Bayesian non-parametric inference for species variety with a two-parameter Poisson–Dirichlet process prior

Summary.  A Bayesian non-parametric methodology has been recently proposed to deal with the issue of prediction within species sampling problems. Such problems concern the evaluation, conditional on a sample of size n , of the species variety featured by an additional sample of size m . Genomic applications pose the additional challenge of having to deal with large values of both n and m . In such a case the computation of the Bayesian non-parametric estimators is cumbersome and prevents their implementation. We focus on the two-parameter Poisson–Dirichlet model and provide completely explicit expressions for the corresponding estimators, which can be easily evaluated for any sizes of n and m . We also study the asymptotic behaviour of the number of new species conditionally on the observed sample: such an asymptotic result, combined with a suitable simulation scheme, allows us to derive asymptotic highest posterior density intervals for the estimates of interest. Finally, we illustrate the implementation of the proposed methodology by the analysis of five expressed sequence tags data sets.     

The Size and Power of Bootstrap and Bartlett-Corrected Tests of Hypotheses on the Cointegrating Vectors

In this paper we compare Bartlett-corrected, bootstrap, and fast double bootstrap tests on maximum likelihood estimates of cointegration parameters. The key result is that both the bootstrap and the Bartlett-corrected tests must be based on the unrestricted estimates of the cointegrating vectors: procedures based on the restricted estimates have almost no power. The small sample size bias of the asymptotic test appears so severe as to advise strongly against its use with the sample sizes commonly available; the fast double bootstrap test minimizes size bias, while the Bartlett-corrected test is somehow more powerful.     

Croissance économique,flexibilité du travail et qualité de l'emploi en Colombie de 2002 à 2011

Entre 2002 et 2011, le marché du travail colombien a connu une nette amélioration des possibilités d'emploi, assortie d'une montée de l'emploi atypique. Les auteurs étudient l'incidence de ces phénomènes sur la qualité de l'emploi au moyen d'un indice synthétique dérivé d'une analyse des correspondances multiples. Ils observent une amélioration, légère mais générale, de cette qualité, associée à l'augmentation des revenus, à l'extension de la protection sociale et au recul du sous‐emploi. Les principales bénéficiaires sont les travailleuses indépendantes. Toutefois, un important déficit qualitatif perdure, qui appelle à consolider les institutions du marché du travail et à stimuler la productivité et l'investissement.     

Did the Decline in Social Connections Depress Americans’ Happiness?

During the last 30 years US citizens experienced, on average, a decline in reported happiness, social connections, and confidence in institutions. We show that a remarkable portion of the decrease in happiness is predicted by the decline in social connections and confidence in institutions. We carry out our investigation in three steps. First, we run a happiness regression that includes various indicators of social connections and confidence in institutions, alongside with own income, reference income, and the usual socio-demographic controls. We find that indicators of social connections and confidence in institutions are positively and significantly correlated with happiness. Second, we investigate the evolution of social connections and confidence in institutions over time, finding that they generally show a declining trend. Third, we calculate the variation in happiness over time as predicted by each of its statistically significant correlates, finding that the decrease in happiness is mainly predicted by the decline in social connections and by the growth in reference income. More precisely, the sum of the negative changes in happiness predicted by the reduction in social connections and the increase in reference income more than offsets the positive change predicted by the growth of household income. Also, the reduction in happiness predicted by the decline in confidence in institutions is non-negligible, although substantially smaller than the one predicted by either social connections or reference income.     

Measuring Change Over Time in Socio-economic Deprivation and Health in an Urban Context: The Case Study of Genoa

Poverty and disability are interrelated, but data that can disentangle to what extent one causes the other and vice versa is not available. However, data from Vietnam allows us to examine this interrelationship in a way not done previously. Using small area estimation techniques, we uncover three findings not yet found in the literature. First, disability prevalence rates vary significantly within a country even at the district level. Second, the poverty gap between people with and without disabilities also varies at the district level. And most importantly, the size of that gap lessens based on district characteristics that can be affected by policy. Districts with better health care and infrastructure, such as road and health services, show less of a link between disability and poverty, supporting the hypothesis that improvements in infrastructure and rehabilitation service can lessen the impact of disability on families with disabled members.     

A new look at schooling inequalities in Italy and their trends over time

This article examines whether the influence of family background on educational attainment has changed in Italy in the course of the 20th century. For several European countries, recent studies have come to question the widely agreed thesis of persistent schooling inequalities. This work discusses extensively factors that may produce variations of class differentials in academic achievement and in participation rates in the Italian case. The empirical analyses are based on a new dataset and on new modelling techniques that ensure high statistical power to detect trends over time. Yet, the substantive conclusions point to a prevailing stability of class differentials, with a limited equalisation restricted to the agricultural classes in the oldest cohorts.     

“Sleep is on the back burner”: Working students and sleep

The current study examines on a potential high-risk sleep loss population: working students at a metropolitan university in a mid-sized Midwestern city in the United States. Open-ended interviews with nineteen working university students provide insight into their beliefs and behaviors regarding how they think about and “do” work, attend university and sleep. Sleep diaries provide information on perceived sleep duration, latency and quality. While students value sleep and recognize the connection between sleep loss and ill health, they accept tiredness as “normal” for their situation. For many students sleep is the one demand that can be “put off”, in the struggle to balance work, school and family demands, “until the bill comes due” when they fall ill. Exchanging sleep loss for educational progress is explored through “health capital” as part of a human capital conceptual framework.     

The key role of positive parenting and children’s temperament in post‐institutionalized children’s socio‐emotional adjustment after adoption placement. A RCT study

Parenting interventions represent a means for experimentally inquiring socio‐emotional change of post‐institutionalized children after adoption. We used this approach in a three time point RCT study involving 83 post‐institutionalized children (M_age = 33.5 months, SD = 17.1) and their adoptive mothers (M_age = 42.6, SD = 3.9), attending either the Video‐Feedback Intervention to promote Positive Parenting in adoption and foster care or a dummy intervention. Controlling for gender and age at adoption, children showed a significant change in their socio‐emotional adjustment in the specific variables inquired—that is, emotional availability‐EA, and behavioral problems—after intervention attendance. Mediation and moderated mediation models showed that maternal EA was a main factor affecting children’s EA and externalizing behavioral problems, with a key moderating role played by children’s temperament; children with high scores on temperamental negative affect benefitted most from their mothers’ increase in EA.