Showing papers in "Statistics & Probability Letters in 2002"

TL;DR: In this article, a generalization of Hoeffding's inequality to partial sums that are derived from a uniformly ergodic Markov chain is presented. But the inequality is restricted to the case where the constants appearing in the bound are uniform.

TL;DR: In this paper, an approximation to the null distribution of Fisher's statistic for combining p-values when the underlying test statistics are jointly distributed as multivariate t with common denominator is presented.

TL;DR: In this article, an EM type algorithm is provided for the Maximum Likelihood estimation of the Normal-Inverse Gaussian distribution, which overcomes numerical difficulties occurring when standard numerical techniques are used.

TL;DR: In this paper, spatial autocorrelation in the mean response specification of the auto-Poisson model has been addressed by incorporating latent map pattern components, and results are reported for seven empirical datasets available in the literature.

TL;DR: In this article, it was shown that for r⩾1000 one has uniqueness as soon as q ⩾r+2. Computer calculations verify that the result is also true for 3⩽r.

TL;DR: In this paper, the connectivity distance cn, the smallest x for which Gn(x) is connected, is shown to satisfy ======(1)limn→∞cndnlogn=1,d= 1,12d,d⩾2,a.s.

TL;DR: In this paper, the authors derived the limiting spectral distribution of a particular variant of a circulant random matrix and showed that the convergence to the limit is quite fast and that the normal distribution for a symmetric version of the Toeplitz matrix is the normal one.

TL;DR: In this article, an almost sure limit theorem for the maxima of stationary Gaussian sequences with covariance rn under the condition r n log n( log log n) 1+e = O (1).

TL;DR: In this article, the authors derived a simultaneous confidence band for the ratio of two survival functions based on independent right-censored data, which is formulated in terms of empirical likelihood and allows them to avoid the use of simulation techniques that are often needed for Wald-type confidence bands.

TL;DR: This paper introduces a variable selection approach to identifying the active effects in SSD via nonconvex penalized least squares via an iterative ridge regression to find the solution of the penalize least squares.

TL;DR: In this paper, a unified method based on a finite Markov chain approach for finding the run length distribution and the average run length of a control scheme is developed, which yields the variance or standard deviation of the running length as a byproduct.

TL;DR: This article presented a variation of the simex algorithm appropriate for the case in which the measurement error variance variance(s) are unknown but replicate measurements are available, using pseudo errors generated from random linear contrasts of the observed replicate measurements.

TL;DR: In this paper, lower bounds for the explosion and implosion breakdown points of the simultaneous Cauchy M-estimator of the regression and scale parameters are derived, for appropriate tuning constants, the breakdown point attains the maximum possible value.

TL;DR: For a random walk with negative mean and heavy-tailed increment distribution, it is well known that under suitable subexponential assumptions, the distribution pi of the maximum has a tail pi(x, infinity) which is asymptotically proportional to integral(x)(infinity)F(y, infinity) dy as discussed by the authors.

TL;DR: In this article, an exact random variate generation for the Bessel distribution is discussed. But the expected time of the algorithm is uniformly bounded over all choices of the parameters, and the algorithm avoids any computation of Bessel functions or Bessel ratios.

TL;DR: The univariate and multivariate skew-normal distributions have a number of intriguing properties as mentioned in this paper, and it is shown that these hold for a general class of distributions, defined in terms of independence conditions on signs and absolute values.

TL;DR: In this paper, the marginal and joint density functions of order statistics under progressive censoring were derived in explicit form and used to obtain an efficient method for computing the desired moments, which is an alternative, highly efficient, method.

TL;DR: In this article, robust model selection procedures are introduced as a robust modification of the Akaike information criterion (AIC) and Mallows Cp. These extensions are based on the weighted likelihood methodology.

TL;DR: In this paper, the authors extended this result to the case where the underlying probability is itself not fixed, but varies over a family of measures, and derived explicit upper bounds on the rate at which the empirical means converge to their true values, when the underlying process is β-mixing.

TL;DR: In this paper, the authors discuss the breakdown behavior of the maximum likelihood estimator in the logistic regression model and formally prove that the ML estimator never explodes to infinity, but rather breaks down to zero when adding severe outliers to a data set.

TL;DR: Some general results are laid out that can be used to identify dependence parameter(s) with respect to the supermodular dependence ordering for a parametric family of copulas constructed through mixing and limits.

TL;DR: In this paper, two nonparametric imputation schemes are considered: risk set imputation and Kaplan-Meier imputation, where the censored time is replaced by a random draw of the observed times amongst those at risk after the censoring time.

TL;DR: In this article, the authors show that a semiparametric bootstrap will consistently underestimate the variation in the data in 3nite samples, and demonstrate that such a bootstrap is not a good choice for mixed models.

TL;DR: This paper showed that the distribution of the minimum and maximum of two random variables whose distribution is bivariate normal centered at the origin is a mixture with equal weights of scaled skew-normal distributions.

TL;DR: In this article, an explicit formulae for the probability that the Brownian motion up-crosses in [0,T], a piecewise-linear function S(t), with the condition that the value of Bt is assigned at a future time u>T or at an intermediate time u.

TL;DR: In this article, the goodness of fit test of the errors of autoregressive models using the kernel estimate of the marginal density function based on residuals was considered and the test statistic is based on the integrated squared error of the nonparametric density estimate and a smoothed version of the parametric fit of the density.

TL;DR: A generalization of the Erdos-Renyi formulation of the Borel-Cantelli lemma is presented in this paper, where the authors show that it can be expressed as

TL;DR: In this article, a test for the validity of scalar-adjusted normal-theory procedures can be viewed as a test on the structure of the matrix of fourth-order moments.

TL;DR: In this paper, a new formulation of bivariate binomial distribution is proposed, in which marginally each of the two random variables has a binomial distributions and they have some nonzero correlation in the joint distribution.

TL;DR: In this article, a method of computing the maximum likelihood estimator of the receiver operating characteristic (ROC) curve assuming convexity has been presented, which is of interest in its own right, when it is believed that the decision variable is monotonically related to the likelihood of disease.