Distributions generated by perturbation of symmetry with emphasis on a multivariate skew t-distribution

Summary . A fairly general procedure is studied to perturb a multivariate density satisfying a weak form of multivariate symmetry, and to generate a whole set of non-symmetric densities. The approach is sufficiently general to encompass some recent proposals in the literature, variously related to the skew normal distribution. The special case of skew elliptical densities is examined in detail, establishing connections with existing similar work. The final part of the paper specializes further to a form of multivariate skew t -density. Likelihood inference for this distribution is examined, and it is illustrated with numerical examples.     

Exploring the relation between maternal mind‐mindedness and children’s symbolic play: A longitudinal study from 6 to 18 months

Relations between mothers’ mind‐mindedness (appropriate attunement to their infants’ internal states) at 6 and 12 months and infants’ early symbolic play during infant–mother pretense at 12 and 18 months were investigated in a sample of 43 mothers and infants. Mothers’ appropriate mind‐related comments were associated with average level, length, complexity, and maturity level of symbolic play. Specific sub‐categories of appropriate mind‐related comments were identified as independent predictors of children's symbolic play. Appropriate comments about desires and cognitions at 6 months were associated with average level and length of episodes, as well as with maturity level of symbolic play at 12 months. Longitudinal stability in the appropriateness and content of mothers’ mind‐related comments was also investigated. The results are discussed in terms of the proposal that attunement to specific types of internal state should vary as a function of infant age in order to index mind‐mindedness.     

A gradient-based deletion diagnostic measure for generalized linear mixed models

A gradient-statistic-based diagnostic measure is developed in the context of the generalized linear mixed models. Its performance is assessed by some real examples and simulation studies, in terms of ability in detecting influential data structures and of concordance with the most used influence measures.     

Risk Assessment of Human Listeriosis from Semisoft Cheeses Made from Raw Sheep's Milk in Lazio and Tuscany (Italy)

Semisoft cheese made from raw sheep's milk is traditionally and economically important in southern Europe. However, raw milk cheese is also a known vehicle of human listeriosis and contamination of sheep cheese with Listeria monocytogenes has been reported. In the present study, we have developed and applied a quantitative risk assessment model, based on available evidence and challenge testing, to estimate risk of invasive listeriosis due to consumption of an artisanal sheep cheese made with raw milk collected from a single flock in central Italy. In the model, contamination of milk may originate from the farm environment or from mastitic animals, with potential growth of the pathogen in bulk milk and during cheese ripening. Based on the 48‐day challenge test of a local semisoft raw sheep's milk cheese we found limited growth only during the initial phase of ripening (24 hours) and no growth or limited decline during the following ripening period. In our simulation, in the baseline scenario, 2.2% of cheese servings are estimated to have at least 1 colony forming unit (CFU) per gram. Of these, 15.1% would be above the current E.U. limit of 100 CFU/g (5.2% would exceed 1,000 CFU/g). Risk of invasive listeriosis per random serving is estimated in the 10^?12 range (mean) for healthy adults, and in the 10^?10 range (mean) for vulnerable populations. When small flocks (10–36 animals) are combined with the presence of a sheep with undetected subclinical mastitis, risk of listeriosis increases and such flocks may represent a public health risk.     

Mortality Peaks in Italy in the Late 19th and Early 20th Centuries: Trends by Age and Sex

Infant and youth mortality fell steeply between the Unification of Italy and the 1930s, particularly due to the decline in infectious and parasitic diseases. A number of mortality crises, however, at times halted this decline: the 1908 Calabria-Sicily earthquake, the 1915 Marsica earthquake, World War I and 1918 Spanish INFLUENZA outbreak.This paper focuses as the repercussions of these events on the general survival status of young people from birth to puberty, as well as the main pathologies responsible for the rise in mortality.An analysis of differences in mortality according to sex during the various crises was also performed to ascertain whether the more difficult survival conditions during these periods affected males and females equally.     

Studying the relationship between anxiety and school achievement: evidence from PISA data

Statistical Methods & Applications - Using the Programme for International Student Assessment (PISA) 2015 data for Italy, this paper offers a complete overview of the relationship between test...     

New Chinese Migrants in Italy

Italy joined the group of European nations with a positive migratory balance in 1980, but now the presence of an immigrant workforce is definitely embedded in the Italian development model. The shift from a net emigration to net immigration country occurred when the internal migration from southern Italy, which had provided the factories in northern Italy with the necessary manpower for their economic development, was coming to an end, and productive decentralization was beginning with the re‐emergence of small businesses. Twenty years later, small dynamic businesses that are mainly clustered in industrial districts specializing in local production are a distinctive feature of the Italian economy to the extent that among industrialized countries Italy counts the largest number of small businesses and the lowest number of employees per business (Accornero, 2000). Starting from the 1980s, opportunities for a low‐skilled labour force opened for new migrants mainly in these productive activities. In addition, throughout the 1980s and the 1990s niche opportunities for self‐employment in workshops producing for Italian suppliers were also appearing or expanding. Among other migrant groups arriving in Italy were those of Chinese origin. The crucial time for the recent migration flow from China to Italy — either directly or via other European countries, such as France and Holland — can be dated from the early 1980s. Since then, a succession of unskilled workers originating almost exclusively from the south‐eastern Chinese province of Zhejiang arrived in the country, after the family‐based chains of emigration that had almost come to a halt during the years of the Cultural Revolution had again been revitalized. The number of immigrants of Chinese origin has grown rapidly over the last 20 years, as has the number of businesses owned by the Chinese. By today, the Chinese migrant community shows the strongest entrepreneurial aptitude, and, according to recent national data, account for the largest number of small business owners among non‐European Union (EU) immigrants in Italy. Unlike the situation in most of the western European countries, such as Great Britain and the Netherlands, where the Chinese are active mainly in the catering service, in Italy their main areas of activity are the production of ready‐to‐wear garments, leather garments and bags, and woollen sweaters. Until recently, these seemed to be the only productive sectors open to Chinese immigrants. However, new trends are emerging in the employment patterns of the Chinese in Italy. The two most striking new features are the expansion from performing only simple manufacturing tasks for Italian suppliers to actually managing the entire productive process in the garment sector, and the growing employment in Italian firms, especially in the dynamic industrial districts where migrants of other origins were already working in large numbers.     

Panel regression models for measuring multidimensional poverty dynamics

This work concerns the study of poverty dynamics and the analysis of the influencing socio-demographic factors. A fuzzy and multidimensional approach has been chosen in order to define two different poverty measures. A panel regression model has been estimated and particular attention has been paid to the treatment of the unobservable heterogeneity among longitudinal units. The specified model combines autoregression with variance components. The empirical analysis has been conducted using the data set of the British Household Panel Survey (BHPS) from 1991 to 1997. This work was co-financed by Murst funds for the projects “Occupazione e disoccupazione in Italia: misura e analisi dei comportamenti”. The paper is the result of the common work of all the authors; in particular G. Betti has written Sects. 2,5.1 and 5.3.1; A. D’Agostino has written sections 4, 5.2 and 5.4; L. Neri has written Sects. 1, 3, 5.3.2 and 6.