基于方向数据的核密度估计的对称检验的大偏差

设$f_n$是基于核函数$K$和取值于$d$-维单位球面${\mathbb{S}}^{d-1}$的独立同分布随机变量列的非参数核密度估计. 我们证明了若核函数是有界变差函数, 随机变量的密度函数$f$是连续的和对称的, $\{\sup_{x\in {\mathbb{SS}}^{d-1}}|f_n(x)-f_n(-x)|,n\ge 1\}$的大偏差原理成立.     

基于R~d上核密度估计的对称检验的中偏差

设f_n是基于一个核函数K和取值于R~d的独立同分布随机变量列的一个非参数核密度估计.推广了何和高一文中相应中偏差的结果,即证明统计量sup_(x∈R)~d|f_n(x)-f_n(-x)|的中偏差,并给出了两个具体的模拟例子.     

核密度估计的对称检验在L_1(R~d)下的中偏差（英文）

设f_n是基于一个核函数K和取值于R~d的独立同分布随机变量列的一个非参数核密度估计.本文证明了{f_n(x)-f_n(-x),n≥1}在L_1(R~d)空间下的两个中偏差定理.     

极限函数的连续性与一致收敛性的关系

<正> 我们知道:如果f_1(x),f_2(x).…,f_n(x)…都在[a,b]上连续且f_1(x),f_2(x)…,f_n(x),…在[a,b]上一致收敛于f(x),那末f(x)必在[a,b]上连续.现在我们提出一个相反的问题:如果f_1(x),f_2(x),…,f_n(x),…都在[a,b]上连续,且f_1(x),f_2(x),…,f_n(x),…在[a,b]上收敛于     

相依随机变量的密度函数的递归核估计的渐近正态性

设{X_n;n≥1}为同分布的ρ-混合序列,其未知密度,f(x)的递归核估计为: f_n(x)=1/n sum from j=1 to n h_j~(-1)K(x-X_j/h_j),本文在适当的条件下,讨论由f_n(x)所产生的随机元的有限维渐近正态性。     

密度核估计的强一致相合性

关于密度函数f(x)的核估计,f_n(x)=(nh_n~d)~(-1)sum from i=1 to (?)(k(x-X_i/h_n)),Devroye和Wagner[1]给出一维情形下,f_n一致强相合于f的一组充分条件,本文给出多维情形下f_n的一致强相合性,而对K和h_n所加的限制是弱的,同时本文改善了徐达明,白志东[2]所得的结果。     

关于密度估计的不变原理

设f(x)为i.i.d随机变量序列X_1,X_2,…共同的分布密度函数,它的核估计为其中h_n↓0,核函数K∈D(-∞,+∞)。 本文首先考虑了由f_n产生的一类D中的随机元的有限维分布的收敛性,然后着重讨论了由f_n产生的另一类D中的随机元在对核函数的适当限制下向正态随机元的弱收敛性。     

相依样本时非参数密度估计的强收敛速度

本文对Loftsgarden和Gucsenberry在文献[1]中提出的概率密度函数f的近邻估计f_n,在样本为φ-混合的情形下,得到了与i.i.d完全相同的结果: (1)f(x)> 0,f满足λ阶Lipschitz条件,选取适当的k_n,在一定的混合速度下,有 lim sup(n/logn)~(λ/(1+2λ)|f_n(x)-f(x)|≤c a.s., (2)f_n在固定点x的渐近正态性, (3)得到了f_n收敛到f时收敛速度的上限。     

论一个由递推关系给出的多项式序列

一、引言笔者曾在一个存在性问题的研究中,偶然地引出了如下一个由递推关系给出的多项式序列{f_n(x)}: f_o(x)=1,f_1(x)=r, f_n(x)=xf_(n-1)(x)-f_(n-2)(x),(n≥2)(1) 尽管其存在性问题早已解决,但由此多项式序列又意外地得到了几个有趣的组合恒等式以及一系列三角恒等式,同时还发现了一类三角函数式的求值方法。故书拙文,以求同行斧正, 二、f_n(x)的表达式与f_n(x)的根由于f_n(x)是x的多项式,因而自然地想求出它的表达式,容易用数学归纳法证明下面的定理1 对任意非负整数n,有其中[t]表示不超过实数t的最大整数。(证略) 当n≥5时,n次多项式的根无公式解,因     

一类核估计强一致收敛的必要条件

§1.引言和结果 设X_1,X_2,…,X_n是来自R~1上的d.f.F(x)的i.i:d.样本,{h_n}是一串正数;K(·)是p.d.f.,令 f_n(X)=1/(nh_n) sum from i=1 to n (K((x-X_i)/(h_n)),x∈R~1. (1) 当F的p.d.f.f存在时,f_n是f的一类重要估计,叫做核估计。关于f_n一致强收敛于f的问题在文献中有很多讨论,所得结果一无例外地要假定f在全直线上一致连续。1969年,E.P.Schuster在[1]中提出了反面的问题:如有函数g,使得     

MODERATE DEVIATIONS AND LARGE DEVIATIONS FOR A TEST OF SYMMETRY BASED ON KERNEL DENSITY ESTIMATOR

Let fn be a non-parametric kernel density estimator based on a kernel function K. and a sequence of independent and identically distributed random variables taking values in R. The goal of this article is to prove moderate deviations and large deviations for the statistic sup ｜fn（x） - fn（-x） ｜.     

