DISPERSION COMPARISONS OF TWO PROBABILITY VECTORS UNDER MULTINOMIAL SAMPLING

We consider testing hypotheses concerning comparing dispersions between two parameter vectors of multinomial distributions in both one-sample and two-sample cases. The comparison criterion is the concept of Schur majorization. A new dispersion index is proposed for testing the hypotheses. The corresponding test for the one-sample problem is an exact test. For the two-sample problem, the bootstrap is used to approximate the null distribution of the test statistic and the p-value. We prove that the bootstrap test is asymptotically correct and consistent. Simulation studies for the bootstrap test are reported and a real life example is presented.     

A modified residual-based test for serial correlation in linear panel data models

This paper suggests a modified serial correlation test for linear panel data models, which is based on the parameter estimates for an artificial autoregression modeled by differencing and centering residual vectors. Specifically, the differencing operator over the time index and the centering operator over the individual index are, respectively, used to eliminate the potential individual effects and time effects so that the resultant serial correlation test is robust to the two potential effects. Clearly, the test is also robust to the potential correlation between the covariates and the random effects. The test is asymptotically chi-squared distributed under the null hypothesis. Power study shows that the test can detect local alternatives distinct at the parametric rate from the null hypothesis. The finite sample properties of the test are investigated by means of Monte Carlo simulation experiments, and a real data example is analyzed for illustration.     

Two-sample Testing for Mean Functions with Incompletely Observed Functional Data

In functional data analysis,the collected data are often assumed to be fully observed on the domain.However,in dealing with real data(for example,environmental pollution data),we are often faced with the scenario that some functional data are fully observed on dense lattice while others are incompletely observed.In this paper,we propose a method for testing equivalence of mean functions of two samples under this scenario.Some asymptotic results of the proposed methods are established.The proposed test is employed to analyze an environmental pollution study in Liuzhou City of China.Simulations show that the proposed test has a good control of the type-I error,and is more powerful than the complete case test in most cases.     

Checking for normality in linear mixed models

Linear mixed models are popularly used to fit continuous longitudinal data,and the random effects are commonly assumed to have normal distribution.However,this assumption needs to be tested so that further analysis can be proceeded well.In this paper,we consider the Baringhaus-Henze-Epps-Pulley (BHEP) tests,which are based on an empirical characteristic function.Differing from their case,we consider the normality checking for the random effects which are unobservable and the test should be based on their predictors.The test is consistent against global alternatives,and is sensitive to the local alternatives converging to the null at a certain rate arbitrarily close to 1/√ n where n is sample size.Furthermore,to overcome the problem that the limiting null distribution of the test is not tractable,we suggest a new method: use a conditional Monte Carlo test (CMCT) to approximate the null distribution,and then to simulate p-values.The test is compared with existing methods,the power is examined,and several examples are applied to illustrate the usefulness of our test in the analysis of longitudinal data.     

High-dimensional Tests for Mean Vector: Approaches without Estimating the Mean Vector Directly

Several tests for multivariate mean vector have been proposed in the recent literature. Generally,these tests are directly concerned with the mean vector of a high-dimensional distribution. The paper presents two new test procedures for testing mean vector in large dimension and small samples. We do not focus on the mean vector directly, which is a different framework from the existing choices. The first test procedure is based on the asymptotic distribution of the test statistic, where the dime...     

Mixtures of semiparametric varying coefficient models for longitudinal data with nonignorable dropout

Informative dropout often arise in longitudinal data. In this paper we propose a mixture model in which the responses follow a semiparametric varying coefficient random effects model and some of the regression coefficients depend on the dropout time in a non-parametric way. The local linear version of the profile-kernel method is used to estimate the parameters of the model. The proposed estimators are shown to be consistent and asymptotically normal, and the finite performance of the estimators is evaluated by numerical simulation.     

A new two-part test based on density ratio model for zero-inflated continuous distributions

In this paper,we consider testing the hypothesis concerning the means of two independent semicontinuous distributions whose observations are zero-inflated,characterized by a sizable number of zeros and positive observations from a continuous distribution.The continuous parts of the two semicontinuous distributions are assumed to follow a density ratio model.A new two-part test is developed for this kind of data.The proposed test takes the sum of one test for equality of proportions of zero values and one conditional test for the continuous distribution.The test is proved to follow a χ~2 distribution with two degrees of freedom.Simulation studies show that the proposed test controls the type I error rates at the desired level,and is competitive to,and most of the time more powerful than two popular tests.A real data example from a dietary intervention study is used to illustrate the usefulness of the proposed test.     

