Third-degree stochastic dominance and inequality measurement

We investigate the third-degree stochastic dominance order, which is receiving increasing attention in the field of inequality measurement. Observing that this partial order fails to satisfy the von Neumann–Morgenstern independence property in the space of random variables, we introduce the concepts of strong and local third-degree stochastic dominance, which do not suffer from this deficiency. We motivate these two new binary relations and characterize them in the spirit of the Lorenz characterization of the second-degree stochastic order, comparing our findings with the closest results in inequality literature. A preliminary version of this paper was presented at the second Canazei Winter School on Inequality and Collective Welfare Theory (IT2). We would like to thank all participants for their comments and suggestions. We are especially grateful to Rolf Aaberge, Peter Lambert, Maria G. Monti, Ernesto Savaglio, John Weymark, Claudio Zoli and two anonymous referees who provided very detailed and insightful comments.     

Factors associated with long-term benzodiazepine use among elderly women and men in Quebec

The goal of this study was to compare factors associated with long-term benzodiazepine use by elderly women and men (n = 1701) who participated in the Quebec Health Survey (QHS). Data from the 1998 QHS were linked with data from the administrative files of the Régie de l'assurance maladie du Québec. Results showed that elderly women were more at risk than men for long-term benzodiazepine use. Results of the multivariate logistic regression did not show a significant difference between women and men on any of the risk factors studied. Other factors such as elderly and physician attitudes deserve further study to explain differences in long-term benzodiazepine use between elderly women and men.     

On the equivalence of coalitional and individual strategy-proofness properties

In this paper, we introduce a sufficient condition on the domain of admissible preferences of a social choice mechanism under which the properties of individual and coalitional strategyproofness are equivalent. Then, we illustrate the usefulness of this general result in the case where a fixed budget has to be allocated among several pure public goods. We would like to express our deepest gratitude to our referee for an extremely careful and detailed report. His/her challenging questions did force us to be more acute on the scope of validity and the limits of our result. We would like also to thank Bernardo Moreno for pointing out a mistake in the statement of Theorem 1 as it was formulated in an earlier version and for sending a copy of his joint work with Barbera et al. (2008). This is the only one paper we know of, offering an alternative systematic analysis of the question explored in our paper.     

Transition from playing with simulated gambling games to gambling with real money: a longitudinal study in adolescence

Digital technology advances have supported an expansion of gambling activities, which is notable via the advent of simulated gambling games. Simulated gambling reproduces ‘real’ gambling activities, which enables the users to gamble without investing money. According to research evidence, a certain number of adolescents are playing with these games, but until now little has been known about how they could facilitate the migration to gambling with real money. Using a longitudinal design with a one-year interval period, the goal of this study was to assess the potential transition between playing with simulated gambling and the initiation to gambling with real money. The final sample was constituted of 1220 adolescents (age range = 14 to 18 y.o.) who had never played with real money at the first measurement time. At the second measurement time, 28.8% of the participants had gambled for the first time with real money. Logistic regressions revealed that the predictive association between simulated gambling and gambling with real money only holds for adolescents who transitioned from simulated poker to poker with real money. These findings highlight the need for regulation and monitoring on Internet gambling poker sites, as well as further research to assess the mechanisms at work.     

On the (sequential) majority choice of public good size and location

This article studies majority voting over the size and location of a public good when voters differ both in income and in their preferences for the public good location. Public good provision is financed either by a lump sum tax or by a proportional income tax. We analyze both the simultaneous and the sequential determinations of the public good’s size and location. We show that, while the choice of the type of public good follows the traditional median logic, the majoritarian determination of the taxation rate need not coincide with the preferences of a median income citizen. With lump sum financing, income heterogeneity plays no role and the sequential equilibrium consists of the median location together with the public good level most-preferred by the individual located at the median distance from the median. This policy bundle also constitutes an equilibrium with simultaneous voting in the special case of a uniform bivariate distribution of individuals’ income and location. With proportional taxation, there is no policy equilibrium with simultaneous voting. We offer a complete characterization of the equations describing the sequential equilibrium in the general case and we show why and how our results depart from those most-preferred by the median income individual located at the median distance from the median. We also compare these majority voting allocations with the socially optimal one.     

A two‐step proximal‐point algorithm for the calculus of divergence‐based estimators in finite mixture models

Estimators derived from the expectation‐maximization (EM) algorithm are not robust since they are based on the maximization of the likelihood function. We propose an iterative proximal‐point algorithm based on the EM algorithm to minimize a divergence criterion between a mixture model and the unknown distribution that generates the data. The algorithm estimates in each iteration the proportions and the parameters of the mixture components in two separate steps. Resulting estimators are generally robust against outliers and misspecification of the model. Convergence properties of our algorithm are studied. The convergence of the introduced algorithm is discussed on a two‐component Weibull mixture entailing a condition on the initialization of the EM algorithm in order for the latter to converge. Simulations on Gaussian and Weibull mixture models using different statistical divergences are provided to confirm the validity of our work and the robustness of the resulting estimators against outliers in comparison to the EM algorithm. An application to a dataset of velocities of galaxies is also presented. The Canadian Journal of Statistics 47: 392–408; 2019 © 2019 Statistical Society of Canada     

Proportionate universalism in child and family social work

Integrated services in preventive health care and child and family social work increasingly embrace the concept of proportionate universalism (PU) as a means of overcoming the dichotomy between universal and targeted services in contexts of diversity. The implementation of the concept of PU raises several theoretical and empirical questions that form the basis of this article. This study aims to provide more insight in how the concept of PU is operationalized in child and family social work. Qualitative research was performed in three specific cases of child and family social work, the so‐called “Huizen van het Kind” or Children's Houses in Flanders (Belgium). The study triangulates three perspectives: policy, organizational level, and street level. The findings generate three meta‐themes: perseverant structuring of populations or predefinitions, image and conceptualization of the Children's House, and organizational challenges. These results reveal a difference between the theoretical assumption of PU and the practical implementation in child and family social work.     

On S-Convexity and Risk Aversion

The present note first discusses the concept of s-convex pain functions in decision theory. Then, the economic behavior of an agent with such a pain function is represented through the comparison of some recursive lotteries.     

Multilevel Models in the Study of Dynamic Household Structures

A modelling procedure is proposed for complex, dynamic household data structures where households change composition over time. Multilevel multiple membership models are presented for such data and their application is discussed with an example.