New Developments in Statistical Computing: Short Notices and Reviews of New Program Packages,other Sources of Information,and New Products

Graphs are presented on which the empirical distribution function can be plotted to test the assumption of normality by the Lilliefors test. A second set of graphs is presented for using the Lilliefors test on exponential distributions. The graphs allow for tests at the 10 percent, 5 percent, and 1 percent levels of significance. Use of these graphs makes it easy for students in a first course in statistics to test normal and exponential distributions without having to unravel the mystery associated with putting together a chi-squared goodness-of-fit test.     

Estimating correlation from categorized bivariate normal data

The polychoric correlation and an approximate maximum likelihood estimator of correlation are compared for count data that are assumed to be derived from an underlying bivariate normal distribution. A related chi squared test for bivariate normality is also examined.     

Measures of lack of fit from tests of chi-squared type

If X² is the Pearson chi-squared statistic for testing fit, then $\text{X}{}^2\text{n}$ has long been considered an associated measure of the degree of lack of fit. Here we consider two classes of statistics of chi-squared type, each having X² as a member. The first is a class of directed divergence statistics discussed by Cressie and Read, the second consists of nonnegative definite quadratic forms in the standardized cell frequencies. We investigate the large sample behavior of $\text{T}\text{n}$, where T is any of these statistics. A number of auxiliary results on the Cressie-Read statistics are also obtained. The measures are illustrated by application to data from classical physics compiled by Stigler.     

Identifying Nonproportional Covariates in the Cox Model

This paper addresses problem of testing whether an individual covariate in the Cox model has a proportional (i.e., time-constant) effect on the hazard. Two existing methods are considered: one is based on the component of the score process, and the other is a Neyman type smooth test. Simulations show that, when the model contains both proportional and nonproportional covariates, these methods are not reliable tools for discrimination. A simple yet effective solution is proposed based on smooth modeling of the effects of the covariates not in focus.     

A Generalized Poisson Distribution

Cumulative probabilities of a Poisson distribution can be written in terms of incomplete gamma function where the parameter of the gamma function is an integer. From this definition a new generalization of the Poisson distribution is obtained with two parameters. Asymptotic behavior of this distribution is shown to be normal. Some order properties of this distribution are also studied.     

善的形上学追问——孟子善恶观的道德解析

善是什么?善何以可能?善的终极根据是什么?通过对善的不断追问,孟子为善建构了形上学的根据。“可欲之谓善”是孟子德性论的道德立场的体现。孟子通过对善的伦理追问、人性追问和天道追问,为善建构了一个较完善的思想体系。各种人伦规范正是可欲之善的现实存在;性善论是善何以可能的内在根据;天道观则是善的超越根据。孟子以性善说人性,以天道说性善的思维理路,成为儒家后学道德形上学建构理论资源。     

An additive marginal regression model for clustered recurrent event in the presence of a terminal event

In this article, an additive rate model is proposed for clustered recurrent event with a terminal event. The subjects are clustered by some property. For the clustered subjects, the recurrent event is precluded by the death. An estimating equation is developed for the model parameter and the baseline rate function. The asymptotic properties of the resulting estimators are established. In addition, a goodness-of-fit test is presented to assess the adequacy of the model. The finite-sample behavior of the proposed estimators is evaluated through simulation studies, and an application to a bladder cancer data is illustrated.     

A unified approach to proving parametric bootstrap consistency for some goodness-of-fit tests

Because model misspecification can lead to inconsistent and inefficient estimators and invalid tests of hypotheses, testing for misspecification is critically important. We focus here on several general purpose goodness-of-fit tests which can be applied to assess the adequacy of a wide variety of parametric models without specifying an alternative model. Parametric bootstrap is the method of choice for computing the p-values of these tests however the proof of its consistency has never been rigourously shown in this setting. Using properties of locally asymptotically normal parametric models, we prove that under quite general conditions, the parametric bootstrap provides a consistent estimate of the null distribution of the statistics under investigation.     

Exponentiality test based on alpha-divergence and gamma-divergence

In the present paper, we use the already defined alpha-divergence and gamma-divergence for constructing some goodness of fit tests for exponentiality. These divergence measures are very robust with respect to outliers. Since the existence of outliers among statistical data can be lead to misleading results, therefore utilizing these divergence measures can be of importance. In order to construct test statistics, two estimators are used for alpha-divergence and gamma-divergence. In the first one, we consider the alpha-divergence and gamma-divergence of the equilibrium distribution function, which is well defined on the empirical distribution function (EDF) and is proposed as an EDF-based goodness of fit test statistic. The second one is an estimator in manner of Vasicek entropy estimator. Simulation results indicate that in comparison with the other tests statistics, our mentioned test statistics almost in most of the cases have higher power. Finally, two examples containing outliers illustrate the importance and use of the proposed tests.     

On Charlier polynomials in testing Poissonity

This article discusses applications of Charlier polynomials when checking how well classic Poisson model fits the data. We show that smooth components pertaining to the polynomials can be effectively used in preliminary analysis of data at hand and we propose and discuss some tests based on them. Our extensive simulations shed new light on power behavior of the best tests in the area.