RDELA—a Delaunay-triangulation-based, location and covariance estimator with high breakdown point

We propose an approach that utilizes the Delaunay triangulation to identify a robust/outlier-free subsample. Given that the data structure of the non-outlying points is convex (e.g. of elliptical shape), this subsample can then be used to give a robust estimation of location and scatter (by applying the classical mean and covariance). The estimators derived from our approach are shown to have a high breakdown point. In addition, we provide a diagnostic plot to expand the initial subset in a data-driven way, further increasing the estimators’ efficiency.     

Multivariate spatial U-quantiles: A Bahadur–Kiefer representation,a Theil–Sen estimator for multiple regression,and a robust dispersion estimator

A leading multivariate extension of the univariate quantiles is the so-called “spatial” or “geometric” notion, for which sample versions are highly robust and conveniently satisfy a Bahadur–Kiefer representation. Another extension of univariate quantiles has been to univariate U-quantiles, on the basis of which, for example, the well-known Hodges–Lehmann location estimator has a natural formulation. Generalizing both extensions, we introduce multivariate spatial U-quantiles and develop a corresponding Bahadur–Kiefer representation. New statistics based on spatial U-quantiles are presented for nonparametric estimation of multiple regression coefficients, extending the classical Theil–Sen nonparametric simple linear regression slope estimator, and for robust estimation of multivariate dispersion. Some other applications are mentioned as well.     

Heteroskedasticity-consistent covariance matrix estimation:white's estimator and the bootstrap ∗

This paper considers the issue of estimating the covariance matrix of ordinary least squares estimates in a linear regression model when heteroskedasticity is suspected. We perform Monte Carlo simulation on the White estimator, which is commonly used in.

empirical research, and also on some alternatives based on different bootstrapping schemes. Our results reveal that the White estimator can be considerably biased when the sample size is not very large, that bias correction via bootstrap does not work well, and that the weighted bootstrap estimators tend to display smaller biases than the White estimator and its variants, under both homoskedasticity and heteroskedasticity. Our results also reveal that the presence of (potentially) influential observations in the design matrix plays an important role in the finite-sample performance of the heteroskedasticity-consistent estimators.     

Robustness and power of parametric, nonparametric, robustified and adaptive tests—The multi-sample location problem

This paper deals with a survey of different types of tests, parametric, nonparametric, robustified and adaptive ones, and with an application to the two-sided c-sample location problem. Some concepts of robustness are discussed, such as breakdown point, influence function, gross-error sensitivity and especially α- and β-robustness. A robustness study on level α in the case of heteroscedasticity and nonnormal distributions is carried out via Monte Carlo methods and also a power comparison of all the tests considered. It turns out that robustified versions of the F-test and Welch-test where the original observations are replaced by its ranks behave well over a broad class of distributions, symmetric ones with different tail weight and asymmetric ones, but, on the whole, an adaptive test is to prefer.     

Efficient time/space algorithm to compute rectangular probabilities of multinomial, multivariate hypergeometric and multivariate Pólya distributions

The computation of rectangular probabilities of multivariate discrete integer distributions such as the multinomial, multivariate hypergeometric or multivariate Pólya distributions is of great interest both for statistical applications and for probabilistic modeling purpose. All these distributions are members of a broader family of multivariate discrete integer distributions for which computationaly efficient approximate methods have been proposed for the evaluation of such probabilities, but with no control over their accuracy. Recently, exact algorithms have been proposed for computing such probabilities, but they are either dedicated to a specific distribution or to very specific rectangular probabilities. We propose a new algorithm that allows to perform the computation of arbitrary rectangular probabilities in the most general case. Its accuracy matches or even outperforms the accuracy exact algorithms when the rounding errors are taken into account. In the worst case, its computational cost is the same as the most efficient exact method published so far, and is much lower in many situations of interest. It does not need any additional storage than the one for the parameters of the distribution, which allows to deal with large dimension/large counting parameter applications at no extra memory cost and with an acceptable computation time, which is a major difference with respect to the methods published so far.     

