Refined crystal structure of methylamine dehydrogenase from Paracoccus denitrificans at 1.75 A resolution

We extend the random intercept logistic model to accommodate negative intracluster correlations for bivariate binary response data. This approach assumes a single random effect per cluster, but entails separate affine transformations of this random effect for the two responses of the pair. We show this approach works for two data sets and a simulation, whereas other mixed effects approaches fail. The two data sets are from a crossover trial and a developmental toxicity study of the effects of chemical exposure on malformation risk among rat pups. Comparisons are made with the conditional likelihood approach and with generalized estimating equations estimation of the population-averaged logit model. Simulations show the conditional likelihood approach does not perform well for moderate to strong negative correlations, as a positive intracluster correlation is assumed. The proposed mixed effects approach appears to be slightly more conservative than the population-averaged approach with respect to coverage of confidence intervals. Nonetheless, the statistical literature suggests that mixed effects models provide information in addition to that provided by population-averaged models under scientific contexts such as crossover trials. Extensions to trivariate and higher-dimensional responses also are addressed. However, such extensions require certain constraints on the correlation structure.     

Biochemical requirements for the targeting and fusion of ER-derived transport vesicles with purified yeast Golgi membranes

Because of limitations of the univariate frailty model in analysis of multivariate survival data, a bivariate frailty model is introduced for the analysis of bivariate survival data. This provides tremendous flexibility especially in allowing negative associations between subjects within the same cluster. The approach involves incorporating into the model two possibly correlated frailties for each cluster. The bivariate lognormal distribution is used as the frailty distribution. The model is then generalized to multivariate survival data with two distinguished groups and also to alternating process data. A modified EM algorithm is developed with no requirement of specification of the baseline hazards. The estimators are generalized maximum likelihood estimators with subject-specific interpretation. The model is applied to a mental health study on evaluation of health policy effects for inpatient psychiatric care.     

地下煤火燃空区冒落岩体孔隙率随机分布规律

本文经随机实验统计分析得出孔隙率函数（3lnφ-2ln（1-φ））近似服从正态分布,在实验的粒径范围内（30~180 mm）,其期望值和方差都随着岩块粒径的增大而增大.在推导出岩层二维下沉曲面方程的基础上,先后推演出燃空区冒落岩体孔隙率的连续非均质分布模型和随机离散化非均质分布模型.依据模型计算矩形煤火空间得出以下结果：燃空区浅部及边缘侧冒落岩体的孔隙率大,而中间区域孔隙率小;孔隙率等值线在x-y平面上的投影呈侧躺的＂U＂形分布;沿x轴,随着深入燃空区距离的增加,孔隙率呈类负指数形式衰减.此外,孔隙率连续分布和随机离散化分布,在整体的变化趋势上是相同的,区别之处在于后者所表示的孔隙率具有一定的随机波动性.将上述随机离散化模型应用在某火区温度场的数值模拟中,并经现场红外测温验证了模拟的准确性和孔隙率模型的适用性.     

Fractional Steps Scheme of Finite Analytic Method for Advection–Diffusion Equation

For simply finding local analytic solution, the time derivative in the traditional finite analytic (FA) method is generally replaced with a first-order finite difference approximation as a source term. However, this may induce excessive numerical diffusion, especially for advection-dominated transport problems. In this paper, a fractional steps scheme of the FA method without using the finite difference approximation to time derivative is proposed by applying the one-dimensional FA method whose local analytic solution is obtained from both spatial and time domains, together with the method of fractional steps. Four hypothetical examples, including two-dimensional and three-dimensional cases, are employed to investigate this newly proposed method as compared with the traditional FA method, the optimal unsteady FA method, and the alternating direction scheme of the hybrid FA method. The results show that the fractional steps scheme of the FA method can greatly diminish numerical diffusion and is superior to the other methods compared herein.     

Generalized Lévy-walk model for DNA nucleotide sequences

We propose a generalized Lévy walk to model fractal landscapes observed in noncoding DNA sequences. We find that this model provides a very close approximation to the empirical data and explains a number of statistical properties of genomic DNA sequences such as the distribution of strand-biased regions (those with an excess of one type of nucleotide) as well as local changes in the slope of the correlation exponent alpha. The generalized Lévy-walk model simultaneously accounts for the long-range correlations in noncoding DNA sequences and for the apparently paradoxical finding of long subregions of biased random walks (length lj) within these correlated sequences. In the generalized Lévy-walk model, the lj are chosen from a power-law distribution P(lj) varies as lj(-mu). The correlation exponent alpha is related to mu through alpha = 2-mu/2 if 2 < mu < 3. The model is consistent with the finding of "repetitive elements" of variable length interspersed within noncoding DNA.     

