scholarly journals Bayesian Inference of δ=P(X

Mathematics ◽  
2019 ◽  
Vol 7 (9) ◽  
pp. 794 ◽  
Author(s):  
Jessie Marie Byrnes ◽  
Yu-Jau Lin ◽  
Tzong-Ru Tsai ◽  
Yuhlong Lio
Keyword(s):  
Empirical Distribution ◽  
Credible Interval ◽  
Absolute Error ◽  
Maximum Likelihood Estimates ◽  
Strength Parameter ◽  
Bayes Estimates ◽  
Censored Samples ◽  
Coverage Probabilities ◽  
Censored Sample ◽  
Burr Type Xii

Let X and Y follow two independent Burr type XII distributions and δ = P ( X < Y ) . If X is the stress that is applied to a certain component and Y is the strength to sustain the stress, then δ is called the stress–strength parameter. In this study, The Bayes estimator of δ is investigated based on a progressively first failure-censored sample. Because of computation complexity and no closed form for the estimator as well as posterior distributions, the Markov Chain Monte Carlo procedure using the Metropolis–Hastings algorithm via Gibbs sampling is built to collect a random sample of δ via the joint distribution of the progressively first failure-censored sample and random parameters and the empirical distribution of this collected sample is used to estimate the posterior distribution of δ . Then, the Bayes estimates of δ using the square error, absolute error, and linear exponential error loss functions are obtained and the credible interval of δ is constructed using the empirical distribution. An intensive simulation study is conducted to investigate the performance of these three types of Bayes estimates and the coverage probabilities and average lengths of the credible interval of δ . Moreover, the performance of the Bayes estimates is compared with the maximum likelihood estimates. The Internet of Things and a numerical example about the miles-to-failure of vehicle components for reliability evaluation are provided for application purposes.

scholarly journals Getting more from heterogeneous HIV-1 surveillance data in a high immigration country: estimation of incidence and undiagnosed population size using multiple biomarkers

2019 ◽  
Vol 48 (6) ◽  
pp. 1795-1803 ◽  
Author(s):  
Federica Giardina ◽  
Ethan O Romero-Severson ◽  
Maria Axelsson ◽  
Veronica Svedhem ◽  
Thomas Leitner ◽  
...  
Keyword(s):  
Dynamic Modelling ◽  
Direct Calculation ◽  
Hiv Infections ◽  
Credible Interval ◽  
Absolute Error ◽  
Surveillance Data ◽  
People Living With Hiv ◽  
Foreign Born ◽  
Multiple Biomarkers ◽  
Hiv 1

Abstract Background Most HIV infections originate from individuals who are undiagnosed and unaware of their infection. Estimation of this quantity from surveillance data is hard because there is incomplete knowledge about (i) the time between infection and diagnosis (TI) for the general population, and (ii) the time between immigration and diagnosis for foreign-born persons. Methods We developed a new statistical method for estimating the incidence of HIV-1 and the number of undiagnosed people living with HIV (PLHIV), based on dynamic modelling of heterogeneous HIV-1 surveillance data. The methods consist of a Bayesian non-linear mixed effects model using multiple biomarkers to estimate TI of HIV-1-positive individuals, and a novel incidence estimator which distinguishes between endogenous and exogenous infections by modelling explicitly the probability that a foreign-born person was infected either before or after immigration. The incidence estimator allows for direct calculation of the number of undiagnosed persons. The new methodology is illustrated combining heterogeneous surveillance data from Sweden between 2003 and 2015. Results A leave-one-out cross-validation study showed that the multiple-biomarker model was more accurate than single biomarkers (mean absolute error 1.01 vs ≥1.95). We estimate that 816 [95% credible interval (CI) 775-865] PLHIV were undiagnosed in 2015, representing a proportion of 10.8% (95% CI 10.3-11.4%) of all PLHIV. Conclusions The proposed methodology will enhance the utility of standard surveillance data streams and will be useful to monitor progress towards and compliance with the 90–90-90 UNAIDS target.

scholarly journals New Flexible Regression Models Generated by Gamma Random Variables with Censored Data

2016 ◽  
Vol 5 (3) ◽  
pp. 9 ◽  
Author(s):  
Elizabeth M. Hashimoto ◽  
Gauss M. Cordeiro ◽  
Edwin M.M. Ortega ◽  
G.G. Hamedani
Keyword(s):  
Regression Model ◽  
Censored Data ◽  
Survival Data ◽  
Regression Models ◽  
Empirical Distribution ◽  
Real Data ◽  
Maximum Likelihood Estimates ◽  
Standard Normal Distribution ◽  
Model Parameters ◽  
Linear Regression Models

We propose and study a new log-gamma Weibull regression model. We obtain explicit expressions for the raw and incomplete moments, quantile and generating functions and mean deviations of the log-gamma Weibull distribution. We demonstrate that the new regression model can be applied to censored data since it represents a parametric family of models which includes as sub-models several widely-known regression models and therefore can be used more effectively in the analysis of survival data. We obtain the maximum likelihood estimates of the model parameters by considering censored data and evaluate local influence on the estimates of the parameters by taking different perturbation schemes. Some global-influence measurements are also investigated. Further, for different parameter settings, sample sizes and censoring percentages, various simulations are performed. In addition, the empirical distribution of some modified residuals are displayed and compared with the standard normal distribution. These studies suggest that the residual analysis usually performed in normal linear regression models can be extended to a modified deviance residual in the proposed regression model applied to censored data. We demonstrate that our extended regression model is very useful to the analysis of real data and may give more realistic fits than other special regression models. 

