Robust weighted likelihood estimators with an application to bivariate extreme value problems

The authors achieve robust estimation of parametric models through the use of weighted maximum likelihood techniques. A new estimator is proposed and its good properties illustrated through examples. Ease of implementation is an attractive property of the new estimator. The new estimator downweights with respect to the model and can be used for complicated likelihoods such as those involved in bivariate extreme value problems. New weight functions, tailored for these problems, are constructed. The increased insight provided by our robust fits to these bivariate extreme value models is exhibited through the analysis of sea levels at two East Coast sites in the United Kingdom.     

A multidimensional and contextual framework for understanding diverse family members' roles in long-term care facilities

Very few studies have explicitly examined the roles of family members in institutionalized settings and how these roles are developed. The most widely used theoretical framework employed in the studies that do exist is Litwak's structural-functionalist framework—the theory of shared functions and balanced coordination. Although Litwak's theory emphasizes the importance of both formal organizations (e.g., long-term care facilities) and primary groups (e.g., family) to optimal care, the framework provides a limited understanding of the roles of family members in long-term care facilities. The first section of this article describes Litwak's framework and then outlines the limitations of this task-assignment approach. By adopting a symbolic interactionist approach and integrating concepts from an ecological perspective and Hughes' concept of career, an alternative, more dynamic, contextual framework for understanding the roles of family members in long-term care settings is presented.     

Latent Variable Models for Mixed Discrete and Continuous Outcomes

We propose a latent variable model for mixed discrete and continuous outcomes. The model accommodates any mixture of outcomes from an exponential family and allows for arbitrary covariate effects, as well as direct modelling of covariates on the latent variable. An EM algorithm is proposed for parameter estimation and estimates of the latent variables are produced as a by-product of the analysis. A generalized likelihood ratio test can be used to test the significance of covariates affecting the latent outcomes. This method is applied to birth defects data, where the outcomes of interest are continuous measures of size and binary indicators of minor physical anomalies. Infants who were exposed in utero to anticonvulsant medications are compared with controls.     

Beliebt und immer beliebter? Fernsehen und Freizeit in Deutschland 1987�C2007

The hypothesis that Germans devote an ever bigger share of their increasing leisure time to television is justified by a comparison with further leisure activities: Television exceeds all these??except the internet??by its increasing supply and increasing differentiation. This hypothesis is examined using the so-called Media-Analysen 1987?C2007. It is confirmed by regression analyses of the absolute and relative television viewing time on time points or on the extent and the differentiation of television supply, controlling for opportunities and preferences as well as cohort membership, region and gender. Thus, television does not lose leisure shares to new media, but crowds out old leisure pastimes.