Explore the vast range of titles available.

We introduce a quantile-adaptive framework for nonlinear variable screening with high-dimensional heterogeneous data. This framework has two distinctive features: (1) it allows the set of active variables to vary across quantiles, thus making it more flexible to accommodate heterogeneity; (2) it is model-free and avoids the difficult task of specifying the form of a statistical model in a high dimensional space. Our nonlinear independence screening procedure employs spline approximations to model the marginal effects at a quantile level of interest. Under appropriate conditions on the quantile functions without requiring the existence of any moments, the new procedure is shown to enjoy the sure screening property in ultra-high dimensions. Furthermore, the quantile-adaptive framework can naturally handle censored data arising in survival analysis. We prove that the sure screening property remains valid when the response variable is subject to random right censoring. Numerical studies confirm the fine performance of the proposed method for various semiparametric models and its effectiveness to extract quantilespecific information from heteroscedastic data.

Ultrahigh-dimensional variable selection plays an increasingly important role in contemporary scientific discoveries and statistical research. Among others, Fan and Lv [J. R. Stat. Soc. Ser. B Stat. Methodol. 70 (2008) 849—911] propose an independent screening framework by ranking the marginal correlations. They showed that the correlation ranking procedure possesses a sure independence screening property within the context of the linear model with Gaussian covariates and responses. In this paper, we propose a more general version of the independent learning with ranking the maximum marginal likelihood estimates or the maximum marginal likelihood itself in generalized linear models. We show that the proposed methods, with Fan and Lv [J. R. Stat. Soc. Ser. B Stat. Methodol. 70 (2008) 849—911] as a very special case, also possess the sure screening property with vanishing false selection rate. The conditions under which the independence learning possesses a sure screening is surprisingly simple. This justifies the applicability of such a simple method in a wide spectrum. We quantify explicitly the extent to which the dimensionality can be reduced by independence screening, which depends on the interactions of the covariance matrix of covariates and true parameters. Simulation studies are used to illustrate the utility of the proposed approaches. In addition, we establish an exponential inequality for the quasi-maximum likelihood estimator which is useful for high-dimensional statistical learning.

Stimulated by the need of describing useful notions related to information measures, we introduce the ‘pdf-related distributions’. These are defined in terms of transformation of absolutely continuous random variables through their own probability density functions. We investigate their main characteristics, with reference to the general form of the distribution, the quantiles, and some related notions of reliability theory. This allows us to obtain a characterization of the pdf-related distribution being uniform for distributions of exponential and Laplace type as well. We also face the problem of stochastic comparing the pdf-related distributions by resorting to suitable stochastic orders. Finally, the given results are used to analyse properties and to compare some useful information measures, such as the differential entropy and the varentropy.

This paper introduces a novel approach to calculating the failure probability of k-out-of-n systems under harmful shocks, which occur randomly and affect at least one component. Traditional methods for this calculation face challenges such as high computational costs and complexity, especially for large systems. The new approach simplifies the computation by developing an easily executable algorithm, saving time and resources. The proposed formula has been shown to be equivalent to existing ones. Additionally, it has been demonstrated that the failure probability under certain conditions follows a binomial distribution, with system design influencing the failure probability for each shock. Keywords: Failure probability, Binomial distribution, Shocks, k - out - of - n system. AMS Subject Classification: 62E99, 62E15, 62P30, 90B25

In this article, we reexamine properties of maximum log-likelihood parameter estimation for two-parameter Weibull distributions which have been applied in many different sciences. Finding reasons for this popularity is a key question. Our main contribution is a thorough existence and uniqueness proof for a global maximizer with respect to the parameter space. We first provide existence and uniqueness of local maximizers by Schauder’s first fixed point theorem, monotony arguments and local concavity of its Hessian matrix. Thus, we can prove our main result of existence and uniqueness of a global maximizer by considering all limiting cases with respect to the parameter space. We finally strengthen our theoretical findings on four data sets. On the one hand, two synthetic data sets underline our need for our data assumptions while, on the other hand, we choose two data sets from wind engineering and reliability engineering to demonstrate usefulness in real-world applications.

