Bathtub Shape Research Articles

On the Topp-Leone Generalized Power Weibull Distribution: Properties, Applications and Regression

Abstract The Topp-Leone generalized power Weibull distribution, which is an extension of generalized power Weibull, is proposed and its properties explored. The failure rate of the proposed distribution exhibits increasing, reversed J, upside-down bathtub, and bathtub shapes. Some statistical properties are obtained: quantile function, moments, moment generating function, incomplete moment, mean and median deviations, mean residual life function, and Lorenz as well as Bonferroni curves. The maximum likelihood estimation approach is deployed to estimate the model parameters. Simulation studies are conducted to evaluate the performance and accuracy of the maximum likelihood estimates of the model parameters. Applications of the model to real datasets are presented. A location-scale regression model is also developed for the proposed model and its application has been demonstrated with a real dataset. Keywords: Bonferroni, Deviation, Mimicked, Simulation, and Upside-down Bathtub.

Unit extended exponential distribution with applications

In this paper, the unit extended exponential distribution is presented. The extended exponential distribution is a two-parameter lifespan distribution that has been demonstrated to be very adaptable. Our goal is to convert this flexibility between the unit interval and the extended exponential distribution. Several different types of probability density functions, including decreasing, left-skewed, right-skewed, and unimodal, have been shown. However, the hazard rate function may take on various forms, including J-shaped, U-shaped, and bathtub shapes. A few statistical properties, such as moments, mean, variance, skewness, kurtosis, expectation-weighted moments, incomplete moments, conditional moments, mean deviation, Lorenz and Bonferroni curves, mean residual life, mean inactivity time, and various entropy measures, round out the theoretical section. The maximum likelihood technique is utilized to estimate model parameters using unit data. This study provides simulation data to evaluate the proposed strategy. Two applications utilizing actual data sets emphasize the significance of the new model compared to existing unit models.

The Modified Kies Flexible Generalized Family: Properties, Simulations, and Applications

The modified Kies flexible generalized family is developed. It can incorporate bimodal and bathtub shapes, and its properties are derived from those of the exponentiated-G class. Within this family, a special case is discussed in terms of its properties and a regression model. The parameters are estimated using the maximum likelihood method, and some simulations are carried out to check their consistency. The usefulness of the proposals is proven by means of three real data sets.

Sine π\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\pi$$\\end{document}-power odd-G family of distributions with applications

This paper investigates a novel category of probability distributions and a specific member within this category. We have formulated a new family of trigonometric distributions by utilizing the odds ratio derived from the distribution function of a base distribution. This newly devised distribution family termed the “Sine pie-power odd-G family” of distributions, is constructed through a transformation involving the sine function. The paper presents an overview of the fundamental characteristics inherent to this proposed distribution family. Using the Weibull distribution as a base reference, we have introduced a member belonging to the proposed distribution family. This member demonstrates various hazard functions such as j, reverse-j, increasing, decreasing, or bathtub shapes. The paper examines essential statistical attributes of this newly introduced distribution. The estimation of the distribution’s parameters is carried out via the maximum likelihood estimation method. The accuracy of the parameter estimation procedure is validated through Monte Carlo simulations. The outcomes of these simulations reveal a reduction in biases and mean square errors as sample sizes increase, even for small samples. Two sets of real-engineering data are considered to demonstrate the proposed distribution’s applicability. The performance of the suggested distribution is evaluated using some model selection criteria and goodness-of-fit test statistics. Empirical evidence from these evaluations substantiates that the proposed model outperforms six existing models.

A new extension of the Gumbel distribution with biomedical data analysis

In the field of biomedical research, data characteristics often exhibit significant variability, challenging the applicability of classical Gumbel distribution for biomedical data modeling. To address this, this paper introduces a novel extension of the Gumbel model known as the odd beta prime Gumbel (OBP-Gum) model. Derived from the odd beta prime family, the new distribution exhibits greater kurtosis compared to the traditional Gumbel distribution. Importantly, the proposed distribution is designed to capture right-skewed, left-skewed, and nearly symmetric density functions, as well as increasing, decreasing, constant, and upside-down bathtub shapes for its hazard rate function, providing excellent curvature features for creating flexible statistical models for biomedical research. We derive the fundamental features of the OBP-Gum model, such as the quantile function, linear representations, moment generating function, moments, skewness, kurtosis, incomplete moments, and Rényi and Tsallis entropies. Parameter estimation for this new model is conducted using the maximum likelihood estimation method. A simulation study demonstrates the performance of the model parameters. The empirical findings, based on applications to two biomedical datasets, suggest that the OBP-Gum distribution outperforms existing models, particularly in handling extreme observations. Instead of relying on conventional models for decision-making, this research provides relevant stakeholders with an improved statistical distribution for more accurate biomedical data modeling.

