Nonparametrio bayes and empirical bayes estimation of the residual survival function at age t

Nonparametric Bayes and empirical Bayes estimations of the

survival function of a unit of age t (> 0) using Dirichlet

process prior are presented. The proposed empirical Bayes

estimators are found to be “asymptotically optimal” in the sense of Robbins (1955). The performances of the proposed

empirical Bayes estimators are compared with those of certain

rival estimators in terms of relative savings loss, The exact

expressions for Bayes risks are also provided in certain cases.     

Minque of variance components in generalized linear model with random effects

We consider the estimation of thc variance components in generalized Linear model with random effects. The Method of Minimum Norm Quadratic Unbiased Estimators extending the Rao's argument is outlined. The method is illustrated with an analysis of cell irradiation data and compared to the methods of estimation proposed by Schall (1991).     

Random effects models for count data

Random effects models are considered for count data obtained in a cross or nested classification. The main feature of the proposed models is the use of the additive effects on the original scale in contrast to the commonly used log scale. The rationale behind this approach is given. The estimation of variance components is based on the usual mean square approach. Directly analogous results to those from the analysis of variance models for continuous data are obtained. The usual Poisson dispersion test procedure can be used not only to test for no overall random effects but also to assess the adequacy of the model. Individual variance component can be tested by using the usual F-test. To get a reliable estimate, a large number of factor levels seem to be required.     

Analysis of ordered covariate effects among groups with repeated measurements

Testing procedures for ordered covariate effects are developed in the repeated measures experiment. The maximum likelihood estimators of covariate effects under the ordered hypothesis are approximated by the isotonic regression of their unconstrained estimators. The asymptotic null distributions of the test statistics are chi-bar-square distributions which are mixtures of chi-square distributions. A Monte-Carlo simulation reveals that the proposed test for ordered covariate effects is seriously more powerful than the usual chi-square test that neglects the information on the order restriction. These testing methods are applied for analyzing the effect of vitamin E diet supplement on growth rate of animals.     

Asian and Pacific Region Authorship Characteristics in Leading Library and Information Science Journals

Authorship characteristics from the Asian and Pacific region in the top twenty journals in library and information science are studied. Data was collected searching the Institute for Scientific Information (ISI) Web of Science databases. Major findings of this study are: there are a total of 1,317 articles for the period 1967 to 2005; the most productive countries are, in rank order, Australia, China, South Korea, Taiwan, Singapore, Japan, New Zealand, Malaysia, Thailand and Philippines; and 77.6 percent of authors in the top twenty library and information science journals contributed a single article. Among the library science journals about 50 percent were written by multiple authors, while 73.1 percent of articles in the information science journals were written collaboratively. The most productive individual authors in the region are reported. The strongest collaboration within the region took place between Australia and China; China and Singapore; Australia and New Zealand.     

Selection of Binary Variables and Classification by Boosting

We adopt boosting for classification and selection of high-dimensional binary variables for which classical methods based on normality and non singular sample dispersion are inapplicable. Boosting seems particularly well suited for binary variables. We present three methods of which two combine boosting with the relatively classical variable selection methods developed in Wilbur et al. (2002 Wilbur , J. D. , Ghosh , J. K. , Nakatsu , C. H. , Brouder , S. M. , Doerge , R. W. ( 2002 ). Variable selection in high-dimensional multivariate binary data with application to the analysis of microbial community DNA fingerprints . Biometrics 58 : 378 – 386 . [Google Scholar]). Our primary interest is variable selection in classification with small misclassification error being used as validation of proposed method for variable selection. Two of the new methods perform uniformly better than Wilbur et al. (2002 Wilbur , J. D. , Ghosh , J. K. , Nakatsu , C. H. , Brouder , S. M. , Doerge , R. W. ( 2002 ). Variable selection in high-dimensional multivariate binary data with application to the analysis of microbial community DNA fingerprints . Biometrics 58 : 378 – 386 . [Google Scholar]) in one set of simulated and three real life examples.     

LOCAL POLYNOMIAL QUASI-LIKELIHOOD REGRESSION ON RANDOM FIELDS

In this paper, local quasi‐likelihood regression is considered for stationary random fields of dependent variables. In the case of independent data, local polynomial quasi‐likelihood regression is known to have several appealing features such as minimax efficiency, design adaptivity and good boundary behaviour. These properties are shown to carry over to the case of random fields. The asymptotic normality of the regression estimator is established and explicit formulae for its asymptotic bias and variance are derived for strongly mixing stationary random fields. The extension to multi‐dimensional covariates is also provided in full generality. Moreover, evaluation of the finite sample performance is made through a simulation study.     

A parametric approach for measuring the effect of the 10th revision of the international classification of diseases

Summary.  The World Health Organization revises the international classification of diseases about every 10 years to stay abreast of advances in medical science and to compare international health statistics. However, the new revision (i.e. the 10th revision) introduces discontinuities in mortality trends, making it impossible to compare the mortality statistics before and after the revision directly. The US National Center for Health Statistics published comparability ratios to correct the discontinuities between the two sets of mortality data: one coded by the ninth revision and the other by the 10th revision. We propose a parametric two-stage model to produce new comparability ratios and use these ratios to correct the discontinuities. The asymptotic behaviour of the comparability ratios is investigated. Our model not only measures the extent of discontinuities in trends in mortality but also can be used to forecast future mortality. Comparing with the National Center for Health Statistics's ratios, our comparability ratios smooth out the discontinuities better for most causes.