Heteroscedasticity and/or Autocorrelation Checks in Longitudinal Nonlinear Models with Elliptical and AR（1） Errors

The aim of this paper is to study the tests for variance heterogeneity and/or autocorrelation in nonlinear regression models with elliptical and AR(1) errors. The elliptical class includes several symmetric multivariate distributions such as normal, Student-t, power exponential, among others. Several diagnostic tests using score statistics and their adjustment are constructed. The asymptotic properties, including asymptotic chi-square and approximate powers under local alternatives of the score statistics, are studied. The properties of test statistics are investigated through Monte Carlo simulations. A data set previously analyzed under normal errors is reanalyzed under elliptical models to illustrate our test methods.     

Some Properties of A Lack-of-Fit Test for a Linear Errors in Variables Model

The relationship between the linear errors-in-variables model and the corresponding ordinary linear model in statistical inference is studied. It is shown that normality of the distribution of covariate is a necessary and sufficient condition for the equivalence. Therefore, testing for lack-of-fit in linear errors-in-variables model can be converted into testing for it in the corresponding ordinary linear model under normality assumption. A test of score type is constructed and the limiting chi-squared distribution is derived under the null hypothesis.Furthermore, we discuss the power of the test and the choice of the weight function involved in the test statistic.     

Identification of Non-Varying Coefficients in Varying- Coefficient Models

A partially varying-coefficient model is one of the useful modelling tools. In this model, some coefficients of a linear model are kept to be constant whilst the others are allowed to vary with another factor. However, rarely can the analysts know a priori which coefficients can be assumed to be constant and which ones are varying with the given factor. Therefore, the identification problem of the constant coefficients should be solved before the partially varying-coefficient model is used to analyze a real-world data set. In this article, a simple test method is proposed to achieve this task, in which the test statistic is constructed as the sample variance of the estimates of each coefficient function in a well-known varying-coefficient model. Moreover two procedures, called F-approximation and three-moment X~2 approximation, are employed to derive the p-value of the test. Furthermore, some simulations are conducted to examine the performance of the test and the results are satisfactory.     

离散型广义非线性纵向数据模型中偏离名义离差的检验及其功效模拟

离散型广义非线性模型包括Poisson,二项,负二项模型.本文讨论离散型广义非线性纵向数据模型中偏离名义离差的检验问题,得到了检验的score统计量,并利用MonteCarlo方法研究了检验统计量的性质.最后,利用杀虫剂数据说明了检验方法的应用.     

TESTING FOR VARYING DISPERSION IN DISCRETE EXPONENTIAL FAMILY NONLINEAR MODELS

§ 1　 Introduction and modelsThe general form of exponential family nonlinear models isg(μi) =f(xi,﹀) , (1 )where,g(· ) is a monotonic link function,f is a known differentiable nonlinear functionand﹀ is a p-vectoroffixed population parameters;μi=E(yi) and the density of response yiisp(yi) =exp{[yiθi -b(θi) -c(yi) ] -12 a(yi,) } ,(2 )whereθi is the natural parameter, is the dispersion parameter.From [1 1 ] ,μi=b(θi) ,Vi=Var(yi) =- 1 b(θi) .If f(xi,β) =x Ti ﹀,then mod…     

离散型指数族非线性模型的变离差检验

It is necessary to test for varying dispersion in generalized nonlinear models. Wei,et al (1998) developed a likelihood ratio test,a score test and their adjustments to test for varying dispersion in continuous exponential family nonlinear models. This type of problem in the framework of general discrete exponential family nonlinear models is discussed. Two types of varying dispersion, which are random coefficients model and random effects model, are proposed ,and corresponding score test statistics are constructed and expressed in simple ,easy to use ,matrix formulas.     