Properties and applications of the Tan Weibull loss distribution

Probability models play crucial role in modeling loss in the finance and actuarial sciences. In this article, a new family of loss distributions known as the Tan F-Loss family of distributions is proposed with the Tan Weibull Loss distribution as a special case. The density exhibits decreasing, right skewed, symmetric, and approximately symmetric shapes. The hazard rate function shows decreasing and modified bathtub shapes. The statistical properties of the Tan Weibull Loss distribution including the quantile function, moments, expansion of the general rate, moment generating function, incomplete moment, and order statistics are studied. The maximum likelihood estimators of the distribution are also studied. Simulations are carried out to examine the behavior of the estimators. The results show that the estimators are consistent. The usefulness of the proposed distribution is demonstrated with two insurance loss datasets. The results show that the proposed distribution gives a better parametric to the two datasets compared with the competing distributions.

Decreasing Trend Bumped Probability Distribution: its Properties, Simulations and Application

In this paper, a probability model is proposed which engaged the mathematical combination of Lindley distribution and a trigonometric component known as haversine function〖 δ〗_s. The one parameter model prototype sustains the capacity to forecast multimodal decreasing trend sinusoidal outcomes. By nomenclature, the proposed probability model is called Modified Lindley Trigonometric Distribution (MLTD). Some statistical properties studied include the hazard function, mean residual life function, moments, conditional moments and moment generating function, Bonferroni and Lorenz curve, entropy, asymptotic distribution, order statistics, and parameter estimation; where the hazard function specially features a cyclic or periodic bathtub and inverted bathtub shape in chain format. The numerical behavior of the estimates of the average bias and mean square error were examined under Monte Carlo simulation approach; and an applicative simulation is experimented to underscore the parametric behavior of MLTD in data modeling. A real life flood data is used to illustrate the essence of the development.

A new extended Pham distribution for modelling cancer data

In this study, a novel extended Pham model is offered and examined. This model can fit positive, negative, and approximately symmetric data. In addition, it features four alternative hazard rate shapes, namely increasing, decreasing, bathtub, and upside-down bathtub shapes. The new model's main properties, such as quantiles, moments, and mean deviations, are derived. To evaluate the estimation of distribution parameters, two approaches are studied. From a classical standpoint, the maximum likelihood technique is used to determine the point and approximate confidence intervals of all unknown parameters. The Bayesian estimation method, on the other hand, is considered via the Markov chain Monte Carlo technique for obtaining Bayes point estimates alongside Bayes credible intervals. We present various Monte Carlo simulation studies to investigate the efficacy of maximum likelihood and Bayes estimation findings for the model's parameters. Numerical investigations showed that the offered Bayes estimates outperformed those derived using the conventional method. We also analyzed two sets of real data taken from the medical sector; the first represents survival rates for cancer patients who received a combination of radiotherapy and chemotherapy, and the second consists of remission times for bladder cancer patients. These clinical scenarios reveal that the new model outperforms other important competing models based on specific statistical criteria. Ultimately, for both clinical data applications, the proposed extended Pham distribution is the best choice compared to the traditional Pham and the other well-known eight lifetime models.

On the Bivariate Extension of the Extended Standard U-quadratic Distribution

This paper derives the bivariate version of the extended standard U-quadratic (eSU) distribution using the method of compounding or pseudo family of distributions. The joint probability and cumulative distribution functions of the derived distribution are obtained and it is observed that the said distribution can generate bivariate shape with the following properties: $(i)$ $X$ and $Y$ have bathtub shapes; $(ii)$ $X$ has constant and $Y$ has bathtub shapes; and $(iii)$ $X$ has inverted bathtub and $Y$ has bathtub shapes. Moreover, some properties of the derived distribution such as the marginal distribution, conditional distributions, conditional moments, product and ratio moments are derived. Further, the maximum likelihood estimation is performed to estimate the parameters of the derived distribution. Also, a simulation study is carried out to evaluate the behavior of the estimates of the parameters. Moreover, we derive a new bivariate Kumaraswamy distribution and use it to simulate bivariate data with $X$ and $Y$ having bathtub shapes. Furthermore, A new bivariate version of the Cubic Transmuted Uniform (CTU) distribution is also derived. Finally, the proposed Bivariate eSU distribution is applied to simulated data and compared with the said Bivarite Cubic Transmuted Uniform distribution. The result shows that the proposed Bivariate eSU distribution provides a better fit for the said simulated dataset as compared with the Bivariate CTU distribution.