On the Fatigue-Life Distributions of Engineering Materials

1997 ◽  
Vol 04 (01) ◽  
pp. 93-115 ◽  
Author(s):  
M. A. Khaleel ◽  
S. C. Saunders
Keyword(s):  
Fatigue Life ◽  
Prestressed Concrete ◽  
Large Data ◽  
Least Square ◽  
Linear Functions ◽  
Maximum Likelihood Estimates ◽  
Stress Regime ◽  
Data Set ◽  
Realistic Condition ◽  
Censored Samples

The applicability of the fatigue-life distribution of Birnbaum–Saunders for modeling the components of partially prestressed concrete girder bridges is argued by the agreement of the calculated distribution with a large data set comprised of many small censored samples, each put into standardized form, of the fatigue-lives of bridge components. Also, the Weibull and lognormal distributions are compared by the appropriateness of the assumptions in their derivation to the cumulative damage to bridge components. The maximum likelihood estimates of the parameters of the fatigue lives of the prestressing steel, mild steel, and concrete are found from randomly censored samples, for several censored data-sets under various stress regimes. The parameters are postulated to be log-linear functions of the maximum stress and stress regimes. Weighted least-square regression is applied to determine the unknown coefficients. To compensate for differences in the precision of the estimates obtained under each stress regime the variances are calculated by the bootstrap statistical method. This procedure gives an estimated distribution of the fatigue life with its parameters functions of the stress regime which is applicable under virtually any realistic condition.

scholarly journals Estimation of the Inverse Weibull Distribution Parameters under Type-I Hybrid Censoring

2021 ◽  
Vol 50 (5) ◽  
pp. 38-51
Author(s):  
Mohammad Kazemi ◽  
Mina Azizpoor
Keyword(s):  
Maximum Likelihood ◽  
Weibull Distribution ◽  
Maximum Likelihood Estimates ◽  
Type I ◽  
Unknown Parameters ◽  
Bayes Estimates ◽  
Hybrid Censoring ◽  
Inverse Weibull Distribution ◽  
Distribution Parameters ◽  
Highest Posterior Density

The hybrid censoring is a mixture of type-I and type-II censoring schemes. This paper presents the statistical inferences of the inverse Weibull distribution parameters when the data are type-I hybrid censored. First, we consider the maximum likelihood estimates of the unknown parameters. It is observed that the maximum likelihood estimates can not be obtained in closed form. We further obtain the Bayes estimates and the corresponding highest posterior density credible intervals of the unknown parameters under the assumption of independent gamma priors using the importance sampling procedure. We also compute the approximate Bayes estimates using Lindley's approximation technique. The performance of the Bayes estimates have been compared with maximum likelihood estimates through the Monte Carlo Markov chain techniques. Finally, a real data set have been analysed for illustration purpose.

scholarly journals Bayesian Estimation of Stress-Strength Parameter under Progressive Hybrid Censored Sample in Lomax Distribution

2021 ◽  
Vol 14 (2) ◽  
pp. 0-0
Author(s):  
Akram Kohansal ◽  
Nafiseh Alemohammad ◽  
Fatemeh Azizzadeh ◽  
◽  
◽  
...  
Keyword(s):  
Bayesian Estimation ◽  
Strength Parameter ◽  
Lomax Distribution ◽  
Censored Sample

scholarly journals Bayesian Estimation and Prediction Based on Progressively First Failure Censored Scheme from a Mixture of Weibull and Lomax Distributions

2020 ◽  
pp. 357-372
Author(s):  
Mohamed M. Mahmoud ◽  
Manal Mohamed Nassar ◽  
Marwa Ahmed Aefa
Keyword(s):  
Monte Carlo ◽  
Maximum Likelihood ◽  
Bayesian Estimation ◽  
Likelihood Estimation ◽  
Bayes Estimation ◽  
Maximum Likelihood Estimates ◽  
Monte Carlo Simulation Study ◽  
Estimation And Prediction ◽  
Censored Samples ◽  
Symmetric Square

This paper develops Bayesian estimation and prediction, for a mixture of Weibull and Lomax distributions, in the context of the new life test plan called progressive first failure censored samples. Maximum likelihood  estimation and Bayes estimation, under informative and non-informative priors, are obtained using Markov Chain Monte Carlo methods, based on the symmetric square error Loss function and the asymmetric linear exponential (LINEX) and general entropy loss functions. The maximum likelihood estimates and the different Bayes estimates are compared via a Monte Carlo simulation study. Finally, Bayesian prediction intervals for future observations are obtained using a numerical example

Sign in / Sign up

Export Citation Format

Share Document