Level A in vivo-in vitro correlation: nonlinear models and statistical methodology

Some new nonlinear models for the relationship between the fraction of drug dose dissolved (absorbed) in vivo and that dissolved in vitro are described. The models are empirical in nature and are generalizations of the linear model that, at present, is the most commonly used model. The modeling approach is based on considering the time at which a drug molecule goes into solution (in vitro or in vivo) to be a random variable and relating the distribution functions using proportional odds, proportional hazards, and proportional reversed hazards models. The models are further extended by allowing the parameter that relates in vivo and in vitro to be a function of time. A statistical model for the data is developed and used as the basis for a statistical methodology for fitting these models. The methods are shown to be generalized linear mixed effects model (GLMM) methods. The models are fitted to some data sets, and the results demonstrate that these models have potential.     

Stochastic Response of a Random Mass Structure

This paper proposes a polynomial approximation approach for the estimation of the stochastic response of a random mass structure subjected to an evolutionary random excitation. A bounded, monopeak, and symmetrically distributed probability density function, called λ-PDF, together with the Gegenbauer polynomial approximation, is introduced to deal with stochastic dynamic response problems of the random mass structures. The λ-PDF model is used to describe the random parameters in the engineering random structures. And then the Gegenbauer polynomial approximation method is used to reduce the random structures into its deterministic equivalent one. The numerical example shows the effectiveness of the proposed method to explore dynamic phenomena in random structures.     

基于广义归纳逻辑因果模型的知识发现与算法实现

以语言场、广义细胞自动机和广义归纳逻辑因果模型为理论依据,分析了广义因果联系类知识的发现机理,给出了因果联系类知识发现的实现算法.该算法为解决具有随机不确定和模糊不确定性特征的因果联系类知识的发现提供了行之有效的方法.通过算法的运行实例,验证和说明了算法的正确性和有效性.     

Iteratively reweighted least squares mapping of quantitative trait loci

Mapping quantitative trait loci (QTL) is a typical problem of regression with uncertain independent variables because the genotype of a putative QTL is not observed. Rather, the genotype is inferred from marker information. The method of maximum likelihood (ML) methods is considered to be the optimal solution for this problem because the distribution of the unobserved QTL genotype is fully taken into account. The simple linear regression method (REG) is a first-order approximation to ML and usually performs very well. In this study, an iteratively reweighted least squares method (IRWLS) is proposed. The new method is a second-order approximation to ML because both the expectation and the variance of the unobserved QTL genotype are taken into consideration. The IRWLS is developed in the context of a single large outbred family. The properties of IRWLS are demonstrated and compared with REG and ML via replicated Monte Carlo simulations. The conclusions are: (1) when marker information content is high, the three methods perform equally well, but ML and IRWLS outperform REG when marker information content is low and the variance explained by the QTL is high; (2) when the residual distribution is not normal, ML can fail or have low power to detect small QTLs, but REG and IRWLS are robust to non-normality; and (3) when the residual distribution is normal, the performance of IRWLS is almost identical to ML, but the computational speed of IRWLS is many times faster than that of ML.     

Reliability Analysis Using Parabolic Failure Surface Approximation

In the second-order reliability method the failure surface is approximated by a general quadratic surface in the neighborhood of the design point. In this paper this general quadratic surface is further approximated by a parabolic surface. Several methods are proposed to obtain the probability content associated with this parabolic failure surface. It is assumed that the basic random variables are Gaussian. The proposed methods can be broadly grouped into: (1) nonasymptotic approximate methods, (2) exact methods, and (3) asymptotic distribution methods. Most of these methods result in a closed-form expression for the failure probability. For nonasymptotic approximations, a least-square approach and an optimal point expansion method using approximate probability density functions of a quadratic form in Gaussian random variables have been proposed. It is shown that such approximations give accurate results without significant numerical effort. Exact results, however, require greater numerical effort. The new asymptotic result is derived for the case when the number of random variables approaches infinity. Several numerical examples are provided to compare the proposed results with existing equivalent results and Monte Carlo simulations.     

Conceptualizing and testing random indirect effects and moderated mediation in multilevel models: New procedures and recommendations.