WEIBULL-POISSON DISTRIBUTION AND THEIR APPLICATION TO SYSTEMATIC PARALLEL RISK

The Weibull-Poisson distribution represents a continuous distribution type applicable to various forms of hazard, including monotone up, monotone down, and upside-down bathtub shapes that ascend. The distribution characterizes lifetimes and can effectively model failures within a series of systems, which evolves from the Exponential-Poisson distribution. This distribution emerges through the compounding of the Weibull Distribution and Zero Truncated Poisson Distribution. The compounding itself integrates several mathematical properties, such as statistical order and Taylor’s number expansion, to reach its final form. Alongside the formulation of the Weibull-Poisson distribution, this paper includes the probability density function, distribution function, rth moment, rth central moment, mean, and variance. For illustration, the Weibull-Poisson distribution is applied to guinea pig survival data after being infected with Turblece virus Bacilli.

Alpha power inverse Weibull distribution: A new lifetime distribution with application to gastric cancer data

Lifetime data analysis has an essential role in various fields of science. In general, lifetime data have a skewed distribution pattern. The Weibull distribution is one of the most frequently used distributions for modeling lifetime data. However, the Weibull distribution is not suitable for modeling data with non-monotonous hazard functions, one of which is an upside-down bathtub shape. According to Sharma et al. (2015), the inverse version of several probability distributions can model the data with an upside-down bathtub shape, one of which is the inverse Weibull distribution. This paper explains the Alpha Power Inverse Weibull (APIW) distribution as a generalization version of the inverse Weibull distribution. This distribution is constructed by using the Alpha Power Transformation method. The modification is done by adding a shape parameter to the inverse Weibull distribution to increase flexibility. The characteristics of APIW distribution discussed include probability density function, distribution function, survival function, hazard function, and the r-th moment. The probability density function of APIW distribution is left-skewed and unimodal. In addition, the hazard function of APIW distribution has an upside-down bathtub shape. The parameters of this distribution are estimated by the maximum likelihood method. Finally, for illustration purposes, the data about the time until gastric cancer patients die are modelled with the inverse Weibull distribution, and the APIW distribution is given. The modeling result shows that the Alpha Power Inverse Weibull distribution is better at modeling the time until gastric cancer patients die data than the inverse Weibull distribution.

A New Life-Time Model with Bathtub and Inverted Bathtub Failure Rate Function

In this paper, a three parameter model called Zubair- Kumaraswamy (Z-Kum) distribution is proposed. The extension was done using Zubair G-Family [1] of continuous probability distribution to extend the well knownKumaraswamy distribution to make it more flexible in modeling and predicting real world phenomenon. Some basic structural properties of the new distributions like cdf, pdf, quantile functions, moments, moment generating functions, characteristics functions and order statistics was obtained. Survival function, hazard function, reversed hazard rate function and a cumulative hazard rate function was also obtained. Behavior of the hazard rate plot exhibit increase, decrease, Bathtub and inverted Bathtub shape. Maximum likelihood estimate was used to estimate the Z-Kum distribution parameters. Monte Carlo simulation was carried out to evaluate the performance of MLE method adopted. Result of the simulation studies indicates that MLE is good for the estimation of our distribution parameters. To compare the proposed model with the other fitted existing models, analytical measure of goodness of fit of some information criterion was considered using three real life data sets. From the results obtained, it is evident that our proposed model gives better fit than the other competing models and therefore, our proposed model provide greater flexibility in modeling real world phenomenon.