The admissible minimax estimator in Gauss–Markov model under a balanced loss function

In this paper, we investigate the admissible minimax estimator (AME) of regression coefficient in Gauss–Markov model under a balanced loss function. In the class of homogeneous linear estimators, we obtain the AME under two occasions, respectively. We also prove that the AME is a shrinkage estimator of the best linear unbiased estimator (BLUE). Furthermore, we prove that the AME dominates the BLUE under certain conditions.     

The Mean,Median, and Confidence Intervals of the Kaplan-Meier Survival Estimate—Computations and Applications

This short note points out estimators of the mean, median, and the associated confidence intervals of the Kaplan-Meier product limit estimate. Some uses of the estimator of the mean are described. In addition, differences among popular software packages in the calculation of both the mean and median and associated confidence intervals are demonstrated and are due to default settings in the software. Simple examples of the calculations are provided using S-Plus, R, SAS, Stata, and SPSS.     

Discussion of “The power of monitoring: how to make the most of a contaminated multivariate sample” by Andrea Cerioli,Marco Riani,Anthony C. Atkinson and Aldo Corbellini

This paper discusses the contribution of Cerioli et al. (Stat Methods Appl, 2018), where robust monitoring based on high breakdown point estimators is proposed for multivariate data. The results follow years of development in robust diagnostic techniques. We discuss the issues of extending data monitoring to other models with complex structure, e.g. factor analysis, mixed linear models for which S and MM-estimators exist or deviating data cells. We emphasise the importance of robust testing that is often overlooked despite robust tests being readily available once S and MM-estimators have been defined. We mention open questions like out-of-sample inference or big data issues that would benefit from monitoring.     

An efficient approximate algorithm for the Kolmogorov—Smirnov and Lilliefors tests †

In an earlier paper we presented a linear time algorithm for computing the Kolmogorov–Smirnov and Lilliefors test statistics. In this paper we present a linear time approximate algorithm which requires less memory than the previous algorithm.     

Discussion of “The power of monitoring: how to make the most of a contaminated multivariate sample”

We contribute to the discussion of an article where Andrea Cerioli, Marco Riani, Anthony Atkinson and Aldo Corbellini review the advantages of analyzing multivariate data by monitoring how the estimated model parameters change as the estimation parameters vary. The focus is on robust methods and their sensitivity to the nominal efficiency and breakdown point. In congratulating with the authors for the clear and stimulating exposition, we contribute to its discussion with an overview of what we experienced in applying the monitoring in our application domain.     

Comments on “The power of monitoring: how to make the most of a contaminated multivariate sample”

These are comments on the invited paper “The power of monitoring: How to make the most of a contaminated multivariate sample” by Andrea Cerioli, Marco Riani, Anthony Atkinson and Aldo Corbellini.     

The Gauss—Markov Theorem and Random Regressors

In the standard linear regression model with independent, homoscedastic errors, the Gauss—Markov theorem asserts that = (X'X)^-1(X'y) is the best linear unbiased estimator of β and, furthermore, that is the best linear unbiased estimator of c'β for all p × 1 vectors c. In the corresponding random regressor model, X is a random sample of size n from a p-variate distribution. If attention is restricted to linear estimators of c'β that are conditionally unbiased, given X, the Gauss—Markov theorem applies. If, however, the estimator is required only to be unconditionally unbiased, the Gauss—Markov theorem may or may not hold, depending on what is known about the distribution of X. The results generalize to the case in which X is a random sample without replacement from a finite population.     

The Generalized Birnbaum–Saunders Distribution and Its Theory,Methodology, and Application

In this paper, we discuss the class of generalized Birnbaum–Saunders distributions, which is a very flexible family suitable for modeling lifetime data as it allows for different degrees of kurtosis and asymmetry and unimodality as well as bimodality. We describe the theoretical developments on this model including properties, transformations and related distributions, lifetime analysis, and shape analysis. We also discuss methods of inference based on uncensored and censored data, diagnostics methods, goodness-of-fit tests, and random number generation algorithms for the generalized Birnbaum–Saunders model. Finally, we present some illustrative examples and show that this distribution fits the data better than the classical Birnbaum–Saunders model.     

