广义U—统计量的指数收敛速度

文「１」研究了一样本Ｕ－统计量的指数收敛速度，本文则研究了广义Ｕ－统计量的指数收敛速度。     

线性模型L－估计其光滑Bootstrap统计量的一些渐近结构

本文证明了文［２］中Ｌ－估计具有强相合性，重对数律，并给出了它的均方收敛速度．证明了Ｌ－估计的光滑Ｂｏｏｔｓｔｒａｐ统计量有与Ｌ－估计类似的线性渐近展开式，由此展开式我们证明了它的渐近正态性及其光滑Ｂｏｏｔｓｔｒａｐ逼近成立．     

U-统计量的指数收敛速度的进一步讨论

在独立未必同分布的情形下，对U－统计量的指数收敛速度进行了讨论，减弱文[2]中的部分条件，给出了类似的结果，同时对Von-Mises统计量也给出了指数收敛速度。     

关于有界核两样本U统计量余项的指数收敛速度

设Ｕｍｎ是以有界对称函数　（ｘ，ｙ）为核的两样本Ｕ－统计量．本文讨论了Ｕｍｎ与其投影之差的指数收敛速度问题，它有别于Ｈｏｅｆｆｄｉｎｇ关于有界核Ｕ－统计量的指数不等式．是两样本Ｕ－统计量所特有的．     

k-U统计量的指数收敛速度

研究了k-U统计量的收敛速度,在一组适当的正则条件下,获得了k-U统计量的指数收敛速度,推广了U-统计量的指数收敛速度的相应结果.     

一类密度估计的收敛速度

ＰｒａｋａｓａＲａｏ在文献［１］中提出一类密度估计ｆｎ（ｘ），我们得到当ｘ固定时ｆｎ（ｘ）－ｆ（ｘ）的ａ．ｓ．收敛速度及ｆｎ（ｘ）正态逼近的Ｂｅｒｒｙ－Ｅｓｓｅｅｎ界，同时，给出ｓｕｐｘ｜ｆｎ（ｘ）－ｆ（ｘ）｜的一致收敛速度     

U—统计计量投影残差的指数收敛速度及其应用

本文研究了一样本Ｕ－统计量投影残差的收敛速度，在核函数有界及某种意义下的指数型有界时，本文得到了一些指数收敛速度，最后，利为上述结果的应用，本文还研究了刻度参数的变点问题。     

扰动Chebyshev结点上的Hermite－Fejer插值

本文发现当Ｃｈｅｂｙｓｈｅｖ结点产生某些扰动时，只要扰动量不超过，则基于扰动后的Ｃｈｅｂｙｓｈｅｖ结点的Ｈｅｒｍｉｔｅ－Ｆｅｊｅｒ插值过程仍然保持对［－１，１］上任意连续函数的一致收敛性，此外，文中还给出了这种收敛性的收敛速度估计。     

扰动Chebyshev结点上的Hermite－Fejer插值

本文发现当Ｃｈｅｂｙｓｈｅｖ结点产生某些扰动时，只要扰动量不超过，则基于扰动后的Ｃｈｅｂｙｓｈｅｖ结点的Ｈｅｒｍｉｔｅ－Ｆｅｊｅｒ插值过程仍然保持对［－１，１］上任意连续函数的一致收敛性，此外，文中还给出了这种收敛性的收敛速度估计。     

关于线性秩统计量的渐近正态性及其收敛速度

本文讨论线性秩统计量的渐近正态性的条件及其收敛速度．推广了Hajek关于线性秩统计量收敛于正态分布的条件的重要定理，并得出了一个较易验证的充分条件．对于一般形式的计分函数，在一定条件下得出了相应线性秩统计量收敛于正态分布的速度．     

Characterization through distributional properties of dual generalized order statistics

Distributional properties of two non-adjacent dual generalized order statistics have been used to characterize distributions. Further, one sided contraction and dilation for the dual generalized order statistics are discussed and then the results are deduced for generalized order statistics, order statistics, lower record statistics, upper record statistics and adjacent dual generalized order statistics.     

