Spatially varying dynamic coefficient models

In this work we present a flexible class of linear models to treat observations made in discrete time and continuous space, where the regression coefficients vary smoothly in time and space. This kind of model is particularly appealing in situations where the effect of one or more explanatory processes on the response present substantial heterogeneity in both dimensions. We describe how to perform inference for this class of models and also how to perform forecasting in time and interpolation in space, using simulation techniques. The performance of the algorithm to estimate the parameters of the model and to perform prediction in time is investigated with simulated data sets. The proposed methodology is used to model pollution levels in the Northeast of the United States.     

On Tiku's robust procedure — a Bayesian insight

Tiku's robust procedure for testing mean and variance from nonnormal universe is examined from the Bayesian viewpoint. The posterior distribution of the scale parameter is derived and then approximated by a Laguerre polynomial expansion while the posterior distribution of the location parameter is approximated by a linear combination of t-distributions. For the example with Darwin's data, the approximations appear to be extremely good.     

Convergence of Heavy-tailed Monte Carlo Markov Chain Algorithms

Abstract.  In this paper, we use recent results of Jarner & Roberts ( Ann. Appl. Probab., 12, 2002, 224) to show polynomial convergence rates of Monte Carlo Markov Chain algorithms with polynomial target distributions, in particular random-walk Metropolis algorithms, Langevin algorithms and independence samplers. We also use similar methodology to consider polynomial convergence of the Gibbs sampler on a constrained state space. The main result for the random-walk Metropolis algorithm is that heavy-tailed proposal distributions lead to higher rates of convergence and thus to qualitatively better algorithms as measured, for instance, by the existence of central limit theorems for higher moments. Thus, the paper gives for the first time a theoretical justification for the common belief that heavy-tailed proposal distributions improve convergence in the context of random-walk Metropolis algorithms. Similar results are shown to hold for Langevin algorithms and the independence sampler, while results for the mixing of Gibbs samplers on uniform distributions on constrained spaces are rather different in character.     

基于旋转变换的多角度单人脸标准化算法新探

提出一种基于旋转变换的多角度单人脸标准化算法.首先计算出人脸的平面旋转角度,然后利用双线性插值的思想,推导出一种便于编程、速度快的插值方法进行旋转变换,将其矫正为正面端正人脸.     

Characterizations based on Rényi entropy of order statistics and record values

Two different distributions may have equal Rényi entropy; thus a distribution cannot be identified by its Rényi entropy. In this paper, we explore properties of the Rényi entropy of order statistics. Several characterizations are established based on the Rényi entropy of order statistics and record values. These include characterizations of a distribution on the basis of the differences between Rényi entropies of sequences of order statistics and the parent distribution.     

寻找有理根的新方法

提出了用矩阵讨论多项式的有理根 ,用列表法一次性求出有理根 .     

一种基于网格剖分的两点射线追踪方法

两点射线追踪是解决复杂地质结构下反射波射线正演的有效方法。在初至波层析射线追踪算法基础上，提出了一种两点射线追踪方法，利用层析网格对模型进行离散化，通过两阶段法射线追踪，分别对激发点和接收点按向前处理过程计算模型单元及节点的旅行时，两次时间相加作为最小旅行时，再在目的层界面邻域扫描最小旅行时子震源网格单元，用粒子群算法在该单元内扫描全局最小旅行时点，得到反射点位置与反射夹角，再利用向后处理过程运用旅行时线性插值算法，从反射点分别到激发点、接收点反向追踪射线路径，最后得到反射波两点射线路径。     

Comments on specification of household expenditure functions and equivalence scales by nonparametric regression

This paper considers Lagrange Multiplier (LM) and Likelihood Ratio (LR) tests for determining the cointegrating rank of a vector autoregressive system. n order to deal with outliers and possible fat-tailedness of the error process, non-Gaussian likelihoods are used to carry out the estimation. The limiting distributions of the tests based on these non-Gaussian pseudo-)likelihoods are derived. These distributions depend on nuisance parameters. An operational procedure is proposed to perform inference. It appears that the tests based on non-Gaussian pseudo-likelihoods are much more powerful than their Gaussian counterparts if the errors are fat-tailed. Moreover, the operational LM-type test has a better overall performance than the LR-type test. Copyright O 1998 by Marcel Dekker, Inc.     

A Nonparametric Test for Autoregressive Conditional Heteroscedasticity: A Markov-Chain Approach

In this article we propose a nonparametric test for autoregressive conditional heteroscedasticity based on finite-state Markov chains. A simple Monte Carlo experiment suggests that in finite samples it performs comparably to the Lagrange multiplier test under conditional normality and is superior for the t, lognormal, and exponential distributions. As an illustration, we apply both tests to Canadian/U.S. forward foreign exchange data.     

带稀疏惩罚的LCNN盲目图像复原

为了加强算法的稀疏性和稳定性,在SCAD基础上提出了一种新的稀疏惩罚函数,并加入到拉格朗日约束神经网络中,以克服传统盲源分离方法和独立分量分析方法的缺陷,有效地避免了方程的病态问题,提高盲目图像复原的稀疏性、稳定性和准确性。通过人工数据和真实数据的不同复原算法对比实验,证明了带稀疏惩罚的拉格朗日约束神经网络盲目图像复原技术具有良好的图像复原效果。