Nonparametrics: The Early Years—Impressions and Recollections

In 1942 Wolfowitz introduced the term nonparametric into the statistical literature to call attention to the need for extending then-existing statistical theory beyond the customary parametric framework. Subsequently, statistical methods that did not depend on a strictly parametric setup became known as nonparametric methods. This article surveys developments in nonparametrics roughly up to 1960. The suggestion is made that statistics might be better served by eliminating the term nonparametric altogether from the statistical vocabulary.     

The two-step approach—a significant ANOVA F-test before Dunnett's comparisons against a control—is not recommended

ABSTRACT

Decision-tree approaches are commonly used in the analysis of toxicological assays. This paper considers the widely-used and recommended approach of first applying the ANOVA F-test and, if it is significant, using the many-to-one comparison procedure of Dunnett (1955 Dunnett, C.W. (1955). A multiple comparison procedure for comparing several treatments with a control. J. Amer. Statist. Assoc. 50(272):1096–1121.[Taylor & Francis Online], [Web of Science ®] , [Google Scholar]). Data configurations are provided for which the F-test is not significant, but the Dunnett-test is significant. Because a conditional F-test before the Dunnett-test may increase the false negative rate, it is recommended that the ANOVA F-test not be used at all as a global pre-test. In addition, related non-parametric tests are investigated.     

The exponentiated exponential–geometric distribution: a distribution with decreasing,increasing and unimodal failure rate

In this paper, we proposed a new family of distributions namely exponentiated exponential–geometric (E2G) distribution. The E2G distribution is a straightforwardly generalization of the exponential–geometric (EG) distribution proposed by Adamidis and Loukas [A lifetime distribution with decreasing failure rate, Statist. Probab. Lett. 39 (1998), pp. 35–42], which accommodates increasing, decreasing and unimodal hazard functions. It arises on a latent competing risk scenarios, where the lifetime associated with a particular risk is not observable but only the minimum lifetime value among all risks. The properties of the proposed distribution are discussed, including a formal proof of its probability density function and explicit algebraic formulas for its survival and hazard functions, moments, rth moment of the ith order statistic, mean residual lifetime and modal value. Maximum-likelihood inference is implemented straightforwardly. From a mis-specification simulation study performed in order to assess the extent of the mis-specification errors when testing the EG distribution against the E2G, and we observed that it is usually possible to discriminate between both distributions even for moderate samples with presence of censoring. The practical importance of the new distribution was demonstrated in three applications where we compare the E2G distribution with several lifetime distributions.     

The uniform local asymptotics for a Lévy process and its overshoot and undershoot

ABSTRACT

In this article, we obtain the uniform local asymptotics for a Lévy process with a heavy-tailed Lévy measure and for the overshoot and undershoot of the Lévy process. As applications, we get the uniform asymptotics of the finite-time ruin probability and the local ruin probability for the Lévy risk model with a heavy-tailed Lévy measure. By the above results, we find that in the compound Poisson model perturbed by a Brownian motion, the effect of the Brownian component on the asymptotics of the finite-time ruin probability and the local ruin probability washes out.     

The Self‐Similar and Multifractal Nature of a Network Traffic Model

Abstract

We look at a family of models for Internet traffic with increasing input rates and consider approximation models which exhibit self‐similarity at large time scales and multifractality at small time scales. Depending on whether the input rate is fast or slow, the total cumulative input traffic can be approximated by a self‐similar stable Lévy motion or a self‐similar Gaussian process. The stable Lévy limit does not depend on the behavior of the individual transmission schedules but the Gaussian limit does. Also, the models and their approximations show multifractal behavior at small time scales.