We introduce a new generalization of the exponentiated power Lindley distribution, called the exponentiated power Lindley power series (EPLPS) distribution. The new distribution arises on a latent complementary risks scenario, in which the lifetime associated with a particular risk is not observable; rather, we observe only the maximum lifetime value among all risks. The distribution exhibits decreasing, increasing, unimodal and bathtub shaped hazard rate functions, depending on its parameters. Several properties of the EPLPS distribution are investigated. Moreover, we discuss maximum likelihood estimation and provide formulas for the elements of the Fisher information matrix. Finally, applications to three real data sets show the flexibility and potentiality of the EPLPS distribution.

A framework of two-sided densities is presented for asymmetric continuous distributions consisting of two branches each with its own generating density. The framework supports the construction of distributions with positive support and a specified mode. Examples thereof shall be constructed using the beta and Burr Type XII distributions for their left and right branch densities. The examples are parameterized via left and right branch scale parameters, a mode parameter and two parameters determining the heaviness of its right tail. Keeping one of the tail parameters fixed, a procedure solving for their parameters is presented given a lower and upper quantile, a mode and a conditional-value-at-risk, popular in risk management of insurance losses. While valuable on its own right, that solution may be used as a starting point for a maximum likelihood routine. The estimation of the parameters is demonstrated using the classical insurance Danish fire loss data set and a French business loss interruption data set. Both data sets are publicly available. Developed models compare favorably with prior models fitted to the Danish fire loss data in the literature.

This article proposes a generalized class of univariate skew distributions that are constructed through partitioning two scaled mixture of normal (Gaussian) distributions. The proposed distributions have a skewness parameter defined in the interval (0,1), allowing direct application to parametric quantile regression. Employing scale mixture of normals facilitates efficient estimation via Markov chain Monte Carlo methods. Two simulation studies, one on estimation with skew error regression models, the other on parametric quantile regression models reveal favourable estimation properties. Two corresponding empirical studies, one analysing U.S. market returns, the other on infant birthweight data further illustrate the proposed distributions and their estimation. The Canadian Journal of Statistics 42: 579–596; 2014 © 2014 Statistical Society of Canada Résumé Les auteurs présentent une classe généralisée de lois univariées asymétriques construites à partir du partitionnement de deux mélanges normalisés de lois normales (gaussiennes). Les lois proposées possèdent un paramètre d'asymétrie défini dans l'intervalle (0,1), permettant une application directe à la régression quantile paramétrique. L'utilisation de mélanges normalisés de lois normales permet une estimation efficace au moyen d'algorithmes de Monte‐Carlo à chaî nes de Markov. Deux études de simulation portant sur la régression à erreur asymétrique et la régression quantile paramétrique révèlent des propriétés favorables pour l'estimation. Les auteurs illustrent les lois proposées et leur estimation pour ces deux types de modèles à l'aide d’études empiriques, une première portant sur l'analyse des rendements du marché des États‐Unis, et une seconde à propos de données sur le poids de bébés à la naissance. La revue canadienne de statistique xx: 1–18; 2014 © 2014 Société statistique du Canada

Gui et al. (2017) proposed the Lindley geometric distribution, derived its properties including estimation issues and illustrated a data application. We introduce a new family of distributions containing the Lindley geometric distribution as a particular case. The new family is shown to provide significantly better fits. We also point out errors in various properties derived by Gui et al. (2017).

In (Lawnik M., Generation of numbers with the distribution close to uniform with the use of chaotic maps, In: Obaidat M.S., Kacprzyk J., Ören T. (Ed.), International Conference on Simulation and Modeling Methodologies, Technologies and Applications (SIMULTECH) (28-30 August 2014, Vienna, Austria), SCITEPRESS, 2014) Lawnik discussed a method of generating pseudo-random numbers from uniform distribution with the use of adequate chaotic transformation. The method enables the “flattening” of continuous distributions to uniform one. In this paper a inverse process to the above-mentioned method is presented, and, in consequence, a new manner of generating pseudo-random numbers from a given continuous distribution. The method utilizes the frequency of the occurrence of successive branches of chaotic transformation in the process of “flattening”. To generate the values from the given distribution one discrete and one continuous value of a random variable are required. The presented method does not directly involve the knowledge of the density function or the cumulative distribution function, which is, undoubtedly, a great advantage in comparison with other well-known methods. The described method was analysed on the example of the standard normal distribution.