Positive embedded integration in Bayesian analysis

This paper describes how embedded sequences of positive interpolatory integration rules (PIIRs) obtained from Gauss-Hermite product rules can be applied in Bayesian analysis. These embedded sequences are very promising for two major reasons. First, they provide a rich class of spatially distributed rules which are particularly useful in high dimensions. Second, they provide a way of producing more efficient integration strategies by enabling approximations to be updated sequentially through the addition of new nodes at each step rather than through changing to a completely new set of nodes. Moreover, as points are added successive rules change naturally from spatially distributed non-product rules to product rules. This feature is particularly attractive when the rules are used for the evaluation of marginal posterior densities. We illustrate the use of embedded sequences of PIIRs in two examples. These illustrate how embedded sequences can be applied to improve the efficiency of the adaptive integration strategy currently in use.     

函数极限性质和存在性的证明

本文用归结原则将函数极限问题转化为数列极限问题去讨论,证明了函数极限性质与极限存在的判定定理,进而更清晰的刻画了函数极限与数列极根之间的关系。     

Polynomial approximations of multivariate smooth functions from quasi-random data

We improve a Monte Carlo algorithm which computes accurate approximations of smooth functions on multidimensional Tchebychef polynomials by using quasi-random sequences. We first show that the convergence of the previous algorithm is twice faster using these sequences. Then, we slightly modify this algorithm to make it work from a single set of random or quasi-random points. This especially leads to a Quasi-Monte Carlo method with an increased rate of convergence for numerical integration.     

Quasi-random resampling for the bootstrap

Quasi-random sequences are known to give efficient numerical integration rules in many Bayesian statistical problems where the posterior distribution can be transformed into periodic functions on then-dimensional hypercube. From this idea we develop a quasi-random approach to the generation of resamples used for Monte Carlo approximations to bootstrap estimates of bias, variance and distribution functions. We demonstrate a major difference between quasi-random bootstrap resamples, which are generated by deterministic algorithms and have no true randomness, and the usual pseudo-random bootstrap resamples generated by the classical bootstrap approach. Various quasi-random approaches are considered and are shown via a simulation study to result in approximants that are competitive in terms of efficiency when compared with other bootstrap Monte Carlo procedures such as balanced and antithetic resampling.     

Quality of Life for the Elder

Abstract

Data from the Parent Health Supplement of the 1991 interview wave of the Panel Studies of Income Dynamics were used to examine the changes in care arrangements for elderly parents (N = 1,028). Following the onset of their dependency, more than 60% of elderly parents experienced at least one form of institutionalization (hospital or nursing home). A majority of those who remained in the community also experienced changes in living/care arrangements, often moving in with someone or having someone move in with them. The findings confirm those of previous studies that health-related need factors and race are significant determinants of institutionalization immediately following the onset of dependency. But availability of caregivers and other enabling factors are also significant determinants of care settings used following hospitalization.     

从语言的功能角度浅析语块在口语中的应用

作为提高学生综合运用英语能力的重要途径之一,英语口语教学在高校英语教学中的重要性不容忽视。分析语言模块作为语言的一种形式所发挥的功能以及在英语口语教学中的积极作用,教学实践经验,尝试相应的教学方式和途径,说明正确使用语言模块对英语口语教学具有促进作用。     

On the maximum of periodic integer-valued sequences with exponential type tails via max-semistable laws

In this work we study the limiting distribution of the maximum term of periodic integer-valued sequences with marginal distribution belonging to a particular class where the tail decays exponentially. This class does not belong to the domain of attraction of any max-stable distribution. Nevertheless, we prove that the limiting distribution is max-semistable when we consider the maximum of the first k_n observations, for a suitable sequence {_kn}$\{k_n\}$ increasing to infinity. We obtain an expression for calculating the extremal index of sequences satisfying certain local conditions similar to conditions D^(m)(_un)$D^{(m)}(u_n)$, m∈N$m\in \mathbb{N}$, defined by Chernick et al. (1991). We apply the results to a class of max-autoregressive sequences and a class of moving average models. The results generalize the ones obtained for the stationary case.     

由两个已知bent序列构造bent序列

文献［１ ～５］ 都讨论了由给定的ｂｅｎｔ 函数（ 或序列） 构造新的ｂｅｎｔ 函数（ 序列） 的方法．本文证明文献［５］ 中的方法实际上可以通过结合文献［１］ 和文献［３］ 的方法而得到,从而对给定的两个ｂｅｎｔ 序列可以得到比文献［５］ 中构造出的序列更多的ｂｅｎｔ 序列     

NA列的Cesaro型强大数律

当1／2＜α＜1，同分布NA列的Cesaro型强大数律依然成立。