Improvements of goodness-of-fit statistics for sparse multinomials based on normalizing transformations

We consider multinomial goodness-of-fit tests for a specified simple hypothesis under the assumption of sparseness. It is shown that the asymptotic normality of the PearsonX ² statistic (X _k ² ) and the log-likelihood ratio statistic (G _k ² ) assuming sparseness. In this paper, we improve the asymptotic normality ofX _k ² andG _k ² statistics based on two kinds of normalizing transformation. The performance of the transformed statistics is numerically investigated.     

Rank estimates in a class of semiparametric two-sample models

We consider a two-sample semiparametric model involving a real parameter and a nuisance parameter F which is a distribution function. This model includes the proportional hazard, proportional odds, linear transformation and Harrington-Fleming models (1982, Biometrika, 69, 533–546). We propose two types of estimates based on ranks. The first is a rank approximation to Huber's M-estimates (1981, Robust Statistics, Wiley) and the second is a Hodges-Lehmann type rank inversion estimate (1963, Ann. Math. Statist., 34, 598–611). We obtain asymptotic normality and efficiency results. The estimates are consistent and asymptotically normal generally but fully efficient only for special cases.Research partially supported by National Science Foundation Grant DMS-86-02083 and National Institute of General Medical Sciences Grant SSS-Y1RO1GM35416-01     

Improved omnibus test statistic for normality

We propose a new omnibus test statistic for normality based on the Jarque–Bera test statistic. We give the exact first four moments of the null distribution for the statistic using a computer algebra system. Our proposed statistic is an improvement of Jarque–Bera test statistic. Then the cumulants of the standardized statistic satisfy the Cornish–Fisher assumption. We give a normalizing transformation of the statistic based on the Wilson–Hilferty transformation.     

<Emphasis Type="Italic">N</Emphasis>-dimensional space-time unit spheres and Lorentz transformation

By using hyperbolic virtual unit of Clifford algebra, the concept of n-dimensional space-time unit spheres is introduced. It is used as n-dimensional Minkowski space-time and Lorentz transformation.     

Asymptotic behavior ofL-statistics for a large class of time series

In this paper we derive the asymptotic normality ofL-statistics with unbounded scores for a large class of time series. To handle the dependence structure, we use the concept ofm(n)-decomposability as an alternative to classical mixing concepts.Research supported by the Office of Naval Research Contract N00014-91-J-1020.Part of this work was done while the author was at the Department of Mathematics, KUN, Nijmegen, The Netherlands.     

Inducing normality from non‐Gaussian long memory time series and its application to stock return data

Motivated by Lee and Ko (Appl. Stochastic Models. Bus. Ind. 2007; 23 :493–502) but not limited to the study, this paper proposes a wavelet‐based Bayesian power transformation procedure through the well‐known Box–Cox transformation to induce normality from non‐Gaussian long memory processes. We consider power transformations of non‐Gaussian long memory time series under the assumption of an unknown transformation parameter, a situation that arises commonly in practice, while most research has been devoted to non‐linear transformations of Gaussian long memory time series with known transformation parameter. Specially, this study is mainly focused on the simultaneous estimation of the transformation parameter and long memory parameter. To this end, posterior estimations via Markov chain Monte Carlo methods are performed in the wavelet domain. Performances are assessed on a simulation study and a German stock return data set. Copyright © 2009 John Wiley & Sons, Ltd.     

Coulomb Problem in a One-Dimensional Space with Constant Positive Curvature

We construct a complex transformation generalizing the known Hurwitz transformation in the Euclidean space for one-dimensional quantum mechanics. As in the case of the flat space, this transformation allows establishing the connection between the Coulomb problem and the oscillator problem with the Calogero–Sutherland potential added. We fully describe the motion in a Coulomb field in S ₁ and determine the energy spectrum and the wave functions with the correct normalizing constant.     

Asymptotic expansions for the distribution of quadratic forms in normal variables

Higher order asymptotic expansions for the distribution of quadratic forms in normal variables are obtained. The Cornish-Fisher inverse expansions for the percentiles of the distribution are also given. The resulting formula for a definite quadratic form guarantees accuracy almost up to fourth decimal place if the distribution is not very skew. The normalizing transformation investigated by Jensen and Solomon (1972, J. Amer. Statist. Assoc., 67, 898–902) is reconsidered based on the rate of convergence to the normal distribution.Faculty of Science, Kyushu University, 6-10-1 Hakozaki, Higashi-ku, Fukuoka 812 Japan     

Higher order asymptotic theory for normalizing transformations of maximum likelihood estimators

Suppose thatX _n =(X ₁,...X _n) is a collection ofm-dimensional random vectorsX _i forming a stochastic process with a parameter . Let be the MLE of . We assume that a transformationA( ) of has thek-thorder Edgeworth expansion (k=2,3). IfA extinguishes the terms in the Edgeworth expansion up tok-th-order (k2), then we say thatA is thek-th-order normalizing transformation. In this paper, we elucidate thek-th-order asymptotics of the normalizing transformations. Some conditions forA to be thek-th-order normalizing transformation will be given. Our results are very general, and can be applied to the i.i.d. case, multivariate analysis and time series analysis. Finally, we also study thek-th-order asymptotics of a modified signed log likelihood ratio in terms of the Edgeworth approximation.Research supported by the Office of Naval Research Contract N00014-91-J-1020.     

Accurate confidence intervals in regression analyses of non-normal data

A linear model in which random errors are distributed independently and identically according to an arbitrary continuous distribution is assumed. Second- and third-order accurate confidence intervals for regression parameters are constructed from Charlier differential series expansions of approximately pivotal quantities around Student’s t distribution. Simulation verifies that small sample performance of the intervals surpasses that of conventional asymptotic intervals and equals or surpasses that of bootstrap percentile-t and bootstrap percentile-|t| intervals under mild to marked departure from normality.     