Large deviations for the radial processes of the Brownian motions on hyperbolic spaces

Using the heat kernel estimates by Davies (1989) and Anker et al. (1996), we show large deviations for the radial processes of the Brownian motions on hyperbolic spaces.     

Large and moderate deviations principles for kernel estimators of the multivariate regression

In this paper, we prove large deviations principle for the Nadaraya-Watson estimator and for the semi-recursive kernel estimator of the regression in the multidimensional case. Under suitable conditions, we show that the rate function is a good rate function. We thus generalize the results already obtained in the one-dimensional case for the Nadaraya-Watson estimator. Moreover, we give a moderate deviations principle for these two estimators. It turns out that the rate function obtained in the moderate deviations principle for the semi-recursive estimator is larger than the one obtained for the Nadaraya-Watson estimator.      

On large deviations of smoothed Kolmogorov-Smirnov’s statistics

The paper investigates the logarithmic asymptotics of the probability of large deviations of Kolmogorov-Smirnov statistics which are intended to test goodness-of-fit and symmetry and constructed on the basis of smoothed empirical distribution functions. Such tests depend on the choice of the kernel and bandwidth of the window; hence, in this case, standard methods for investigation of large deviations for distribution-free tests, which are based on empirical distribution functions, are inapplicable. For this reason we suggest another approach, which essentially employs the Plachky-Steinebach theorem. The results obtained are no different from Kolmogorov-Smirnov tests constructed by the conventional empirical distribution function, which means, in particular, that Bahadur’s asymptotic efficiency of smoothed Kolmogorov-Smirnov statistics also coincides with that of the classical tests.     

Moderate deviations for deconvolution kernel density estimators with ordinary smooth measurement errors

In this paper, we establish the pointwise and uniform moderate deviations limit results for the deconvolution kernel density estimator in the errors-in-variables model, when the measurement error possesses an ordinary smooth distribution. The results are similar to the moderate deviations theorems for the classical kernel density estimators, but a factor related to the ordinary smooth order is needed to account for the measurement errors.     

Large deviations estimates for some non-local equations: Fast decaying kernels and explicit bounds

We study large deviations for some non-local parabolic type equations. We show that, under some assumptions on the non-local term, problems defined in a bounded domain converge with an exponential rate to the solution of the problem defined in the whole space. We compute this rate in different examples, with different kernels defining the non-local term, and it turns out that the estimate of convergence depends strongly on the decay at infinity of that kernel.     

Décroissance exponentielle du noyau de la chaleur sur la diagonale (II)

Summary We give some conditions for the heat kernel to have an asymptotic expansion in small time such that all coefficients vanish, although the phenomenon seems difficult to understand by large deviations theory. The fact that the leading term is not zero is strongly related to Bismut's condition. These examples are related to the Varadhan estimates of the density of a dynamical system submitted to small random perturbations. To understand that type of asymptotic, one must modify the definition of the distance by adding the Bismut condition (unnoticed, but hidden, in classical cases).     

Tridiagonal Random Matrix: Gaussian Fluctuations and Deviations

This paper is devoted to the Gaussian fluctuations and deviations of the traces of tridiagonal random matrices. Under quite general assumptions, we prove that the traces are approximately normally distributed. A Multi-dimensional central limit theorem is also obtained here. These results have several applications to various physical models and random matrix models, such as the Anderson model, the random birth–death Markov kernel, the random birth–death Q matrix and the \(\beta \)-Hermite ensemble. Furthermore, under an independent-and-identically-distributed condition, we also prove the large deviation principle as well as the moderate deviation principle for the traces.     

带复合泊松跳扩散模型的点波动率门限估计量的渐近性质

本文研究了带复合泊松跳扩散模型的点波动率门限估计量的渐近性质.利用门限方法和核函数技术,构造并证明了此模型点波动率估计量的渐近正态性.同时,应用Grtner-Ellis定理及大偏差中的Delta方法,得到了估计量的中偏差原理.     

LARGE DEVIATIONS AND MODERATE DEVIATIONS FOR SUMS OF NEGATIVELY DEPENDENT RANDOM VARIABLES

In this article, we obtain the large deviations and moderate deviations for negatively dependent (ND) and non-identically distributed random variables defined on (-∞, +∞). The results show that for some non-identical random variables, precise large deviations and moderate deviations remain insensitive to negative dependence structure.