A class of mean residual life regression models with censored survival data

When describing a failure time distribution, the mean residual life is sometimes preferred to the survival or hazard rate. Regression analysis making use of the mean residual life function has recently drawn a great deal of attention. In this paper, a class of mean residual life regression models are proposed for censored data, and estimation procedures and a goodness-of-fit test are developed. Both asymptotic and finite sample properties of the proposed estimators are established, and the proposed methods are applied to a cancer data set from a clinic trial.     

对应分析统计检验体系探讨

对应分析因其结果的易读性，近些年得到了越来越广泛的应用。为了更好地应用对应分析，提出建立对应分析统计检验体系，包括对应分析适用性的统计检验以及对应分析效果的检验，同时还提出应用对应分析时应注意的其它问题。     

一种榫卯连接方钢管组装框架模型的荷载 位移曲线试验研究

提出一种榫卯连接方钢管组装框架结构。对两个方向的平面框架模型进行受力性能试验。介绍试验概况，给出框架模型的竖向荷载与挠度和水平荷载与水平侧移曲线，这些曲线介于刚节点框架和铰节点框架之间，属于半刚性节点框架的范畴。     

A VARYING-COEFFICIENT APPROACH TO ESTIMATION AND EXTRAPOLATION OF HOUSEHOLD SIZE

Household formation analysis is both a multidimensional economical and statistical problem of great complexity. Since most of the literature tries to incorporate multiple economic aspects, there is, considering the extraordinary practical relevance of the problem, a remarkable gap between theory and application in this field. This paper tries to diminish this gap by a comprehensive treatise on the statistical site of the problem. Thus, we develop a model of household composition, where the evolution of the household membership rates is captured by a logit link-function and a multinomial distribution, which automatically fulfills the non-negativity and adding-up restrictions of the underlying probabilities. We use a varying-coefficients procedure by polynomially smoothing the household membership rates over age for every household size class and assuming a linear predictor in other variables. As an application we estimated and extrapolated the distribution of household sizes of an autonomous region using population register data. Our sample consisted of approximately 450,000 people living in about 170,000 households, grouped into nine different household size classes and classified into age classes from 0 to 90. The data covers a time span of 12 years, from 1986 to 1997. Empirical results show the robustness of the procedure even in case of low cell frequencies. Thus, there is no need for regional or age-group aggregations.     

Modification of Tukey's additivity test

In this paper we discuss testing for an interaction in the two-way ANOVA with just one observation per cell. The known results are reviewed and a simulation study is performed to evaluate type I and type II risks of the tests. It is shown that the Tukey and Mandel additivity tests have very low power in case of more general interaction scheme. A modification of Tukey's test is developed to resolve this issue. All tests mentioned in the paper have been implemented in R package Additivity Tests.     

Nonparametric tests for scale shift at an unknown time point

A class of linear rank tests is suggested for testing a shift in scale at an unknown time point in a sequence of independent observations. The tests,based on inverse normal scores and on ordered exponential scores,are shown to be asymptotically as efficient as their distribution-oriented competitors. Critical values and powers for these two rank tests are also discussed.     

Ban Estimation for Chi-Square Test Criteria in Categorical Data

This expository paper describes some recent work that further develops the theory of BAN estimators and the related chi-scuare test statistics.The extensions are in several directions: (a) the class of regular estimators is broadened by permitting extraneous random elements; (b) more general models are permitted under the constraint equations specification; and (c) BAN estimators are defined for general models combining features of two types of specification.In particular, WLS estimators are shown to be BAN.     

On the use of the scholz-sievers method for dlstribution-free inference about the difference in slopes of two regression lines

A simple adaptation of a distribution-free method due to Scholz (1978) and Sievers (1978) for inference in a single regression setting is proposed for inference about the difference in slopes of two regression lines. We assume that the data are obtained from a designed experiment with common regression constants. A comparison of the proposed method to its competitors-one due to Hollander and the other due to Rao and Gore-indicates superiority of the new method.     

Generalized Linear Models

The importance of random number generators has increased over the years. This follows from the fact that contemporary research methods rely more and more on simulation and the increased importance of encryption technology. The output of a random number generator is created by either an algorithm or a physical device. The most popular method for random number generation is through the use of an algorithm. This article presents a new category of physical random bit generator that is packaged by several manufacturers. A statistical analysis of the output from the generators is given.     

Accent on Teaching Materials

A linear combination test for combining several tests of the correlation coefficient in the bivariate normal distribution is proposed. The linear combination test is compared with the well-known Fisher method of combining tests. It is shown by a Monte Carlo study that the linear combination test has a larger power.