In this article, a new distribution, called transformed Generalized Exponential Distribution () is proposed. The distribution has simple closed forms pdf and cdf. Several properties of the are studied including unimodality, moments, conditional stochastic ordering Shannon entropy. capable monotonically increasing, decreasing, bathtub upside down shaped hazard rates. Furthermore, we discussed several methods estimation for estimating parameters. particular, compare, through simulation study,...

This article considers a multi-state system which is composed by several multi-type components, it assumed that any type of components has two strengths suffered from stresses. Further, assume have dependent relationship, as well the stresses, but there are no relationship among and stresses for different types components. By extending applied scenarios, new survival signature, named improved generalized introduced used to analyze reliability. When stress (strength) variables follow...

This article considers statistical analysis of dependent competing risks model from Weibull distribution in accelerated life testing, which copula function is used to examine the dependence structure between failure modes. We derive maximum likelihood estimates, approximate, and Bootstrap confidence intervals parameters. The effects different structures on estimates parameters are investigated. simulation given compare performance when modes with those independent. Finally, one dataset was...

In life testing, the competing risks model is usually discussed under assumption of independence. this paper, we consider a dependent using bivariate Birnbaum-Saunders distribution in constant-stress accelerated testing. To observe expected failure times and terminate tests around predetermined time, adaptive progressively hybrid censoring scheme adopted. Based on with scheme, obtain maximum-likelihood estimators, approximate confidence intervals, bootstrap intervals unknown parameters. test...

Based on the tampered failure rate model under adaptive Type-II progressively hybrid censoring data, we discuss maximum likelihood estimators of unknown parameters and acceleration factors in general step-stress accelerated life tests this paper. We also construct exact unique confidence interval for extended Weibull shape parameter. In numerical analysis, describe simulation procedures to obtain data present an experimental illustrate performance estimators.

In this paper we introduce a new three parameter distribution called the generalized odd log-logistic exponential (GOLLEx) distribution. The proposed possesses very flexible hazard rate function shapes which provide more flexibility in data analysis. We study main properties of including quantiles, moments, moment generating function. obtain maximum likelihood and Bayes estimates GOLLEx based on complete type-II censored data. unknown parameters are obtained by using Markov Chain Mont Carlo...

Under constant stress accelerated test, we analyze the masked data from hybrid systems including series-parallel system and parallel-series system. The Bayesian posterior distribution estimates of components' subsurvival functions are obtained by assuming a prior multivariate Dirichlet process. By establishing relationship between survival components, reliabilities for components derived functions. It is not confined to common restriction that sets discontinuity points have be disjointed....

In this paper, studies of competing risks model are considered when the observations left-truncated and right-censored data. When failure times distributed by a generalized inverted exponential with same scale but different shape parameters partially observed causes, statistical inference for unknown is discussed from classical Bayesian approaches, respectively. Maximum likelihood estimators parameters, along associated existence uniqueness, established, asymptotic theory also used to...

In reliability analysis and life testing studies, the experimenter is frequently interested in studying a specific risk factor presence of other factors. this paper, estimation unknown parameters, hazard functions alpha power exponential distribution considered based on progressively Type-II censored competing risks data. We assume that latent cause failures has independent distributions with different scale shape parameters. The maximum likelihood method to estimate model parameters as well...

The present study focuses on estimating the stress–strength parameter when parent distribution is alpha power exponential model and available data are progressively Type-II censored. As a starting point, usual maximum likelihood approach applied to obtain point interval estimates of parameters, as well parameter. Another competing strategy employed in this paper product spacing method, which may be thought rival method. used for various parameters. asymptotic properties both methods...

Abstract In this paper, reliability estimation of multicomponent system under a multilevel accelerated life testing. When the lifetime components follows Weibull distribution, problem point and interval estimates are discussed from different perspectives. Under general life‐stress assumption that there multiple nonconstant stress‐dependent scale shape parameters, maximum likelihood unknown parameters along with associated existence uniqueness established. Approximate confidence intervals...

Abstract This paper considers a constant‐stress accelerated dependent competing risks model under Type‐II censoring. The structure between is modeled by Marshall‐Olkin bivariate exponential distribution, and the described power rule model. point interval estimation of parameters reliability function normal usage condition at mission time are obtained using maximum likelihood method bootstrap sampling technique. Moreover, pivotal quantities based adopted to estimate generalized confidence...

In this article we consider the process capability index (PCI) $C_{pmk}$ which can be used for normal random variables. The objective of is four fold: first address different classical methods estimation PCI from frequentest approaches distribution and compare them in terms their biases mean squared errors. Second, three bootstrap confidence intervals (BCIs) $C_{pmk}$. Third, Bayesian under symmetric asymmetric loss functions. Fourth, have incorporated a tolerance cost function to develop...

Abstract Sometimes classification tasks have to be based on multivariate time series data collected for each class. In these situations the class might exhibit non-stationary behaviour together with complex dependence structures. We propose a vine copula-based approach capture features in before applying Bayesian classifier. Vine copulas been very successful modelling asymmetric tail among variables and are coupled univariate model illustrate this using from neural activity experiment...

In this paper, problems of estimation and prediction for record values are discussed a two-parameter unit generalized Rayleigh distribution. Maximum likelihood estimators model parameters along with their existence uniqueness established, corresponding approximate confidence intervals constructed based on asymptotic theory. addition, alternative inferential approach is provided comparison the proposed pivotal quantities. Further, remaining useful life also presented under classical methods...