Statistical inference of joint competing risks models from comparative bathtub shape distributions with hybrid censoring

In reliability engineering studies, the class of lifetime distributions with bathtub-shaped failure rate functions is particularly important since the lifetimes of electro-mechanical, electronic, and mechanical goods are frequently modelled with this characteristic. Comparative competing risk data are obtained in a variety of applications, including engineering, biological, medical, and other related fields. In this study, we adopted the statistical inference of joint distributions with a bathtub shape or increasing failure rate function (Chen distributions). The problem of determining the relative merits of products according to their lifetime duration is discussed under the hybrid type-I censoring scheme. Also, under consideration of independent causes of failure, a survival analysis and the assessment of one risk in the presence of other risks are discussed. The maximum likelihood (ML) method and the Bayes approach relative to the symmetric loss function are used to estimate the model parameters. Additionally, we build the classical confidence intervals (CIs) (asymptotic CI and bootstrap CI) to compare with the Bayes credible intervals. Moreover, theoretical results are evaluated and contrasted using a Monte Carlo simulation study. Finally, for illustration purposes, a real data set obtained from a laboratory experiment is evaluated using the suggested model with some brief comments.

Odd Chen Exponential Distribution: Properties and Applications

In this study, a new statistical distribution with three parameters called the Odd-Chen Exponential has been proposed. The statistical properties of the proposed distribution, such as the quantile, moments, incomplete moments, moment-generating function, and mean residual life, were developed. The density shows different shapes, making it more flexible for analyzing different forms of data. The hazard function also exhibits different shapes, including the well-known bathtub shape, which means that the distribution is flexible with real-life data. To estimate the distribution parameters, ordinary least squares estimators, Cramér-von Mises estimators, and maximum likelihood estimators were derived. The results were compared using a Monte Carlo simulation. Two-time datasets; one from the mining field and the other from survival analysis, were used to check the applicability of the proposed distribution. The results revealed that the OCE distribution performed better than the Odd Chen Weibull, Odd Chen Rayleigh, Rayleigh, Cauchy, Generalised Inverse Weibull and the Modified Extended Chen distributions.

A two‐parameter parsimonious bathtub model for the analysis of system failure times with illustrations to reliability data

AbstractIn this study, a two‐parameter, upper‐bounded probability distribution called the tau distribution is introduced and its applications in reliability engineering are presented. Each of the parameters of the tau distribution has a clear semantic meaning. Namely, one of them determines the upper bound of the distribution, while the value of the other parameter influences the shape of the cumulative distribution function. A remarkable property of this new probability distribution is that its probability density function, survival function, hazard rate function (HRF), and quantile function can all be expressed in terms of its cumulative distribution function. The HRF of the proposed probability distribution can exhibit an increasing trend and various bathtub shapes with or without a low and long‐flat phase (useful time phase), which makes this new distribution suitable for modeling a wide range of real‐world problems. The constraint maximum likelihood estimation, percentile estimation, approximate Bayesian computation, and approximate quantile estimation computation are proposed to calculate the unknown parameters of the model. The suitability of the estimation methods is verified with the aid of simulation and real‐world data results. The modeling capability of the tau distribution was compared with that of some well‐known two‐ and three‐parameter probability distributions using two data sets known from the literature of reliability engineering: time between failures data of a machining center, and time to failure of data acquisition system cards. Based on empirical results, the new distribution may be viewed as a viable competitor to the Weibull, Gamma, Chen, and modified Weibull distributions.

Inverse power Ramos–Louzada distribution with various classical estimation methods and modeling to engineering data

This work uses the inverse-power transformation to create the inverse power Ramos–Louzada distribution (IPRLD), a novel two-parameter version of the Ramos–Louzada distribution. The failure rate of the new distribution can be represented by a reverse bathtub shape, a rising shape, or a decreasing shape, making it appropriate for a range of real data. Asymmetrical and unimodal densities can be produced via the IPRLD. Its mathematical characteristics are computed in some cases. The novel proposed model’s structural characteristics are derived. To estimate the model parameters, several estimating strategies are explored, including ten classical methods. Simulation results with their partial and total ranks are used to evaluate the ranking and behavior of various approaches. Finally, two real-world datasets are used to experimentally show the suggested distribution’s adaptability. The analysis of the data reveals that the introduced distribution offers a better fit than some significant rival distributions, including the inverse Ramos–Louzada, inverse power Burr Hatke, inverse Nakagami-M, inverse log-logistic, inverse weighted Lindley, inverse Lindley, and Ramos–Louzada.

