Showing papers in "Statistics & Probability Letters in 2015"

TL;DR: Based on the effect hierarchy principle in experimental design, an aliased effect-number pattern (AENP, or AP for short) is proposed to judge two-level regu- lar designs; it contains the basic information of all effects aliased with other effects at varying severity degrees in a design.

TL;DR: In this paper, the first-exit time of a tempered β-stable subordinator, also called inverse tempered stable (ITS) subordinator was investigated and the limiting form of the ITS density and its k-th order derivatives were derived as the space variable x → 0 +.

TL;DR: In this article, the likelihood ratio order and the stochastic order between minimums of independent and dependent samples, respectively, were studied for heterogeneous Weibull samples with a common shape parameter and weakly majorized scale parameters.

TL;DR: In this article, the authors study the system lifetime mixed δ -shock models and obtain the survival function of the system under these new shock models, where the system fails when the time between two successive shocks is smaller than a critical threshold or the magnitude of the shock (the cumulative magnitude of shocks) is larger than another critical threshold γ.

TL;DR: In this paper, a new bivariate distribution with beta marginal distributions, positive probability over the unit square, and correlations over the full range was proposed, which can be extended to three or more dimensions.

TL;DR: Here the optimal design for a fixed number of periods is derived; this does not allocate an equal number of cluster units to each treatment sequence as might otherwise have been expected.

TL;DR: In this article, the authors discuss stochastic comparisons of parallel systems with exponentiated Weibull components in terms of the usual dispersive order and the likelihood ratio order, and give some sufficient conditions for the comparison.

TL;DR: This article proposed a nonparametric variance estimator when ranked set sampling (RSS) and judgment post stratification (JPS) are applied by measuring a concomitant variable.

TL;DR: This work proposes extensions of classical FOBI and JADE estimates for multivariate time series, with a special focus on time series with stochastic volatility.

TL;DR: In this article, the distribution of random correlation matrices using the hyperspherical parameterization of their Cholesky factors and the distributions of the related angles is studied. And the roles of this procedure in generating high-dimensional correlation matures are highlighted.

TL;DR: In this article, the optimal foldover plans for two-level designs in terms of the uniformity criteria measured by Lee, symmetric, wrap-around and centered discrepancy were studied.

TL;DR: This paper showed that an elicitable distortion risk measure is either a Value-at-Risk or the mean, and discussed the conflict between comonotonic additivity and elicitability.

TL;DR: In this article, concentration inequalities for extrema of stationary Gaussian processes were studied and the authors provided nonasymptotic tail inequalities which fully reflect the fluctuation rate, and as such improved upon standard Gaussian concentration.

TL;DR: In this paper, new estimators for the parameters of the Gamma distribution are proposed, which are used for constructing a test of fit for this model based on the ratio of two variance estimators.

TL;DR: In this article, the authors considered the limit theorems for discrete time Hawkes processes and obtained the law of large number, the central limit theorem and the invariance principle.

TL;DR: In this article, a multivariate EWMA control chart based on a variable selection using AIC was proposed, where not all variables but a few variables may shift from the in-control state.

TL;DR: In this article, the authors explored confidence intervals for the family of proportional reversed hazard distributions based on lower record values, and the confidence intervals are validated as long as the sample is of size n ≥ 3.

TL;DR: In this article, the authors proposed an estimator that has a smaller bias and better coverage probability than the traditional estimator of Kendall's τ for zero-inflated continuous distributions.

TL;DR: A sandwich likelihood correction is proposed to remedy an inferential limitation of the Bayesian quantile regression approach based on the misspecified asymmetric Laplace density, by leveraging the benefits of the approach.

TL;DR: In this paper, the truncated Karhunen-Loeve expansion is used for approximating the maximum a posteriori (MAP) solutions to infinite dimensional Bayesian inverse problems.

TL;DR: In this paper, the optimal foldover plans for three-level designs with multi-level factors with the uniformity criterion measured by the Lee discrepancy were identified by an exhaustive search.

TL;DR: In this paper, Zhou et al. proposed a new discrepancy measure, mixture discrepancy (MD), and showed that MD may be a better uniformity measure than wrap-around L 2 -discrepancy and centered L 2 −disparance.

TL;DR: Brown et al. as discussed by the authors derived a Stein-type inequality for the multivariate Student's t -distribution and generalized their result to the family of generalized hyperbolic distributions and derived a lower bound for the variance of a function of a random variable.

TL;DR: In this paper, a method for sequential detection of structural changes in linear quantile regression models is proposed, and the authors establish the asymptotic properties of the proposed test statistic, and demonstrate the advantages of their proposed method over existing tests through simulation.

TL;DR: In this paper, the weak law of large numbers for sums of negatively associated random vectors in Hilbert spaces is established, and it is shown that such conditions cannot be dispensed with.

TL;DR: In this article, the authors studied the oracle property of group SCAD under high dimensional settings where the number of groups can grow at a certain polynomial rate, and presented numerical studies to demonstrate the merit of the SCAD.

TL;DR: In this article, the class of all finite mixtures of skew-normal distributions with null location parameter is proved to be identifiable, and the real moments of a skew-t random variable are explicitly obtained in a closed-form.

TL;DR: In this paper, the authors discuss in depth the mixture discrepancy as the uniformity measure for symmetric two-, three-and four-level balanced designs and show that it is more reasonable than other discrepancies for measuring uniformity from different aspects such as the intuitive view, the uniformness of sub-dimension projection, the curse of dimensionality and the geometric property of the kernel function.

TL;DR: Theoretical results and simulation studies show the good performance of the proposed new scalar and shift transform invariant test statistic for the high-dimensional two-sample location problem.