out to assess the perfor- mance of the methods of inference developed here and some real-life data sets are analyzed finally for illustrative purpose.
Robust Minimum Divergence Estimation for the Multinomial Circular Logistic Regression Model
(MDPI, 2023-10-07) Castilla, Elena; Ghosh, Abhik
Circular data are extremely important in many different contexts of natural and social science, from forestry to sociology, among many others. Since the usual inference procedures based on the maximum likelihood principle are known to be extremely non-robust in the presence of possible data contamination, in this paper, we develop robust estimators for the general class of multinomial circular logistic regression models involving multiple circular covariates. Particularly, we extend the popular density-power-divergence-based estimation approach for this particular set-up and study the asymptotic properties of the resulting estimators. The robustness of the proposed estimators is illustrated through extensive simulation studies and few important real data examples from forest science and meteorology
Statistical Modeling and Robust Inference for One-shot Devices
(Academic Press, 2025) Balakrishnan, Narayanaswamy; Castilla, Elena
The study of one-shot devices such as automobile airbags, fire extinguishers, or antigen tests, is rapidly becoming an important problem in the area of reliability engineering. These devices, which are destroyed or must be rebuilt after use, are a particular case of extreme censoring, which makes the problem of estimating their reliability and lifetime challenging. However, classical statistical and inferential methods do not consider the issue of robustness. Statistical Modeling and Robust Interference for One-shot Devices offers a comprehensive investigation of robust techniques of one-shot devices under accelerated-life tests. With numerous examples and case studies in which the proposed methods are applied, this book includes detailed R codes in selected chapters to help readers implement their own codes and use them in the proposed examples and in their own research on one shot devicetesting data. Researchers, mathematicians, engineers, and students working on acceleratedlife testing data analysis and robust methodologies will find this to be a welcome resource.