Combining Univariate Tests for Multivariate Location Problem

In this article, three methods of combining dependent univariate tests are studied. The Bahadur approximate efficiencies are derived under the asymptotic normal assumption. These procedures are applied to the multivariate location problem and compared with two Hotelling-type tests. A Monte Carlo study indicates that in certain cases the powers of the combination methods are much better than Hotelling's T ² and other multivariate nonparametric tests.     

Labour and international accounting standards: A question of social justice

As the international guardian of social justice, the ILO is witnessing a global revolution in accounting, which has culminated in international accounting standards (IAS-IFRS). Previously, accounting measured the economy in relation to the capacities and responsibilities of workers and their employers. Today, the exact opposite is the case: the IAS-IFRS no longer measure work and enterprises, referring instead to the abstract concept of a cybernetic entity capable of constant restructuring, at the cost of unprecedented inequality. The author points to the incoherence of this system and to the need to restore the full carrying value of labour.     

Travail et normes comptables internationales: une question de justice sociale

En tant que garante internationale de la justice sociale, l'OIT se trouve confrontée à une révolution comptable mondiale, parachevée par les normes comptables internationales (IAS-IFRS). La comptabilité mesurait autrefois l'économie en rapport avec les capacités et les responsabilités des travailleurs et de ceux qui en disposent. C'est aujourd'hui l'exact opposé: les normes IAS-IFRS ont perdu le sens de la mesure du travail et de l'entreprise en se référant au concept abstrait d'une entité cybernétique capable d'incessantes réorganisations, au prix d'inégalités sans limites. L'auteur en dénonce les incohérences et démontre la nécessité de redonner au travail toute sa valeur comptable.     

T. Brandsen,S. Cattacin,A. Evers,A. Zimmer (Eds.): Social Innovations in the Urban Context

VOLUNTAS: International Journal of Voluntary and Nonprofit Organizations -     

Prosocial Behavior: Long‐term Trajectories and Psychosocial Outcomes

This study investigated developmental trajectories for prosocial behavior for a sample followed from the age of 10–18 and examined possible adjustment outcomes associated with membership in different trajectory groups. Participants were 136 boys and 148 girls, their teachers, and their parents (19.4 percent African‐American, 2.4 percent Asian, 51.9 percent Caucasian, 19.5 percent Hispanic, and 5.8 percent other). Teachers rated children's prosocial behavior yearly in grades 4–12. At the end of the 12th grade year, teachers, parents, and participants reported externalizing behaviors and participants reported internalizing symptoms, narcissism, and features of borderline personality disorder. Results suggested that prosocial behavior remained stable from middle childhood through late adolescence. Group‐based mixture modeling revealed three prosocial trajectory groups: low (18.7 percent), medium (52.8 percent), and high (29.6 percent). Membership in the high prosocial trajectory group predicted lower levels of externalizing behavior as compared with the low prosocial trajectory group, and for girls, lower levels of internalizing symptoms. Membership in the medium prosocial trajectory group also predicted being lower on externalizing behaviors. Membership in the high prosocial trajectory group predicted lower levels of borderline personality features for girls only.     

Propensity score prediction for electronic healthcare databases using super learner and high-dimensional propensity score methods

ABSTRACT

The optimal learner for prediction modeling varies depending on the underlying data-generating distribution. Super Learner (SL) is a generic ensemble learning algorithm that uses cross-validation to select among a ‘library’ of candidate prediction models. While SL has been widely studied in a number of settings, it has not been thoroughly evaluated in large electronic healthcare databases that are common in pharmacoepidemiology and comparative effectiveness research. In this study, we applied and evaluated the performance of SL in its ability to predict the propensity score (PS), the conditional probability of treatment assignment given baseline covariates, using three electronic healthcare databases. We considered a library of algorithms that consisted of both nonparametric and parametric models. We also proposed a novel strategy for prediction modeling that combines SL with the high-dimensional propensity score (hdPS) variable selection algorithm. Predictive performance was assessed using three metrics: the negative log-likelihood, area under the curve (AUC), and time complexity. Results showed that the best individual algorithm, in terms of predictive performance, varied across datasets. The SL was able to adapt to the given dataset and optimize predictive performance relative to any individual learner. Combining the SL with the hdPS was the most consistent prediction method and may be promising for PS estimation and prediction modeling in electronic healthcare databases.     

Education and religion: Individual, congregational, and cross-level interaction effects on biblical literalism

Using ideas from cultural and organizational theory, I examine the interplay of individual and congregation-level educational attainment on biblical literalism. Data on 387 congregations and 100,009 worshippers (US Congregational Life Survey, 2001) are used to test hypotheses. Results indicate that the effects of congregational education and individual educational attainment are among the largest effects in models. This study is the first to show that regardless of an individual’s own education, affirmations of biblical literalism are less likely when persons with higher education dominate a congregation. This finding brings into relief the important role of social context in persons’ belief in biblical literalism. Additionally, congregational education amplifies the influence of individual education on biblical literalism such that the gap in belief between college/non-college education individuals widens in high education congregations. This finding suggests that high education persons more deeply absorb the influence of a more educated congregational context.     

Technology,Geography, and Trade

We develop a Ricardian trade model that incorporates realistic geographic features into general equilibrium. It delivers simple structural equations for bilateral trade with parameters relating to absolute advantage, to comparative advantage (promoting trade), and to geographic barriers (resisting it). We estimate the parameters with data on bilateral trade in manufactures, prices, and geography from 19 OECD countries in 1990. We use the model to explore various issues such as the gains from trade, the role of trade in spreading the benefits of new technology, and the effects of tariff reduction.     

Getting your supervisors and managers on the right team

They do a great job. So we promote them. Now they supervise people who don't do the job as well as they did. We give them a big raise. But because they're exempt they make less than their leads. They have the toughest job in the company—managing people. So we grant them an entire day of training to prepare. We ask them to mentor, coach, and have close relationships with their direct reports—all 132 of them. Then when the stock dips, we blame “middle management” and lay a bunch of them off.