Learning discrete decomposable graphical models via constraint optimization

Statistical model learning problems are traditionally solved using either heuristic greedy optimization or stochastic simulation, such as Markov chain Monte Carlo or simulated annealing. Recently, there has been an increasing interest in the use of combinatorial search methods, including those based on computational logic. Some of these methods are particularly attractive since they can also be successful in proving the global optimality of solutions, in contrast to stochastic algorithms that only guarantee optimality at the limit. Here we improve and generalize a recently introduced constraint-based method for learning undirected graphical models. The new method combines perfect elimination orderings with various strategies for solution pruning and offers a dramatic improvement both in terms of time and memory complexity. We also show that the method is capable of efficiently handling a more general class of models, called stratified/labeled graphical models, which have an astronomically larger model space.     

Emotional Transactions in the Paris Subway: Combining Naturalistic Videotaping,Objective Facial Coding and Sequential Analysis in the Study of Nonverbal Emotional Behavior

We report on what, to our knowledge, represents the first study of nonverbal emotional behavior in crowded public places combining naturalistic videotaping of situated activity, objective coding of facial movement, and sequential analysis of behavior. In the first part of the study we argue that passengers do not lose emotional sensitivity to physical contact as density (passengers per square meter) increases, which indicates that physical contact is experienced as a territorial intrusion regardless of crowdedness. In the second part of the study, we suggest that passengers resolve the emotions due to intrusive physical contacts through two interactional strategies involving facial movements usually interpreted as “expressions of emotions.” Since proxemic violations seem to represent a pervasive emotion elicitor, the protocol can be extended to other means of transportation and replicated in other locations. We conclude that the methodology provides an effective tool for theory-building in the study of nonverbal emotional behavior.     

Impacts of urban sprawl on species richness of plants,butterflies, gastropods and birds: not only built-up area matters

Urban growth is a major factor of global environmental change and has important impacts on biodiversity, such as changes in species composition and biotic homogenization. Most previous studies have focused on effects of urban area as a general measure of urbanization, and on few or single taxa. Here, we analyzed the impacts of the different components of urban sprawl (i.e., scattered and widespread urban growth) on species richness of a variety of taxonomic groups covering mosses, vascular plants, gastropods, butterflies, and birds at the habitat and landscape scales. Besides urban area, we considered the average age, imperviousness, and dispersion degree of urban area, along with human population density, to disentangle the effects of the different components of urban sprawl on biodiversity. The study was carried out in the Swiss Plateau that has undergone substantial urban sprawl in recent decades.Vascular plants and birds showed the strongest responses to urban sprawl, especially at the landscape scale, with non-native and ruderal plants proliferating and common generalist birds increasing at the expense of specialist birds as urban sprawl grew. Overall, urban area had the greatest contribution on such impacts, but additional effects of urban dispersion (i.e., increase of non-native plants) and human population density (i.e., increases of ruderal plants and common generalist birds) were found. Our findings support the hypothesis that negative impacts of urban sprawl on biodiversity can be reduced by compacting urban growth while still avoiding the formation of very densely populated areas.     

Exploring the nonverbal facet of ethnic discrimination: a field experiment on anti-Roma racism in the Paris métro

A field experiment on the discrimination of Roma migrants from Eastern Europe was conducted in two stations of the Paris metro to explore the behaviors that may communicate misrecognition in everyday encounters. An actress asked for help to randomly chosen passengers on a metro platform, wearing a glaringly Romani skirt in the treatment condition but an unconspicuous middle-class style in the control condition. In interaction with the actress wearing the Romani skirt, passengers were found to enact the so-called “visual dominance pattern”, and male passengers in particular were found to keep greater distances. Reverse discrimination also occurred as women kept shorter distances from the actress bearing the ethnic stigma. Last, passengers helped less the stigmatized actress, but only in one of the two metro stations where trials were conducted.     

Activation and social inclusion: challenges and possibilities

The last two decades have seen an increasing focus on the activation of individuals receiving welfare benefits. This has entailed an attempt to transform employment assistance and social security systems to make them more employment‐friendly through the development of explicit linkages between social protection policies, labour market participation and labour market programs. At the same time there has been a growing interest in the concept of social inclusion, and social inclusion has been a commonly stated goal of activation programs. However, despite some synergies between these two approaches, in other respects it is not clear that they are always compatible. This paper explores the extent to which activation programs are central to the social inclusion approach and the similarities and differences between these approaches. It then briefly examines the evidence regarding the ability of activation programs to enhance social inclusion.     

Academic economists behaving badly? A survey on three areas of unethical behavior

This article measures the degree to which academic economists have engaged in unethical behavior and the degree to which academic economists believe the profession as a whole engages in unethical behavior. Three main types of unethical behavior are examined: (1) falsification of research; (2) expropriation of graduate student research or including an undeserving co-author on a research paper; and (3) exchange of grades for gifts, money, or sex. Using a unique data set gathered at the 1998 American Economic Association (AEA) meetings, we find that there is a significant amount of misconduct, particularly in the second category.     

A Note on the Large Sample Properties of Estimators Based on Generalized Linear Models for Correlated Pseudo‐observations

Pseudo‐values have proven very useful in censored data analysis in complex settings such as multi‐state models. It was originally suggested by Andersen et al., Biometrika, 90, 2003, 335 who also suggested to estimate standard errors using classical generalized estimating equation results. These results were studied more formally in Graw et al., Lifetime Data Anal., 15, 2009, 241 that derived some key results based on a second‐order von Mises expansion. However, results concerning large sample properties of estimates based on regression models for pseudo‐values still seem unclear. In this paper, we study these large sample properties in the simple setting of survival probabilities and show that the estimating function can be written as a U‐statistic of second order giving rise to an additional term that does not vanish asymptotically. We further show that previously advocated standard error estimates will typically be too large, although in many practical applications the difference will be of minor importance. We show how to estimate correctly the variability of the estimator. This is further studied in some simulation studies.     

Validation of Nonparametric Two-sample Bootstrap in ROC Analysis on Large Datasets

The nonparametric two-sample bootstrap is applied to computing uncertainties of measures in receiver operating characteristic (ROC) analysis on large datasets in areas such as biometrics, speaker recognition, etc. when the analytical method cannot be used. Its validation was studied by computing the standard errors of the area under ROC curve using the well-established analytical Mann–Whitney statistic method and also using the bootstrap. The analytical result is unique. The bootstrap results are expressed as a probability distribution due to its stochastic nature. The comparisons were carried out using relative errors and hypothesis testing. These match very well. This validation provides a sound foundation for such computations.     

The Local Power of the CADF and CIPS Panel Unit Root Tests

Very little is known about the local power of second generation panel unit root tests that are robust to cross-section dependence. This article derives the local asymptotic power functions of the cross-section argumented Dickey–Fuller Cross-section Augmented Dickey-Fuller (CADF) and CIPS tests of Pesaran (2007), which are among the most popular tests around.