属性数学-属性测度和属性统计

本文研究了属性集和属性测度,它们是属性数学的基础.本文提出了属性统计方法,并指出,概率统计、模糊统计、集值统计是它的特殊情况.     

一类相合的分位点型检验

广义非参数似然比检验统计量是一类很广的统计量,包含了众多重要的检验统计量,如Anderson-Darling(AD)等.利用Rubin的随机经验分布函数替代经验分布函数的方法,得到了广义非参数似然比检验统计量的新版本,构造了新的检验统计量.由于新的检验统计量在给定样本下仍然是随机变量,选择了它的分位点和期望作为检验统计量,分别称之为分位点型检验统计量和期望型检验统计量.在简单假设情况下,证明了分位点型检验统计量和期望型检验统计量在固定备择下的相合性.模拟结果显示,在某些备择下,新的检验的功效明显高于原有的基于经验分布函数的检验的功效.     

基于情景分析的多维拟凸风险统计量

本文定义了三类特殊的多维风险统计量,分别是多维共单调拟凸风险统计量、多维拟凸风险统计量和多维经验分布不变拟凸风险统计量,并采用对偶方法给出了它们的表示定理.本文的结果既是一维拟凸风险统计量的推广,也是多维凸风险统计量的拓展.     

Introducing the Emerging Discipline of Statistics Education

Increasing attention has been given over the last decade by the statistics, mathematics and science education communities to the development of statistical literacy and numeracy skills of all citizens and the enhancement of statistics education at all levels. This paper introduces the emerging discipline of statistics education and considers its role in the development of these important skills. The paper begins with information on the growing importance of statistics in today's society, schools and colleges, summarizes unique challenges students face as they learn statistics, and makes a case for the importance of collaboration between mathematicians and statisticians in preparing teachers to teach students how to understand and reason about data. We discuss the differences and interrelations between statistics and mathematics, recognizing that mathematics is the discipline that has traditionally included instruction in statistics. We conclude with an argument that statistics should be viewed as a bridge between mathematics and science and should be taught in both disciplines.     

On exceedances of record and order statistics

Exact, limiting distributions along with their rates of convergence of exceedance statistics for both order statistics and record statistics are provided when the underlying distribution is arbitrary. The exact distribution of record statistics for arbitrary underlying distributions is obtained as well.

     

Asymptotic Results on a General Class of Empirical Statistics: Power and Confidence Interval Properties

We consider a very general class of empirical statistics that includes (a) empirical discrepancy (ED) statistics, (b) generalized empirical exponential family likelihood statistics, (c) generalized empirical likelihood statistics, (d) empirical statistics arising from Bayesian considerations, and (e) Bartlett-type adjusted versions of ED statistics. With reference to this general class, we investigate higher order asymptotics on power and expected lengths of confidence intervals. For (b)-(e), such results have been hitherto unexplored. Furthermore, our findings help in understanding the presently known results on the subclass (a) from a wider perspective.     

漫谈统计学的应用与发展(1)

本文分两部分:第一部分通过20多个实际案例说明统计学在各个领域的广泛应用,希望使更多的人对统计学有更全面、更深切的了解;第二部分简要介绍统计学在国内外的发展概况,并通过其发展进程的介绍,进一步阐明统计学的意义与价值。同时列举更多的论据说明近代统计学是当今最重要的科学技术之一。     

漫谈统计学的应用与发展(2)

本文分两部分:第一部分通过20多个实际案例说明统计学在各个领域的广泛应用,希望使更多的人对统计学有更全面、更深切的了解;第二部分简要介绍统计学在国内外的发展概况,并通过其发展进程的介绍,进一步阐明统计学的意义与价值。同时列举更多的论据说明近代统计学是当今最重要的科学技术之一。     

Multiple Window Scan Statistics for Two Dimensional Poisson Processes

In this article, approximations for the distribution of multiple window scan statistics for Poisson Processes on a two dimensional rectangular region are derived, for the conditional and unconditional model. These multiple window scan statistics are based on the minimum of p-values and repeated minimum p-values of fixed window scan statistics. Numerical results are presented to evaluate the performance of these multiple window scan statistics and compare their power with fixed window scan statistics for selected local type alternatives.