The authors propose new procedures for evaluating direct, indirect, and total effects in multilevel models when all relevant variables are measured at Level 1 and all effects are random. Formulas are provided for the mean and variance of the indirect and total effects and for the sampling variances of the average indirect and total effects. Simulations show that the estimates are unbiased under most conditions. Confidence intervals based on a normal approximation or a simulated sampling distribution perform well when the random effects are normally distributed but less so when they are nonnormally distributed. These methods are further developed to address hypotheses of moderated mediation in the multilevel context. An example demonstrates the feasibility and usefulness of the proposed methods. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Calcium and mechanically induced potentials in fibroblasts of rat atrium

Pattern-mixture models stratify incomplete data by the pattern of missing values and formulate distinct models within each stratum. Pattern-mixture models are developed for analyzing a random sample on continuous variables y(1), y(2) when values of y(2) are nonrandomly missing. Methods for scalar y(1) and y(2) are here generalized to vector y(1) and y(2) with additional fixed covariates x. Parameters in these models are identified by alternative assumptions about the missing-data mechanism. Models may be underidentified (in which case additional assumptions are needed), just-identified, or overidentified. Maximum likelihood and Bayesian methods are developed for the latter two situations, using the EM and SEM algorithms, direct and interactive simulation methods. The methods are illustrated on a data set involving alternative dosage regimens for the treatment of schizophrenia using haloperidol and on a regression example. Sensitivity to alternative assumptions about the missing-data mechanism is assessed, and the new methods are compared with complete-case analysis and maximum likelihood for a probit selection model.     

Galerkin Solution for Linear Stochastic Algebraic Equations

Algebraic equations with random coefficients, referred to as stochastic algebraic equations, are used extensively to solve approximately differential equations describing mechanics problems with uncertain material properties and applied loads. This paper (1) constructs optimal and suboptimal Galerkin solutions for linear stochastic algebraic equations, (2) reviews current procedures for deriving stochastic algebraic equations from stochastic differential equations and proposes alternative methods, (3) demonstrates the implementation of the proposed Galerkin method by numerical examples, and (4) calculates statistics of the displacement field for a plate on random elastic foundation. The optimal Galerkin solution coincides with the conditional expectation of the exact solution with respect to a σ-field coarser than the σ-field relative to which the exact solution is measurable, and is unbiased. Generally, suboptimal Galerkin solutions are biased but may provide approximations for the tails of the distribution of the exact solution that are superior to those by the optimal Galerkin solution.     

Combined scatter and attenuation correction for 201Tl myocardial perfusion SPECT using OS-EM algorithm

There are two possible ways to obtain scatter-corrected images with the ML-EM (maximum likelihood expectation maximization) algorithm: one is the subtraction of scatter estimate si from projection data pi, and then (pi-si) is used for scatter-corrected projection data (denoted as SC(T)); the other method is the addition of scatter estimate si to the projections calculated from the reconstructed image without performing data subtraction (SC(E)). This paper investigated these two ML-EM algorithms of combined scatter and attenuation correction on 201Tl myocardial perfusion SPECT imaging. Scatter windows were placed one full width at half maximum (FWHM) below and above the photopeak centerline. The scatter fraction in the primary peak was estimated using trapezoidal approximation by the triple energy window method. Phantom and clinical images were reconstructed using 6 iterations of ordered subsets EM algorithm (OS-EM). A cylindrical phantom with a cold-rod insert and a heart/thorax phantom with liver insert were used to evaluate scatter and the attenuation compensation technique. A cylindrical phantom filled with uniform 201Tl solution was used to evaluate statistical noise. The percent root-mean-square uncertainty (%RMSU) was used as a quantitative measure of noise amplification. %RMSU showed that the SC(E) method amplified noise less in comparison with the SC(T) method, however, no significant difference in image quality was observed between the two methods. In conclusion, both the SC(T) and SC(E) methods provided significant and similar improvement in the removal of scatter in 201Tl myocardial perfusion SPECT imaging.     

Unsupervised Learning for Efficient Texture Estimation From Limited Discrete Orientation Data

The estimation of orientation distribution functions (ODFs) from discrete orientation data, as produced by electron backscatter diffraction or crystal plasticity micromechanical simulations, is typically achieved via techniques such as the Williams–Imhof–Matthies–Vinel (WIMV) algorithm or generalized spherical harmonic expansions, which were originally developed for computing an ODF from pole figures measured by X-ray or neutron diffraction. These techniques rely on ad-hoc methods for choosing parameters, such as smoothing half-width and bandwidth, and for enforcing positivity constraints and appropriate normalization. In general, such approaches provide little or no information-theoretic guarantees as to their optimality in describing the given dataset. In the current study, an unsupervised learning algorithm is proposed which uses a finite mixture of Bingham distributions for the estimation of ODFs from discrete orientation data. The Bingham distribution is an antipodally-symmetric, max-entropy distribution on the unit quaternion hypersphere. The proposed algorithm also introduces a minimum message length criterion, a common tool in information theory for balancing data likelihood with model complexity, to determine the number of components in the Bingham mixture. This criterion leads to ODFs which are less likely to overfit (or underfit) the data, eliminating the need for a priori parameter choices.     

