Decomposing Bayesian networks: triangulation of the moral graph with genetic algorithms

In this paper we consider the optimal decomposition of Bayesian networks. More concretely, we examine empirically the applicability of genetic algorithms to the problem of the triangulation of moral graphs. This problem constitutes the only difficult step in the evidence propagation algorithm of Lauritzen and Spiegelhalter (1988) and is known to be NP-hard (Wen, 1991). We carry out experiments with distinct crossover and mutation operators and with different population sizes, mutation rates and selection biasses. The results are analysed statistically. They turn out to improve the results obtained with most other known triangulation methods (Kjærulff, 1990) and are comparable to results obtained with simulated annealing (Kjærulff, 1990; Kjærulff, 1992).     

Democratic transitions and the semiperiphery of the world-economy

The dramatic global transition to democracy of the last decade reveals important systematic patterns. Using recent contributions to world-systems theory, this study examines the relationship between political regime changes and the position of nations in the world-economy over the last two decades, to argue that democratic transitions have been centered among semiperipheral nations. The study also found a strong relationship between the structure of the labor force and the global distribution of democratic institutions, but a weak relationship between the structure of the labor force and the timing of transitions in the semiperiphery. Overall, the findings suggest that world-systemic categories provide a useful vantage point to distinguish global trends from the specific characteristics of individual nations, thereby allowing for greater analytical precision in identifying the crucial causal relations shaping transitions from dictatorship to democracy.     

A class of log-linear models with constrained marginal distributions

Summary In the log-linear model for bivariate probability functions the conditional and joint probabilities have a simple form. This property make the log-linear parametrization useful when modeling these probabilities is the focus of the investigation. On the contrary, in the log-linear representation of bivariate probability functions, the marginal probabilities have a complex form. So the log-linear models are not useful when the marginal probabilities are of particular interest. In this paper the previous statements are discussed and a model obtained from the log-linear one by imposing suitable constraints on the marginal probabilities is introduced. This work was supported by a M.U.R.S.T. grant.     

A general maximum likelihood analysis of measurement error in generalized linear models

This paper describes an EM algorithm for maximum likelihood estimation in generalized linear models (GLMs) with continuous measurement error in the explanatory variables. The algorithm is an adaptation of that for nonparametric maximum likelihood (NPML) estimation in overdispersed GLMs described in Aitkin (Statistics and Computing 6: 251–262, 1996). The measurement error distribution can be of any specified form, though the implementation described assumes normal measurement error. Neither the reliability nor the distribution of the true score of the variables with measurement error has to be known, nor are instrumental variables or replication required.Standard errors can be obtained by omitting individual variables from the model, as in Aitkin (1996).Several examples are given, of normal and Bernoulli response variables.     

The Influence of The People of Puerto Rico Project on Mexican Anthropology

In the 1970s in Mexico, anthropological regional projects were designed to explore new research interests: irrigation works, peasants, rural capitalism, and mines. Julian H. Steward, Eric R. Wolf, and Sidney W. Mintz, participants in the research project on Puerto Rico, were all popular authors among the new generation of anthropologists and were frequently cited in their thesis bibliographies. This article explores the influence of the People of Puerto Rico project at the design level of these new collective and regional projects. Students were distributed within larger areas, covering various climatic and production subareas, in their research training. The important role of cities, industries, haciendas, markets, and government programs was highlighted. I suggest that senior anthropologists and academic leaders who were planning this new anthropological era were more familiar than their students with the conceptual lines of the Puerto Rico Project. I gained greater insight into the difficulties of a regional research enterprise when I did anthropological research in the 1980s at the Tennessee Valley project.     

Identity status differences among Italian adolescents: Associations with time perspective

Based on Marcia's identity status model, this cross-sectional study examined adolescents' identity formation analyzing its association with time perspective. A sample of 1300 Italian adolescents filled in self-report measures assessing two major developmental processes: identity resolution and time perspective. Adolescents who achieved an integrated identity status seemed to primarily adopt a future time perspective and to have a positive view of the past. By contrast, Diffused adolescents reported negative experiences in the past, a lower future orientation and a greater inclination to fatalism compared to others.     

Intimate Partner Violence in Late Life: An Analysis of National News Reports

Intimate partner violence (IPV) in late life takes various forms including physical harm, sexual assault, and murder. Using national newspaper reports of IPV among elders, we identified the types of violence reported most frequently in media and examined how the abuse was conceptualized by reporters. We found that most cases of IPV reported involved murder, with men as perpetrators and women as victims. Caregiving stress and health problems were frequently cited as contributing factors in the cases. Interpreting these findings from a feminist perspective, we suggest implications for practitioners working with older adults.     

Using simulation to manage project supply chain in the offshore oil and gas industry

This paper is aimed at comparing simulation against spreadsheets as decision support tools to properly manage project supply chain in the offshore oil and gas industry. The paper presents a case study related to the problem of sizing a chain for pipeline laying from an offshore field in the Barents sea to the Russian coast. Results obtained through a spreadsheet developed by an oil and gas company have been compared to the ones gathered from an ad hoc simulation model. A simulation model with no stochastic variable has been introduced: results are quite similar to the ones of the spreadsheet, which allowed to validate the simulation model. However, the spreadsheet cannot take into account the continuous move of the pipe-lay vessel while laying the pipes and it does not consider stochastic variables whose effect in real life is not negligible. Both weaknesses above are discussed.     

Measuring Citizen Satisfaction with Aspects of Public Services from a Local Authority and Determining Their Importance: A Case Study

The measurement of service quality is a theme of great importance to service providers, particularly public agencies. Over the years their role has been changing by providing more and more high quality services, away from basic ones. In this paper the service quality of a local government is analyzed through the measurement of customer satisfaction. The analysis, based on a questionnaire survey, identified and classified the most essential factors that make up the customer satisfaction with the services provided by the Demographic Department of Gioia del Colle, a town in southern Italy.