The Euclidean distance classifier: an alternative to the linear discriminant function

The sample linear discriminant function (LDF) is known to perform poorly when the number of features p is large relative to the size of the training samples, A simple and rarely applied alternative to the sample LDF is the sample Euclidean distance classifier (EDC). Raudys and Pikelis (1980) have compared the sample LDF with three other discriminant functions, including thesample EDC, when classifying individuals from two spherical normal populations. They have concluded that the sample EDC outperforms the sample LDF when p is large relative to the training sample size. This paper derives conditions for which the two classifiers are equivalent when all parameters are known and employs a Monte Carlo simulation to compare the sample EDC with the sample LDF no only for the spherical normal case but also for several nonspherical parameter configurations. Fo many practical situations, the sample EDC performs as well as or superior to the sample LDF, even for nonspherical covariance configurations.     

Ethnic mobilization,multiculturalism and the political process in two Belgian cities: Antwerp and Liège

Next to discussing aspects of the political and social situation of migrant ethnic communities in two Belgian cities, this article provides interesting insight into identity politics in contemporary Belgium divided between the Flemish emphasis on cultural and linguistic homogenization and hegemonization and the Walloon focus on citizenship. This fundamental ideological split influences also how multiculturalism is discussed and practiced in the two parts of Belgium in general and in Antwerp and Liege in particular.     

Even Risk-Averters may Love Risk

A decision maker bets on the outcomes of a sequence of coin-tossings. At the beginning of the game the decision maker can choose one of two coins to play the game. This initial choice is irreversible. The coins can be biased and the player is uncertain about the nature of one (or possibly both) coin(s). If the player is an expected-utility maximizer, her choice of the coin will depend on different elements: the nature of the game (namely, whether she can observe the outcomes of the previous tosses before making her next decision), her utility function, the prior distribution on the bias of the coin. We will show that even a risk averter might optimally choose a riskier coin when learning is allowed. We will express most of our results in the language of stochastic orderings, allowing comparisons that are valid for large classes of utility functions.     

Finite mixtures approach to ecological regression

During past few years great attention has been devoted to the analysis of disease incidence and mortality rates, with an explicit focus on modelling geographical variation of rates observed in spatially adjacent regions. The general aim of these contributes has been both to highlight clusters of regions with homogeneous relative risk and to determine the effects of observed and unobserved risk factors related to the analyzed disease. Most of the proposed modelling approaches can be derived as alternative specifications of the components of a general convolution model (Molliè, 1996). In this paper, we consider the semiparametric approach discussed by Schlattmann and Böhning (1993); in particular, we focus on models with an explicit spatially structured component (see Biggeri et al., 2000), and propose alternative choices for the structure of the spatial component.     

Network,exposure and rhetoric: Italian occupational fields and heterogeneity in constructing the globalized self

Drawing on the findings of a broad inter‐university research programme conducted in Italy, in this article we explore how individuals' transnational networks combine with other dimensions of their social experience in the production of a self‐perception of their own ‘global identity’. In particular, attention is focused on the structures and social spaces of everyday life in five crucial occupations (corporate managers, financial services workers, artists, media professionals and schoolteachers) where people's professional action is performed simultaneously along local and global axes. Within these groups the globalized self does not merely reflect individuals' engagement in transnational networks, but is also the outcome of a complex process including two added dimensions of social life in the job setting: (1) the degree and type of non‐filtered exposure to pressures stemming from the global environment, which both constrain and enable subjective practices of coping with change and ambiguity; and (2) the degree and type of competence in the rhetorics of globalization, namely the level of access to well‐known repertoires of interpretive resources for making sense of global trends. This analysis is consistent with social science conceptualizations arguing for a more nuanced understanding of globalization. In this light, not only is globalization a multidimensional process but it also produces a variety of responses and meanings by differently positioned actors.     

A Critical Reflection on the Experimental Method for Planning Research: Testing the Added Value of PSS in a Controlled Environment

For planning research to successfully generate usable mechanisms for planning practitioners more hypothesis-testing research designs are needed. Currently, the academic field seems more geared toward generating hypotheses, either by observing practice or from theoretical studies. This approach is especially common in research that generates knowledge of planning. In this paper, I map several relevant research designs that allow for such hypothesis testing and discuss their usability in planning research. Then, I particularly focus on the experimental method as a promising design for generating contextualized mechanisms for planning practice. I describe and analyze a study that aimed to develop mechanisms about the added value of knowledge technologies for the quality of planning. Two consecutive experiments are described in detail, after which the usability of the experimental method for planning research is discussed. Reflecting on these experiments indicate that the main strength of this research design is that it allows to create ideal circumstances for falsification (which is virtually impossible in planning practices. The main weakness is the ecological validity of findings, especially when the research is executed with students.     

A New Perspective on Neonatal Smiling: Differences Between the Judgments of Expert Coders and Naive Observers

To better understand the form and recognizability of neonatal smiling, 32 newborns (14 girls; M = 25.6 hr) were videorecorded in the behavioral states of alertness, drowsiness, active sleep, and quiet sleep. Baby Facial Action Coding System coding of both lip corner raising (simple or non‐Duchenne) and lip corner raising with cheek raising (Duchenne smile) was followed by a smile recognition task using 48 naive observers. Both types of smiles were detected in all behavioral states. Lip corner raising with cheek raising (Duchenne smiling) tended to predominate in active (rapid eye movement) sleep, suggesting a potential tie to early constituents of emotion. A significant portion of the typically briefer lip corner raising distinguished by expert coders was not recognized as smiling by the naive observers. These briefer actions may represent a motor phenomenon idiosyncratic to the neonatal period.     

Variance component models for longitudinal count data with baseline information: epilepsy data revisited

Random effect models have often been used in longitudinal data analysis since they allow for association among repeated measurements due to unobserved heterogeneity. Various approaches have been proposed to extend mixed models for repeated count data to include dependence on baseline counts. Dependence between baseline counts and individual-specific random effects result in a complex form of the (conditional) likelihood. An approximate solution can be achieved ignoring this dependence, but this approach could result in biased parameter estimates and in wrong inferences. We propose a computationally feasible approach to overcome this problem, leaving the random effect distribution unspecified. In this context, we show how the EM algorithm for nonparametric maximum likelihood (NPML) can be extended to deal with dependence of repeated measures on baseline counts.     

Assessment of Organizational Trust: Italian Adaptation and Factorial Validity of the Organizational Trust Inventory

Trust influences interactions among individuals and organizations but has been an elusive concept to define and measure. The Organizational Trust Inventory (OTI) measures three dimensions of organizational trust, as defined by Cummings and Bromiley (in: Kramer and Tyler (eds) Trust in Organizations, 1996), believing or feeling that others: keep commitments, negotiate honestly, and do not take excessive advantage. This research presents an original adaptation of the OTI for the Italian people. It can now be used to evaluate trust regarding colleagues, managers, suppliers, subordinates, clients, and organizations. Using a sample of 490 employees and structural equation modeling, we consider the validity of the questionnaire and the theoretical model articulation both across different counterpart and countries. Besides, we develop a new reduced-form of the questionnaire (OTI/R), which offers better psychometric properties than the long form.