Evaluating interventions with differential attrition: The importance of nonresponse mechanisms and use of follow-up data.

Evaluations of psychological interventions are often criticized because of differential attrition (DA), which is cited as a severe threat to validity. The present study shows that DA is not a problem unless the mechanism causing the attrition is inaccessible (unavailable for analysis). With a simulation study, it is shown that conclusions about program effects (1) are unbiased when there is no DA, even with usual complete cases analysis; (2) may be severely biased when based on usual complete cases analyses and there is DA; (3) are unbiased when based on the expectation-maximization (EM) algorithm, even when there is DA, as long as the attrition mechanism is accessible; and (4) are biased, even with the EM algorithm, when the attrition mechanism is inaccessible. Following R. J. Little and D. B. Rubin (1987), the collection of new data from a random sample of Ss with initially missing data is advocated. On the basis of these data a simple correction is proposed to the EM algorithm estimates. The correction produces unbiased estimates of program effects parameters, even with an inaccessible attrition mechanism and substantial DA. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Detecting cyclicity in social interaction.

Reviews spectral and cross-spectral analytic methods for detecting cyclicity, cross-cyclicity, and lead–lag relationships in continuous data derived from the observation of dyadic interaction. It is found that lead–lag relationships can be assessed using the phase spectrum. Spectral analytic methods are then generalized to categorical observational data (taken from a study by the author and his associates; see record 1978-20895-001). It is shown that by these methods one can derive the classical information theory definition of social communication and its distribution statistics. (27 ref) (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Using the Expectation Maximization Algorithm to Estimate Coefficient Alpha for Scales With Item-Level Missing Data.

A 2-step approach for obtaining internal consistency reliability estimates with item-level missing data is outlined. In the 1st step, a covariance matrix and mean vector are obtained using the expectation maximization (EM) algorithm. In the 2nd step, reliability analyses are carried out in the usual fashion using the EM covariance matrix as input. A Monte Carlo simulation examined the impact of 6 variables (scale length, response categories, item correlations, sample size, missing data, and missing data technique) on 3 different outcomes: estimation bias, mean errors, and confidence interval coverage. The 2-step approach using EM consistently yielded the most accurate reliability estimates and produced coverage rates close to the advertised 95% rate. An easy method of implementing the procedure is outlined. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Reliability, Risk, and Uncertainty Analysis Using Generic Expectation Functions

In engineering design and analysis, mathematical models that generally involve a number of uncertain parameters are frequently employed for decision making. Over the years, a number of techniques have been developed to quantify model output uncertainty contributed by uncertain input parameters. Typically, the methods that are easy to apply may give inaccurate estimates of model output uncertainty. Other methods that reliably produce very accurate results are either difficult to apply or require intensive computational effort. This paper describes the development of generic expectation functions as a function of means and coefficients of variation of input random variables. The generic expectation functions are straightforward to develop, and apply to problems related to reliability, risk, and uncertainty analysis. Several expectation functions based on commonly used probability distributions have been developed. Using them, any order of moment can be estimated exactly. It is found that if exact moments of the model output are available, one can find a good estimate of reliability, risk, and uncertainty of a system without knowing its model output distribution exactly. This technique is applicable when an output variable is a function of several independent random variables in multiplicative, additive, or combined (multiplicative and additive) forms. A practical example is presented to demonstrate the application of generic expectation functions.     

基于MICE_RF的组合赋权—极限随机树岩爆预测模型

目前岩爆预测的真实训练数据量小、数据存在缺失,为了更加准确地预测岩爆等级,提出了一种基于链式随机森林多重插补（MICE_RF）算法的组合赋权—极限随机树（ET）预测模型。首先,在选取岩爆灾害主要评判指标的基础上,采用MICE_RF算法插补缺失数据;然后,由改进层次分析法（IAHP）和基于指标相关性的权重确定方法（CRITIC）确定指标主、客观权重,并引入权向量距离概念对指标组合赋权;最后,将插补和赋权后数据集采用ET算法,构建岩爆等级预测模型。利用国内外工程实例数据进行20次随机抽样试验,并与其他模型进行对比分析。结果表明：MICE_RF插补后可显著提高岩爆模型预测效果;改进AHP-CRITIC法较改进前更具优势,该模型平均预测准确率为93.10%,各比较指标结果均优于对比模型,预测结果更稳定。