arXiv subjects

Adriano Polpo

Publications and source records attributed to Adriano Polpo.

11 recordsLinked to original sources

arXiv2023

Modelling failure risks in load sharing systems with heterogeneous components

A load sharing system has several components and the failure of one component can affect the lifetime of the surviving components. Since component failure does not equate to system failure for different system designs, the analysis of the dependency structure between components becomes a meaningful exercise. The Extended Sequential Order Statistics model allows us to model a dependence structure between heterogeneous components in load sharing systems. However, the results may suggest that the risk of failure decreases as components fail sequentially, which can be counterintuitive, especially when data is scarce. We propose to address this issue by imposing an order restriction on the model parameters that represent increasing failure risks. This assumption corresponds more realistically to the physical properties of the system in many applications. We discuss the advantages of the newly proposed estimates and describe situations where they should be used with caution.

stat.AP↗

arXiv2019

Estimation of component reliability from superposed renewal processes with masked cause of failure by means of latent variables

In a system, there are identical replaceable components working for a given task and a failed component is replaced by a functioning one in the corresponding position, which characterizes a repairable system. Assuming that a replaced component lifetime has the same lifetime distribution as the old one, a single component position can be represented by a renewal process and the multiple components positions for a single system form a superposed renewal process. When the interest consists in estimating the component lifetime distribution, there are a considerable amount of works that deal with estimation methods for this kind of problem. However, the information about the exact position of the replaced component is not available, that is, a masked cause of failure. In this work, we propose two methods, a Bayesian and a maximum likelihood function approaches, for estimating the failure time distribution of components in a repairable system with a masked cause of failure. As our proposed estimators consider latent variables, they yield better performance results compared to commonly used estimators from the literature. The proposed models are generic and straightforward for any probability distribution. Aside from point estimates, interval estimates are presented for both approaches. Using several simulations, the performances of the proposed methods are illustrated and their efficiency and applicability are shown based on the so-called cylinder problem.

stat.AP↗

arXiv2018

Odds for the Brazilian 2018 president elections: An application of Bayesian statistics in contingency tables

The purpose of these notes is to present an assessment of the probability of a candidate be elected in a two-round presidential election. In the first round, all candidates can be voted on. If one of them has more than 50% of the vote (s)he is elected and there is no second round. If none of the candidates obtain more than 50% of the votes, then the top two candidates will be selected for a second round. In this second round, the most voted candidate is elected. This is the scenario of the Brazilian elections that are taking place at the moment. We are calculating the odds associated with the 2018 presidential elections in Brazil. The first round is on October 7, and the second round is on October 28, 2018.

stat.AP↗

arXiv2018

Reliability Estimation in Coherent Systems

Usually, methods evaluating system reliability require engineers to quantify the reliability of each of the system components. For series and parallel systems, there are some options to handle the estimation of each component's reliability. We will treat the reliability estimation of complex problems of two classes of coherent systems: series-parallel, and parallel-series. In both of the cases, the component reliabilities may be unknown. We will present estimators for reliability functions at all levels of the system (component and system reliabilities). Nonparametric Bayesian estimators of all sub-distribution and distribution functions are derived, and a Dirichlet multivariate process as a prior distribution is presented. Parametric estimator of the component's reliability based on Weibull model is presented for any kind of system. Also, some ideas in systems with masked data are discussed.

stat.ME↗

arXiv2018

Reliability of components of coherent systems: estimates in presence of masked data

The reliability of a system of components depends on reliability of each component. Thus, the initial statistical work should be the estimation of the reliability of each component of the system. This is not an easy task because when the system fails, the failure time of a given component can not be observed, that is, censored data. Rodrigues et al. (2017) presented a solution for reliability estimation of components when it is avaliable the system failure time and the status of each component at the time of system failure (if it had failed before, after or it is responsible for system failure). However, there are situations it may be difficult to identify the status of components at the moment of system failure. Such cases are systems with masked causes of failure. Since parallel and series systems are the simplest systems, innumerous alternative solutions for these two systems have been appeared in the literature. To the best of our knowledge, this seems to be the first work that considers the general case of coherent systems. The three-parameter Weibull distribution is considered as the component failure time model. Identically distributed failure times is not required restrictions. Furthermore, there is no restriction on the subjective choice of prior distributions but preference has been given to continuous prior distributions; these priors represent well the nuances of the environment that the system operates. The statistical work of obtaining quantities of the posterior distribution is supported by the Metropolis within Gibbs algorithm. With several simulations, the excellent performance of the model was evaluated. We also consider a computer hard-drives real dataset in order to present the practical relevance of the proposed model.

