Multiple Window and Cluster Size Scan Procedures

Researchers apply scan statistics to test for unusually large clusters of events within a time window of specified length w, or alternatively an unusually small window w that contains a specified number of events. In some cases, the researcher is interested in testing for a range of specified window lengths, or a set of several specified number of events k (cluster sizes). In this paper, we derive accurate approximations for the joint distributions of scan statistics for a range of values of w, or of k, that can be used to set an experiment-wide level of significance that takes into account the multiple comparisons involved. We use these methods to compare different ways of choosing the window sizes for the different cluster sizes. One special case is a multiple comparison procedure based on a generalized likelihood ratio test (GLRT) for a range of window sizes. We compare the power of the GLRT with another method for allocating the window sizes. We find that the GLRT is sensitive for very small window sizes at the expense of moderate and larger window sizes. We illustrate these results on two examples, one involving clustering of translocation breakpoints in DNA, and the other involving disease clusters.     

Thermo-XRD analysis of the adsorption of Congo-red by montmorillonite saturated with different cations

The adsorption of the organic anionic dye Congo red (CR) by montmorillonite saturated with Na⁺, Cs⁺, Mg²⁺, Cu²⁺, Al³⁺ and Fe³⁺ was investigated by XRD of unwashed and washed samples after equilibration at 40% humidity and after heating at 360 and at 420°C. The clay was treated with different amounts of CR, most of which was adsorbed. Clay samples, untreated with CR, after heating showed collapsed interlayer space. Unwashed and washed samples, which contained CR, before heating were characterized by three peaks or shoulders, labeled A (at 0.96-0.99 nm, collapsed interlayers), B (at 1.24-1.36 nm) and C (at 2.10-2.50 nm). Peak B represents adsorbed monolayers of water and dye anions inside the interlayer spaces. Peak C represents interlayer spaces with different orientations of the adsorbed water and organic matter. Diffractograms of samples with small amounts of dye were similar to those without dye showing peak B whereas diffractograms of most samples with high amounts of dye showed an additional peak C. Heated unwashed and washed samples were also characterized by three peaks or shoulders, labeled A' (at 0.96 nm), B' (at 1.10-1.33 nm) and C' (at 1.61-2.10 nm), representing collapsed interlayers, and interlayers with charcoal composed of monolayers or multilayers of carbon. When the samples were heated from 360 to 420°C some of the charcoal monolayers underwent rearrangement to multilayers. In the case of Cu the charcoal decomposed and oxidized. The present results show that most of the adsorbed dye was located inside the interlayer space.This revised version was published online in November 2005 with corrections to the Cover Date.     

Large gaps between consecutive zeros of the Riemann zeta-function

Combining the amplifiers, we exhibit other choices of coefficients that improve the results on large gaps between the zeros of the Riemann zeta-function. Precisely, assuming the Generalized Riemann Hypothesis (GRH), we show that there exist infinitely many consecutive gaps greater than 3.033 times the average spacing.     

The empirical distribution function and strong laws for functions of order statistics of uniform spacings

Let N points be arbitrarily chosen on the circle with unit circumference, and order them clockwise. The uniform mth order spacings are then defined as the clockwise distances between any pair of points having m − 1 other points in between. A Glivenko-Cantelli theorem and nonlinear almost sure bounds for the empirical distribution function based on these uniform spacings are derived. The parameter m is allowed to increase with N to infinity. Applications to linear combinations of functions of mth order spacings are given.     

On exponential scores statistics for testing against positive aging

It has been shown in this paper that a test proposed by Barlow and Doksum (1972) based on the exponential scores statistic for testing exponentiality against increasing failure rate distributions is consistent for the much wider class of harmonic new better than used in expectation distributions.     

Theoretical study of the electronic structure of LiNa and LiNa<Superscript>+</Superscript> molecules

Adiabatic potential energy, spectroscopic constants, dipole moments, and vibrational levels of the lowest electronic states of the alkali dimer LiNa molecule dissociating into Na (3s, 3p, 4s, 3d, and 4p) + Li (2s, 2p, 3s, and 3p) in ^1,3Σ, ^1,3Π, and ^1,3Δ symmetries are presented. Adiabatic results are also reported for ²Σ, ²Π, and ²Δ electronic states of the molecular ion LiNa⁺ dissociating into Li (2s, 2p, 3s, and 3p) + Na⁺ and Li⁺  + Na(3s, 3p, 4s, 3d, and 4p). We use an ab initio approach involving a non-empirical pseudopotential for the Li (1s²) and Na (1s²2s²2p⁶) cores and core valence correlation correction. A very good agreement is obtained for some lowest states of the LiNa and LiNa⁺ molecules for spectroscopic constants with the available theoretical works. The existence of numerous avoided crossings between electronic states of ²Σ and ²Π symmetries is related to the charge transfer process between the two ionic systems Li⁺Na and LiNa⁺.     

Mean sample spacings, sample size and variability in an auction-theoretic framework

In terms of a standard model for English auctions and sealed-bid auctions, we study the impact of an increase in bidding competition and in variance of the distribution of valuations on the winner's expected rent using tools from order statistics and stochastic ordering.     

Random suffix search trees

A random suffix search tree is a binary search tree constructed for the suffixes X_i = 0 · B_iB_i+1B_i+2… of a sequence B₁, B₂, B₃, … of independent identically distributed random b‐ary digits B_j. Let D_n denote the depth of the node for X_n in this tree when B₁ is uniform on ?_b. We show that for any value of b > 1, ??D_n = 2 log n + O(log²log n), just as for the random binary search tree. We also show that D_n/??D_n → 1 in probability. © 2003 Wiley Periodicals, Inc. Random Struct. Alg., 2003     

Bahadur efficiencies of spacings tests for goodness of fit

This paper is concerned with the exact Bahadur efficiencies of spacings statistics. For a general class of statistics based on a fixed number of spacings, the explicit forms of the exact slopes are derived, and it is shown that the sum of the logarithms of spacings is optimal in this class. Some results are extended to the case where the number of spacings increase with the sample size to infinity.