On regression modelling with dummy variables versus separate regressions per group: Comment on Holgersson et al.

In a recent issue of this journal, Holgersson et al. [Dummy variables vs. category-wise models, J. Appl. Stat. 41(2) (2014), pp. 233–241, doi:10.1080/02664763.2013.838665] compared the use of dummy coding in regression analysis to the use of category-wise models (i.e. estimating separate regression models for each group) with respect to estimating and testing group differences in intercept and in slope. They presented three objections against the use of dummy variables in a single regression equation, which could be overcome by the category-wise approach. In this note, I first comment on each of these three objections and next draw attention to some other issues in comparing these two approaches. This commentary further clarifies the differences and similarities between dummy variable and category-wise approaches.     

An experimental investigation of risk sharing and adverse selection

Does adverse selection hamper the effectiveness of voluntary risk sharing? How do differences in risk profiles affect adverse selection? We experimentally investigate individuals’ willingness to share risks with others. Across treatments we vary how risk profiles differ between individuals. We find strong evidence for adverse selection if individuals’ risk profiles can be ranked according to first-order stochastic dominance and only little evidence for adverse selection if risk profiles can only be ranked according to mean-preserving spreads. We observe the same pattern also for anticipated adverse selection. These results suggest that the degree to which adverse selection erodes voluntary risk sharing arrangements crucially depends on the form of risk heterogeneity.     

Maternal Conflict Behavior Profiles and Child Social Skills

The current study examined associations between mothers’ behavioral profiles during mother‐child conflict interactions and their children's social skills. This person‐centered approach classified 181 mothers according to their levels of emotional responsiveness, intrusiveness, negativity, and engagement facilitation behaviors during an eight‐minute conflict discussion task with their child. Three distinct classes of mothers were identified using latent profile analysis: sensitive/engaged, moderately sensitive/engaged, and insensitive/disengaged. An analysis of covariance indicated that children of mothers in the sensitive/engaged group had significantly higher social skills than children of mothers in the moderately sensitive/engaged and insensitive/disengaged groups. Results suggest that mother‐child conflict interactions may benefit children's social development when mothers facilitate their children's participation in a highly sensitive manner.     

Promoting Ethnic Entrepreneurship in European Cities: Sometimes Ambitious,Mostly Absent,Rarely Addressing Structural Features

An increasing number of immigrants have become entrepreneurial and many governments expect or hope that the ongoing rise of ethnic entrepreneurship will contribute significantly to the integration of immigrants, to their upward mobility, and to the economic development of the city of residence. In this article we explore the rules, regulations and policy interventions that shape self‐employment trajectories in general and those of immigrant ethnic minorities in particular. The article is based on a general inventory of measures to promote ethnic entrepreneurship in 32 European countries, and a somewhat deeper inventory of policies and interventions in 28 European cities. We came across all kinds of measures and interventions and identified certain patterns, but the most striking finding was that such explicit measures and interventions were actually thin on the ground. We conclude this article with a discussion of the structural determinants of this outcome.     

Predictors of Antisocial and Prosocial Behavior in an Adolescent Sports Context

This study examined antisocial and prosocial behavior of N = 439 adolescent athletes between 14 and 17 years of age (67 teams). Multi‐level analyses showed that team membership explained 20 and 13 percent of the variance in antisocial and prosocial behavior in the sports context, respectively. The team effects suggest that aggregating antisocial or prosocial adolescents within teams may partially explain differences in antisocial and prosocial behavior among athletes in the sports context. A trend was found toward a relation between higher levels of moral reasoning within teams, and less antisocial behavior in the sports context. Favorable moral atmosphere was positively associated with more prosocial behavior in the sports context. Finally, supportive coach–athlete relationships were associated with both less antisocial and more prosocial behavior in the sports context.     

Bayesian Classifiers Applied to the Tennessee Eastman Process

Fault diagnosis includes the main task of classification. Bayesian networks (BNs) present several advantages in the classification task, and previous works have suggested their use as classifiers. Because a classifier is often only one part of a larger decision process, this article proposes, for industrial process diagnosis, the use of a Bayesian method called dynamic Markov blanket classifier that has as its main goal the induction of accurate Bayesian classifiers having dependable probability estimates and revealing actual relationships among the most relevant variables. In addition, a new method, named variable ordering multiple offspring sampling capable of inducing a BN to be used as a classifier, is presented. The performance of these methods is assessed on the data of a benchmark problem known as the Tennessee Eastman process. The obtained results are compared with naive Bayes and tree augmented network classifiers, and confirm that both proposed algorithms can provide good classification accuracies as well as knowledge about relevant variables.     

Understanding the complexity of knowledge integration in collaborative new product development teams: A case study

Knowledge integration is important in collaborative new product development (Co-NPD). The research literature shows that the way actors create a shared understanding about the new to create products is a quality indicator of Co-NPD. This study investigates what factors influence the creation of a shared understanding in Co-NPD. The results show factors at three different levels; the actor, project and company level. Additionally, there exist relationships across the factors. The related factors form four different types of interfaces. The interfaces differ from each other since different types of collaborative mechanisms exist within them.     

Unraveling quantity discounts

We consider the situation in which a buying organization deals with a discrete quantity discount schedule offered by a selling organization. Furthermore, the buying organization can negotiate with the selling organization about the lot size and purchase price, but does not know the underlying function that was used by the selling organization to determine the quantity discount schedule. In this paper, we provide an analytical and empirical basis for one general quantity discount function (QDF) that can be used to describe the underlying function of almost all different quantity discount types. We first develop such a QDF analytically. Among other things, this QDF enables buying organizations to calculate detailed prices for a large number of quantities. We subsequently show that the QDF fits very well with 66 discount schedules found in practice. We discuss that the QDF and related indicators can be a useful tool in supplier selection and negotiation processes. It can also be used for competitive analyses, multiple sourcing decisions, and allocating savings for purchasing groups. Additionally, the QDF can be included in research models incorporating quantity discounts. We conclude the paper with an outlook on further QDF research regarding the characterization of commodity markets from a demand elasticity point of view.     

Poverty Research in a Development Policy Context

This article provides an evaluation of the extent to which science is addressing worldwide poverty and hunger. It is based on the literature contained in the Thomson Reuters' Web of Science Citation Index (1980 to 2008) and focuses on the WOTRO Strategy Plan 2007–2010 of the Netherlands Foundation for the Advancement of Tropical Research, although similar policies from other countries might also be assessed. The data show that poverty/hunger research has grown steadily over time in many disciplines, most significantly in Environmental Sciences and Technology. Much of this research is hidden; hence the construction of an internationally recognised open‐access database is recommended so that scientists can easily identify critical gaps related to scientific capacity‐building.