Variational Bayesian Inference for Exponentiated Weibull Right Censored Survival Data

The exponential, Weibull, log-logistic and lognormal distributions represent the class of light and heavy-tailed distributions that are often used in modelling time-to-event data. The exponential distribution is often applied if the hazard is constant, while the log-logistic and lognormal distributions are mainly used for modelling unimodal hazard functions. The Weibull distribution is on the other hand well-known for modelling monotonic hazard rates. Recently, in practice, survival data often exhibit both monotone and non-monotone hazards. This gap has necessitated the introduction of Exponentiated Weibull Distribution (EWD) that can accommodate both monotonic and non-monotonic hazard functions. It also has the strength of adapting unimodal functions with bathtub shape. Estimating the parameter of EWD distribution poses another problem as the flexibility calls for the introduction of an additional parameter. Parameter estimation using the maximum likelihood approach has no closed-form solution, and thus, approximation techniques such as Newton-Raphson is often used. Therefore, in this paper, we introduce another estimation technique called Variational Bayesian (VB) approach. We considered the case of the accelerated failure time (AFT) regression model with covariates. The AFT model was developed using two comparative studies based on real-life and simulated data sets. The results from the experiments reveal that the Variational Bayesian (VB) approach is better than the competing Metropolis-Hasting Algorithm and the reference maximum likelihood estimates.

Inverse Hamza Distribution: Properties and Applications to Lifetime Data

In this paper, a new distribution, named ‘the Inverted Hamza distribution’, was introduced. It is an extension of the Hamza distribution that can model real-world data with an upside-down bathtub shape and heavy tails. Mathematical and statistical characteristics such as the quantile function, moments, entropy measure, stochastic ordering and distribution of order statistics have been derived. Furthermore, dependability measures such as the survival function and hazard function have been developed. The greatest likelihood technique was used to estimate the distribution parameters. To demonstrate the applicability of the distribution, a numerical example was given. According on the results, the proposed distribution outperformed the competing distributions.

A Novel Zero-Truncated Katz Distribution by the Lagrange Expansion of the Second Kind with Associated Inferences

In this article, the Lagrange expansion of the second kind is used to generate a novel zero-truncated Katz distribution; we refer to it as the Lagrangian zero-truncated Katz distribution (LZTKD). Notably, the zero-truncated Katz distribution is a special case of this distribution. Along with the closed form expression of all its statistical characteristics, the LZTKD is proven to provide an adequate model for both underdispersed and overdispersed zero-truncated count datasets. Specifically, we show that the associated hazard rate function has increasing, decreasing, bathtub, or upside-down bathtub shapes. Moreover, we demonstrate that the LZTKD belongs to the Lagrangian distribution of the first kind. Then, applications of the LZTKD in statistical scenarios are explored. The unknown parameters are estimated using the well-reputed method of the maximum likelihood. In addition, the generalized likelihood ratio test procedure is applied to test the significance of the additional parameter. In order to evaluate the performance of the maximum likelihood estimates, simulation studies are also conducted. The use of real-life datasets further highlights the relevance and applicability of the proposed model.

Generalized Unit Half-Logistic Geometric Distribution: Properties and Regression with Applications to Insurance

The use of distributions to model and quantify risk is essential in risk assessment and management. In this study, the generalized unit half-logistic geometric (GUHLG) distribution is developed to model bounded insurance data on the unit interval. The corresponding probability density function plots indicate that the related distribution can handle data that exhibit left-skewed, right-skewed, symmetric, reversed-J, and bathtub shapes. The hazard rate function also suggests that the distribution can be applied to analyze data with bathtubs, N-shapes, and increasing failure rates. Subsequently, the inferential aspects of the proposed model are investigated. In particular, Monte Carlo simulation exercises are carried out to examine the performance of the estimation method by using an algorithm to generate random observations from the quantile function. The results of the simulation suggest that the considered estimation method is efficient. The univariate application of the distribution and the multivariate application of the associated regression using risk survey data reveal that the model provides a better fit than the other existing distributions and regression models. Under the multivariate application, we estimate the parameters of the regression model using both maximum likelihood and Bayesian estimations. The estimates of the parameters for the two methods are very close. Diagnostic plots of the Bayesian method using the trace, ergodic, and autocorrelation plots reveal that the chains converge to a stationary distribution.