stat.ME↗

arXiv2017

Categorical data analysis using a skewed Weibull regression model

In this paper, we present a Weibull link (skewed) model for categorical response data arising from binomial as well as multinomial model. We show that, for such types of categorical data, the most commonly used models (logit, probit and complementary log-log) can be obtained as limiting cases. We further compare the proposed model with some other asymmetrical models. The Bayesian as well as frequentist estimation procedures for binomial and multinomial data responses are presented in details. The analysis of two data sets to show the efficiency of the proposed model is performed.

stat.ME↗

arXiv2017

The Likelihood Ratio Test and Full Bayesian Significance Test under small sample sizes for contingency tables

Hypothesis testing in contingency tables is usually based on asymptotic results, thereby restricting its proper use to large samples. To study these tests in small samples, we consider the likelihood ratio test and define an accurate index, the P-value, for the celebrated hypotheses of homogeneity, independence, and Hardy-Weinberg equilibrium. The aim is to understand the use of the asymptotic results of the frequentist Likelihood Ratio Test and the Bayesian FBST -- Full Bayesian Significance Test -- under small-sample scenarios. The proposed exact P-value is used as a benchmark to understand the other indices. We perform analysis in different scenarios, considering different sample sizes and different table dimensions. The exact Fisher test for $2 \times 2$ tables that drastically reduces the sample space is also discussed. The main message of this paper is that all indices have very similar behavior, so the tests based on asymptotic results are very good to be used in any circumstance, even with small sample sizes.

stat.ME↗

arXiv2017

Estimation of Component Reliability in Coherent Systems

The first step in statistical reliability studies of coherent systems is the estimation of the reliability of each system component. For the cases of parallel and series systems the literature is abundant. It seems that the present paper is the first that presents the general case of component inferences in coherent systems. The failure time model considered here is the three-parameter Weibull distribution. Furthermore, neither independence nor identically distributed failure times are required restrictions. The proposed model is general in the sense that it can be used for any coherent system, from the simplest to the more complex structures. It can be considered for all kinds of censored data; including interval-censored data. An important property obtained for the Weibull model is the fact that the posterior distributions are proper, even for non-informative priors. Using several simulations, the excellent performance of the model is illustrated. As a real example, boys first use of marijuana is considered to show the efficiency of the solution even when censored data occurs.

stat.ME↗

arXiv2015

On relative weighted entropies with central moments weight functions

Following [1], the aim of this paper is to analyze the relative weighted entropy involving the central moments weight functions. We compare the standard relative entropy with the weighted case in two particular forms of Gaussian distributions. As an application, the weighted deviance information criterion is proposed.

cs.IT↗

arXiv2014

Confidence Statements for Ordering Quantiles

This work proposes Quor, a simple yet effective nonparametric method to compare independent samples with respect to corresponding quantiles of their populations. The method is solely based on the order statistics of the samples, and independence is its only requirement. All computations are performed using exact distributions with no need for any asymptotic considerations, and yet can be run using a fast quadratic-time dynamic programming idea. Computational performance is essential in high-dimensional domains, such as gene expression data. We describe the approach and discuss on the most important assumptions, building a parallel with assumptions and properties of widely used techniques for the same problem. Experiments using real data from biomedical studies are performed to empirically compare Quor and other methods in a classification task over a selection of high-dimensional data sets.

stat.ME↗

arXiv2013

Reliability estimators for the components of series and parallel systems: The Weibull model

This paper presents a hierarchical Bayesian approach to the estimation of components' reliability (survival) using a Weibull model for each of them. The proposed method can be used to estimation with general survival censored data, because the estimation of a component's reliability in a series (parallel) system is equivalent to the estimation of its survival function with right- (left-) censored data. Besides the Weibull parametric model for reliability data, independent gamma distributions are considered at the first hierarchical level for the Weibull parameters and independent uniform distributions over the real line as priors for the parameters of the gammas. In order to evaluate the model, an example and a simulation study are discussed.

stat.ME↗