Bayesian incorporation of repeated measurements in logistic discrimination

A common problem in medical statistics is the discrimination between two groups on the basis of diagnostic information. Information on patient characteristics is used to classify individuals into one of two groups: diseased or disease-free. This classification is often with respect to a particular disease. This discrimination has two probabilistic components: (1) the discrimination is not without error, and (2) in many cases the a priori chance of disease can be estimated. Logistic models (Cox 1970; Anderson 1972) provide methods for incorporating both of these components. The a posteriori probability of disease may be estimated for a patient on the basis of both current measurement of patient characteristics and prior information. The parameters of the logistic model may be estimated on the basis of a calibration trial. In practice, not one but several sets of measurements of one characteristic of the patient may be made on a questionable case. These measurements typically are correlated; they are far from independent. How should these correlated measurements be used? This paper presents a method for incorporating several sets of measurements in the classification of a case.     

毒隐翅虫研究进展 1名称,分类与生物学

本文论及毒隐翅虫的学名、俗名、分类与生物学.该属棣于毒隐翅虫亚科的毒隐翅虫族.     

Criteria for the equality between ordinary least squares and best linear unbiased estimators under certain linear models

A new necessary and sufficient condition is derived for the equality between the ordinary least-squares estimator and the best linear unbiased estimator of the expectation vector in linear models with certain specific design matrices. This condition is then applied to special cases involving one-way and two-way classification models.     

An analysis of two probabilistic model induction techniques

Two probabilistic model induction techniques, cart and constructor, are compared, via a series of experiments, in terms of their ability to induce models that are both interpretable and predictive. The experiments show that, although both algorithms are able to deliver classifiers with predictive performance close to that of the optimal Bayes rule,constructor is able to generate a probabilistic model that is more easily interpretable than the cart model. On the other hand, cart is a more mature algorithm and is capable of handling many more situations (e.g., real-valued training sets) thanconstructor. A variety of characteristics of both algorithms are compared, and suggestions for future research are made.     

A Comment on Ali Tas˛ıran's `Wage and income effects on the timing and spacing of births in Sweden and in the United States'

This note reviews and evaluates Taşıran's (1995) claim that estimated female wage effects on Swedish fertility dynamics reported by Heckman and Walker (1990) are not robust to the use of microwage data. The results reported here indicate that once individual wage measures have been purged of measurement error, estimated female wage effects are not sensitive to the introduction of microwages. The results reported by Heckman and Walker (1990) persist even with the use of microwage data. Received: 8 March 1996/Accepted: 4 December 2001 I thank Tom MaCurdy, Eric French and two anonymous referees for useful comments. This research was supported by NICHD grants HD-19226 and HD-28685. The usual disclaimer applies. Responsible editor: Klaus F. Zimmermann.     

Integer programming formulations of statistical classification problems

A series of approaches is presented to formulate statistical classification problems using integer programming. The formulations attempt to maximize the number of observations that can be properly classified and utilize single function, multiple function and hierarchical multiple function approaches to the problems. The formulations are tested using standard software on a sample problem and new approaches are compared to those of other authors. As the solution of such problems gives rise to various awkward features in an integer programming framework, it is demonstrated that new approaches to formulation will not be completely successful in avoiding the difficulties of existing methods, but demonstrate certain gains.     

Feature Selection for Consistent Biclustering via Fractional 0–1 Programming

Biclustering consists in simultaneous partitioning of the set of samples and the set of their attributes (features) into subsets (classes). Samples and features classified together are supposed to have a high relevance to each other which can be observed by intensity of their expressions. We define the notion of consistency for biclustering using interrelation between centroids of sample and feature classes. We prove that consistent biclustering implies separability of the classes by convex cones. While previous works on biclustering concentrated on unsupervised learning and did not consider employing a training set, whose classification is given, we propose a model for supervised biclustering, whose consistency is achieved by feature selection. The developed model involves solution of a fractional 0–1 programming problem. Preliminary computational results on microarray data mining problems are reported.This research work was partially supported by NSF, NIH and AirForce grants.     

Analysis of overdispersed paired count data

This article is about the statistical analysis of overdispersed paired count data for comparing two treatments. The data consist of the number of events obtained in a stratum during the fixed observation period. Three types of model are discussed: the Poisson, a mixed, and a semiparametric model. Overdispersion is represented in the last two models but not in the Poisson model. Of particular interests are to examine whether there is any loss of efficiency in using the estimate of the treatment effect obtained under other two models if the mixed model is true, and also whether overdispersion leads to a larger variance of the estimate than that expected from the Poisson model. It is shown that all three models provide the same estimate of the treatment effect (i.e., there is no loss of efficiency) and that the variance of the estimate of the treatment effect obtained under the Poisson model is the same as that based on the mixed model. However, the semiparametric model provides the variance of the estimate larger than those obtained under the other two models.     

ABC Classification: Service Levels and Inventory Costs

ABC inventory classifications are widely used in practice, with demand value and demand volume as the most common ranking criteria. The standard approach in ABC applications is to set the same service level for all stock keeping units (SKUs) in a class. In this paper, we show (for three large real life datasets) that the application of both demand value and demand volume as ABC ranking criteria, with fixed service levels per class, leads to solutions that are far from cost optimal. An alternative criterion proposed by Zhang et al. performs much better, but is still considerably outperformed by a new criterion proposed in this paper. The new criterion is also more general in that it can take criticality of SKUs into account. Managerial insights are obtained into what class should have the highest/lowest service level, a topic that has been disputed in the literature.