Asymptotic behavior of M-estimator and related random field for diffusion process

The M-estimate which maximizes a positive stochastic process Q is treated for multidimensional diffusion models. The convergence in distribution of the process of ratio of Q's after normalizing is proved. The asymptotic behavior of M-estimates is stated. We present the asymptotic variance in general cases and in estimation by misspecified models.     

Geometric properties of root vectors for equation of nonhomogeneous damped string: transformation operators method

The spectral decomposition theorem for a class of nonselfadjoint operators in a Hilbert space is obtained in the paper. These operators are the dynamics generators for the systems governed by 1–dim hyperbolic equations with spatially nonhomogeneous coefficients containing first order damping terms and subject to linear nonselfadjoint boundary conditions. These equations and boundary conditions describe, in particular, a spatially nonhomogeneous string subject to a distributed viscous damping and also damped at the boundary points. The main result leading to the spectral decomposition is the fact that the generalized eigenvectors (root vectors) of the above operators form Riesz bases in the corresponding energy spaces. The proofs are based on the transformation operators method. The classical concept of transformation operators is extended to the equation of damped string. Originally, this concept was developed by I. M. Gelfand, B. M. Levitan and V. A. Marchenko for 1–dim Schrödinger equation in connection with the inverse scattering problem. In the classical case, the transformation operator maps the exponential function (stationary wave function of the free particle) into the Jost solution of the perturbed Schrödinger equation. For the equation of a nonhomogeneous damped string, it is natural to introduce two transformation operators (outgoing and incoming transformation operators). The terminology is motivated by an analog with the Lax—Phillips scattering theory. The transformation operators method is used to reduce the Riesz bases property problem for the generalized eigenvectors to the similar problem for a system of nonharmonic exponentials whose complex frequencies are precisely the eigenvalues of our operators. The latter problem is solved based on the spectral asymptotics and known facts about exponential families. The main result presented in the paper means that the generator of a finite string with damping both in the equation and in the boundary conditions is a Riesz spectral operator. The latter result provides a class of nontrivial examples of non—selfadjoint operators which admit an analog of the spectral decomposition. The result also has significant applications in the control theory of distributed parameter systems.     

Empirical estimation of the proportional hazard premium for heavy-tailed claim amounts

The asymptotic normality of the sample proportional hazard premium for heavy-tailed claim amounts with infinite variance cannot be obtained by classical results for L-statistics. In this paper, we propose an alternative estimator for this class of premiums and we establish its asymptotic normality.     

Normalizing and variance stabilizing transformations of multivariate statistics under an elliptical population

Summary Normalizing and variance stabilizing transformations of a sample correlation, multiple correlation and canonical correlation coefficients are obtained under an elliptical population. It is shown that the Fisher'sz-transformation is efficient for these statistics. A normalizing transformation is also studied for a latent root of a sample covariance matrix in an elliptical sample.     

准正交基与准正交变换

利用内积给出了准正交基,准正交变换与准对合变换的概念,研究了它们的性质及其之间的联系,获得了许多新的结果,推广了正交基,正交变换,对合变换的概念,性质以及张禾瑞,郝新,邹本强等先生的相关结果。     

成组复发事件下的半参数变换模型

本文在成组复发事件下研究了一个一般半参数的边际变换模型,利用估计方程的理论,给出了该模型中未知参数和基本比率函数的估计,同时利用现代经验过程理论证明了所得估计的相合性和渐近正态性.     

删失数据下的变系数回归模型

研究了删失数据下的变系数回归模型．通过数据变换,利用局部多项式方法,给出了系数函数的局部加权最小二乘估计．证明了该估计的渐近偏差和渐近方差,同时获得了该估计的渐近正态性．     

Some Upper Bounds on the Covering Radii of Linear Codes Over Fq and Their Applications

We show that the covering radius R of an [n,k,d] code over F_q is bounded above by R n-n _q(k, d/q). We strengthen this bound when R d and find conditions under which equality holds.As applications of this and other bounds, we show that all binary linear codes of lengths up to 15, or codimension up to 9, are normal. We also establish the normality of most codes of length 16 and many of codimension 10. These results have applications in the construction of codes that attain t[n,k,/it>], the smallest covering radius of any binary linear [n,k].We also prove some new results on the amalgamated direct sum (ADS) construction of Graham and Sloane. We find new conditions assuring normality of the ADS; covering radius 1 less than previously guaranteed for ADS of codes with even norms; good covering codes as ADS without the hypothesis of normality, from concepts p- stable and s- stable; codes with best known covering radii as ADS of two, often cyclic, codes (thus retaining structure so as to be suitable for practical applications).     

On the Sears–Slater basic hypergeometric transformations

We introduce the concept of a Jackson integral of type BC ₁ which is a q-series permitting Weyl group symmetry. Using this, we give a simple proof of transformation formulas for a very-well-poised-balanced _2r ψ _2r hypergeometric series discovered by Sears and Slater. This work was supported in part by Grant-in-Aid for Scientific Research (C) No. 17540034 from the Ministry of Education, Culture, Sports, Science and Technology, Japan.     

关于正交变换两种定义方式的研讨

指出由于当前正交变换两种定义方式并存以及其中的定义2违反了给概念下定义的规则,已经导致了一些对正交变换概念的错误理解.建议各教材统一采用本文定义1的方式定义正交变换.上述研讨与结果也可平行地移植到酉变换上去.