Robust methods for generalized linear models with nonignorable missing covariates

The EM algorithm is often used for finding the maximum likelihood estimates in generalized linear models with incomplete data. In this article, the author presents a robust method in the framework of the maximum likelihood estimation for fitting generalized linear models when nonignorable covariates are missing. His robust approach is useful for downweighting any influential observations when estimating the model parameters. To avoid computational problems involving irreducibly high‐dimensional integrals, he adopts a Metropolis‐Hastings algorithm based on a Markov chain sampling method. He carries out simulations to investigate the behaviour of the robust estimates in the presence of outliers and missing covariates; furthermore, he compares these estimates to the classical maximum likelihood estimates. Finally, he illustrates his approach using data on the occurrence of delirium in patients operated on for abdominal aortic aneurysm.     

Patient violence. Report of 200 incidents

Studies of assaultive behavior in hospital settings are increasing. Results are often contradictory. These variances are dependent upon the type of hospital, the specific setting, and the disciplines involved in the reporting process. Open recognition that violent incidents occur, and the substitution of fact finding for finger pointing, are the first steps toward prevention and management.     

The value of green belt land

This paper estimates the value of green belt land by assessing its output: agricultural; amenity; recreational; and savings in costs, by restricting the size of urban areas. These outputs are valued in social terms by the application of welfare economics. Some types of agriculture are shown to impose net social cost rather than benefits. Hedonic price models and contingent valuation are used to assess amenity benefits which are revealed as the most important justification for green belts. These benefits are set against the opportunity cost of the land in terms of foregone housing and industrial development. Uncertainty and irreversibility of a land-use change, from green belt, suggests that the benefits of housing or industry should substantially exceed the value of green belt land before a land-use change is sanctioned.     

Estate Inheritance: A Sociological Lacuna*

Estate inheritance, a frequently mentioned but rarely examined feature of stratification systems, has been a neglected area of research in sociology. In this paper, several possible causes of the sociological neglect are discussed. The treatment of inheritance patterns in functionalist and conflict theories of stratification is analyzed, and an overview of existing research on inheritance is presented. Finally, a conflict theory of stratification that incorporates the phenomenon of inheritance is proposed, and avenues for further research are suggested.     

Multilevel Latent Class Models

The latent class (LC) models that have been developed so far assume that observations are independent. Parametric and nonparametric random–coefficient LC models are proposed here, which will make it possible to modify this assumption. For example, the models can be used for the analysis of data collected with complex sampling designs, data with a multilevel structure, and multiple–group data for more than a few groups. An adapted EM algorithm is presented that makes maximum–likelihood estimation feasible. The new model is illustrated with examples from organizational, educational, and cross–national comparative research.     

Examining the Impact of Changes in Maternal Employment on High School Completion Among Low-Income Youth

The passage of the Personal Responsibility and Work Opportunity Reconciliation Act and decisions about its re-authorization have resurrected interest in the impact of maternal employment on child outcomes in poor families. The emerging evidence suggests that employment stability among former welfare recipients is a key factor in making successful transitions from welfare to work. This investigation explores how changes in maternal employment in poor families relate to high school completion among at risk youths. Our findings show that a substantial number of mothers experience unstable employment patterns. This instability is positively correlated with dropout among adolescents. The paper concludes with policy implications for the next phase of welfare reform.