On the Lagrangian Katz family of distributions as a claim frequency model

The Panjer (Katz) family of distributions is defined by a particular first-order recursion which is built on the basis of two parameters. It is known to characterize the Poisson, negative binomial and binomial distributions. In insurance, its main usefulness is to yield a simple recursive algorithm for the aggregate claims distribution. The present paper is concerned with the more general Lagrangian Katz family of distributions. That family satisfies an extended recursion which now depends on three parameters. To begin with, this recursion is derived through a certain first-crossing problem and two applications in risk theory are described. The distributions covered by the recursion are then identified as the generalized Poisson, generalized negative binomial and binomial distributions. A few other properties of the family are pointed out, including the index of dispersion, an extended Panjer algorithm for compound sums and the asymptotic tail behaviour. Finally, the relevance of the family is illustrated with several data sets on the frequency of car accidents.     

恰当散度非线性模型变离差的检验

本文研究了恰当散度非线性模型变离差的检验问题.基于似然比统计量和得分统计量,得到变离差的检验.并且用数值例子说明方法是有效的.     

Bayesian‐type count data models with varying coefficients: estimation and testing in the presence of overdispersion

In this paper we study varying‐coefficient models for count data. A Bayesian approach is taken to model the variability of the regression parameters. Based on a Kalman filter procedure the varying coefficients are estimated as the mode of the posterior distribution. All hyperparameters, including an overdispersion parameter in the negative binomial varying‐coefficient model (NBVC), are estimated as ML‐estimators using an EM‐type algorithm. A bootstrapping test of the fixed‐coefficient hypothesis against a varying‐coefficient alternative is proposed, which is evaluated running a simulation study. The study shows that the choice of a suitable count data model is of special importance in the framework of varying‐coefficient models. The methodology is illustrated analysing the determinants of the number of individual doctor visits. Copyright © 2001 John Wiley & Sons, Ltd.     

Dispersion of mass and the complexity of randomized geometric algorithms

How much can randomness help computation? Motivated by this general question and by volume computation, one of the few instances where randomness provably helps, we analyze a notion of dispersion and connect it to asymptotic convex geometry. We obtain a nearly quadratic lower bound on the complexity of randomized volume algorithms for convex bodies in Rn (the current best algorithm has complexity roughly n⁴, conjectured to be n³). Our main tools, dispersion of random determinants and dispersion of the length of a random point from a convex body, are of independent interest and applicable more generally; in particular, the latter is closely related to the variance hypothesis from convex geometry. This geometric dispersion also leads to lower bounds for matrix problems and property testing.     

A note on model diagnostics in longitudinal data analysis

Longitudinal study has become one of the most commonly adopted designs in medical research. The generalized estimating equations (GEE) method and/or mixed effects models are employed very often in causal inferences. The related model diagnostic procedures are not yet fully formalized, and perhaps never will be. The potential causes of major problems are the high variety of the dependence within subjects and/or the number of repeated measurements. A single testing procedure, e.g., run test, is not possible to resolve all model diagnostics problems in longitudinal data analysis. Multiple quantitative indexes for model diagnostics are needed to take into account this variety. We propose eight testing procedures for randomness accompanied with some conventional and/or non-conventional plots to remedy model diagnostics in longitudinal data analysis. The proposed issue in this paper is well illustrated with four clinical studies in Taiwan.     

无重复因析试验中多个散度效应检验的一种改进方法

在无重复因析试验的多个散度效应分析中,常常出现错误识别的现象,即两个显著的散度效应可能在它们的交互列上产生一个错误的散度效应,并且现有的许多方法都存在这样的问题.为了解决这种模棱两可性,McGrath和Lin(2001)提出了一种基于残差样本方差几何平均的检验方法(ML方法),但是这个方法不能应用于零残差样本方差的情形.鉴于此,提出了一种基于修改残差的改进方法,适用于零残差样本方差的情形,并且通过实例验证了方法的合理性.最后,通过模拟和ML方法做了比较.     

Score tests for zero-inflated double poisson regression models

Count data with excess zeros encountered in many applications often exhibit extra variation. Therefore, zero-inflated Poisson (ZIP) model may fail to fit such data. In this paper, a zero-inflated double Poisson model (ZIDP), which is generalization of the ZIP model, is studied and the score tests for the significance of dispersion and zero-inflation in ZIDP model are developed. Meanwhile, this work also develops homogeneous tests for dispersion and/or zero-inflation parameter, and corresponding score test statistics are obtained. One numerical example is given to illustrate our methodology and the properties of score test statistics are investigated through Monte Carlo simulations.