Showing papers in "Computational Statistics & Data Analysis in 1998"

TL;DR: In this article, different formulations for the overdispersion mechanism can lead to different variance functions which can be placed within a general family of estimation methods, including maximum likelihood, moment methods, extended quasi-likelihood, pseudo-like likelihood and non-parametric maximum likelihood.

TL;DR: In this paper, the relationship between two coefficients used in sensitivity analysis of model output is investigated, namely the Fourier amplitude sensitivity test's coefficient and the Sobol' sensitivity indices, developed in the 1990s.

TL;DR: A difference penalty on adjacent B-spline coefficients is incorporated into a penalized version of the Fisher scoring algorithm, and each component has a separate smoothing parameter, and the penalty is optimally regulated through extensions of cross validation or information criterion.

TL;DR: Some of previously indicated errors in Microsoft Excel 97 and Excel XP have been eliminated in Excel 2003 but some others have not been corrected and new ones have been found as is shown by numerical examples.

TL;DR: Three methods for estimating the three-dimensional position of a point via trilateration are presented: a linear least- Squares estimator, an iteratively reweighted least-squares estimators, and a non-linear least-Squares technique.

TL;DR: This paper pursues three objectives in the context of multiple regression models: to give a rationale for model selection criteria which combine a badness of fit term with a measure of complexity of a model.

TL;DR: In this paper, a simple way of constructing a bivariate boxplot based on convex hull peeling and B-spline smoothing is proposed, which leads to defining a natural inner region which is completely nonparametric and smooth.

TL;DR: Partially ordered Markov models (POMMs) as mentioned in this paper are a subset of the class of MRFs but have probability distributions that can be written in closed form and are used for texture synthesis and the inverse problem of parameter estimation.

TL;DR: Diversity, as a desirable approach for addressing the classes of faults that underlay all these topics, i.e., design faults and intrusion faults, is focused on.

TL;DR: In this paper, wavelet regression estimators are introduced, both in the random and the irregular design cases and without the restriction that the sample size is a power of two, and a fast computational algorithm for approximating the empirical counterpart of the scaling and wavelet coefficients is developed.

TL;DR: A new method for detection of outliers which is very resistant to such high contamination of data with outliers is proposed and detects outliers better than the Rocke and Woodruff method for data highly contaminated (35–45%) with outlier.

TL;DR: In this article, the statistical inference problem for the geometric process is studied under the assumption that X1 follows a Gamma distribution, and the parameters a, μ and σ2, where μ is respectively, the mean and variance of X1, are estimated by parametric methods including maximum likelihood method along with some nonparametric methods previously proposed by Y. Lam such as the modified moment method.

TL;DR: In this paper, order n algorithms are developed for computing the estimated mean vector, regression coefficients, standard errors and smoothing parameter selection criteria for Speckman smoothing spline estimators in partially linear models.

TL;DR: The limits of formal methods are reviewed and some recent results on how model checking and theorem proving tools revealed new and known flaws in authentication protocols are summarized.

TL;DR: A new clustering-based approach for multiple outlier identification that utilizes the predicted and residual values obtained from a least squares fit of the data is proposed.

TL;DR: In this article, the properties of most important estimators of long-range dependence parameters are compared via Monte Carlo experiments and an empirical approach for confidence intervals for the different parameter estimates is given.

TL;DR: In this article, the maximum likelihood and maximum penalized likelihood (MPL) procedures are applied to deconvolve image data which has been degraded by blurring and Poisson variability in recorded activity.

TL;DR: In this article, the authors present estimation and likelihood-ratio testing for various monotone trend alternatives to independence in contingency tables with ordered categories, characterized by non-negative values for four types of log odds ratios for ordinal data: Local, global, cumulative, and continuation ratios.

TL;DR: Based on the theory of spherical distributions, a multivariate version of Ghosh (1996)'s T3plot (MT3-plot) is proposed to detect non-multinormality as discussed by the authors.

TL;DR: In this paper, a Bayesian analysis is used to detect a change point in a sequence of independent random variables from exponential family distributions, and the marginal posterior distribution of the change point j is derived.

TL;DR: The relevance of the security concept of noninterference to safety-related properties, and conversely, the applicability of fault-tolerance mechanisms usually applied to provide safety and reliability in the security domain are examined.

TL;DR: In this article, the SIMPLIMAX method is generalized to handle three-way arrays, where the minimum sum of the m smallest elements of the rotated core array is minimized.

TL;DR: Here, models induced by several competing weight functions are compared, including one model which does not account for publication bias, and such models are fit hierarchically from a Bayesian perspective using non-informative priors in order to let the data drive the inference.

TL;DR: In this paper, the authors derived MHD estimates for finite Poisson mixtures and compared their performance relative to that of the ML estimators, and provided a numerical example involving data sets on environmental complaints.

TL;DR: The need for a clear set of system dependability concepts and terminology, adequate for situations in which there are uncertainties about system boundaries, and the very complexity of systems is a major problem is discussed.

TL;DR: In this article, the aligned rank transform procedure for the factorial designs is formulated and the alignment analogues of some well-known multiple comparison procedures are developed, and the asymptotic validity of these procedures is proved.

TL;DR: In this article, a nonparametric bootstrap is used to estimate the optimal number of extremes to be used for the tail index estimation and the second bootstrap to obtain confidence intervals.

TL;DR: In this paper, the authors study thirteen new methods and show that the new method based on Fisher's mid-p value is a solution halfway between methods Z and F1 (for every values of K), which frequently surpasses in power, and approaching the B and B′ methods, especially in large samples (where B or B′ can not be applied).

TL;DR: In this article, the ordinal principal component is defined as a new ordinal variable which orders the sample observations in such a way that the sum of the squares of the rank correlation coefficients between the original variables and the principal components is maximal.

TL;DR: In this article, the authors proposed a nonparametric bootstrap solution for the open problem of obtaining workable finite sample confidence intervals of these estimators, based on the minimization of the asymptotic mean squared error.