Global sensitivity analysis of stochastic computer models with joint metamodels

The global sensitivity analysis method used to quantify the influence of uncertain input variables on the variability in numerical model responses has already been applied to deterministic computer codes; deterministic means here that the same set of input variables always gives the same output value. This paper proposes a global sensitivity analysis methodology for stochastic computer codes, for which the result of each code run is itself random. The framework of the joint modeling of the mean and dispersion of heteroscedastic data is used. To deal with the complexity of computer experiment outputs, nonparametric joint models are discussed and a new Gaussian process-based joint model is proposed. The relevance of these models is analyzed based upon two case studies. Results show that the joint modeling approach yields accurate sensitivity index estimators even when heteroscedasticity is strong.     

Services and Intimate Partner Violence in the United States: A County‐Level Analysis

Despite the prevalence of intimate partner violence and its social costs, we show that many counties lack services to help victims and that community resources play a significant role in determining the likelihood of service provision. Because resources are often generated at the local level and state and federal funding usually require a grant proposal, services for victims of intimate partner violence are more likely to be available in well‐resourced areas with a major college or university in the county. Analysis of the changes in the provision of services since the Violence Against Women Act was introduced suggests that funding needs to be specifically targeted to underserved areas.     

Differentials in the femininity ratio among centenarians: variations between northern and southern Italy from 1870

Significant differentials have been observed between Italian regions in the distribution of centenarians by sex, from two women per man in the south to over eight in certain regions in the north. In order to explain these differentials we studied the evolution of the femininity ratio (FR), using a longitudinal approach to follow the ageing process in two cohorts, and making use of nearly all the statistical data available since the time of the Unification of Italy in 1870. Significant differentials in the FR observed at the age of 100 are mainly due to mortality differentials among men over the age of 60. The high mortality of men in the north and their low mortality in the south are the main explanations of why the FRs are higher in the north and lower in the south. Mortality differentials among women have only a marginal impact.     

Family Well-Being During the COVID-19 Pandemic: The Risks of Financial Insecurity and Coping

During the COVID-19 pandemic, families have experienced unprecedented financial and social disruptions. We studied the impact of preexisting psychosocial factors and pandemic-related financial and social disruptions in relation to family well-being among N = 4091 adolescents and parents during early summer 2020, participating in the Adolescent Brain Cognitive Development^SM Study. Poorer family well-being was linked to prepandemic psychosocial and financial adversity and was associated with pandemic-related material hardship and social disruptions to routines. Parental alcohol use increased risk for worsening of family relationships, while a greater endorsement of coping strategies was mainly associated with overall better family well-being. Financial and mental health support may be critical for family well-being during and after a widespread crisis, such as the COVID-19 pandemic.     

Developing a Human‐centred and Science‐based Approach to Design: The Knowledge Management Platform Project

The gap between theory and practice is a persistent problem in management and organization research. In this respect, several scholars have suggested that ‘design’ is an ideal‐typical form of mode 2 knowledge production. Design research develops knowledge in the service of action and problem solving in organizational settings. In this paper, we connect two perspectives on design that can be considered to be largely complementary but have hardly been combined and integrated in practice: science‐based design drawing on design propositions grounded in research and human‐centred design emphasizing an active and systematic participation by users and other stakeholders. An integrated approach that builds on both perspectives is developed and subsequently applied to designing and developing a portal for mapping competencies in an information technology cluster. This project involves creating problem awareness and articulating design propositions as well as developing scenarios of use, experimenting with prototypes, and organizational transformation. As such, this methodology addresses the dual challenge of rigour and relevance by producing both scientific and practical knowledge.