A comparison of nonparametric priors in hierarchical mixture modelling for AFT regression

We will pursue a Bayesian nonparametric approach in the hierarchical mixture modelling of lifetime data in two situations: density estimation, when the distribution is a mixture of parametric densities with a nonparametric mixing measure, and accelerated failure time (AFT) regression modelling, when the same type of mixture is used for the distribution of the error term. The Dirichlet process is a popular choice for the mixing measure, yielding a Dirichlet process mixture model for the error; as an alternative, we also allow the mixing measure to be equal to a normalized inverse-Gaussian prior, built from normalized inverse-Gaussian finite dimensional distributions, as recently proposed in the literature. Markov chain Monte Carlo techniques will be used to estimate the predictive distribution of the survival time, along with the posterior distribution of the regression parameters. A comparison between the two models will be carried out on the grounds of their predictive power and their ability to identify the number of components in a given mixture density.     

Agency costs of free cash flow,internal capital markets and unrelated diversification

This paper investigates whether free cash flow arguments or the internal capital market perspective better explains diversification decisions. Based on a unique panel of hand-collected data from listed and unlisted Italian firms for the 1980–2010 time period, the results of this study generally reveal the predominant role of the internal capital market arguments. The benefits of unrelated diversification, which include the avoidance of costly external financing, outweigh its costs, which involve opportunistic problems. Although the literature suggests two distinct forces concurrently affect diversification decisions, in the Italian context, financial benefits appear to be the prevailing motivation for unrelated diversification decisions. Furthermore, the internal capital market argument has a strong effect on decisions to engage in unrelated diversification, particularly with respect to firms that are sensitive to financial constraints.     

Measuring Health Inequality in US: A Composite Index Approach

Social Indicators Research - In this paper, we use the standardized mortality rates for 21 mutual exclusive causes of death to propose a composite index of US county-level health performances in...     

Activation and Local Welfare in Italy: Trends and Issues

This article deals with the development of local welfare in Italy and is grounded on a research project focusing on activation as a main feature of change in Italian social policies. Along with decentralization processes, many Italian regions have been acting as policy laboratories, developing and testing very different approaches according to their political attitude. On the one hand this results in a fragmented policy landscape which is difficult to recompose, and, moreover, in growing inequalities in the Italian welfare system. On the other hand, it opens opportunities for experimentation on institutional and organizational structures on a regional scale, creating a variety of practices for research and policy analysis. In the article we first describe the main trends in national social policies, with a specific focus on the dynamics of change referring to activation. We will then focus on a pilot programme which is aiming at the promotion and implementation of innovative practices in health and social care services in Friuli‐Venezia Giulia, a region in which there is a significant orientation towards enhancing social citizenship and enforcing the central position of the public actor. We investigate how the dynamics of territorialization and personalization, implied by the programme, trigger specific logics and practices of activation. Finally, referring to this case study, we propose an analytical overview of some relevant issues in the development of ‘local active welfare’ in Italy.     

The Spreading of Cohabitation as a Diffusion Process: Evidence from Italy

Drawing on seminal work by Nazio and Blossfeld (Eur J Popul 19(1):47–82, 2003) and Di Giulio and Rosina (Demogr Res 16(14):441–468, 2007), this paper tests whether the recent spread of cohabitation in Italy has followed the typical pattern of diffusion of innovation processes. In doing so, we contribute to the debate on the determinants of the emergence of “new” family behaviour. Following previous literature, innovative behaviour should spread initially through direct social modelling, i.e. interpersonal communication among highly selected individuals (peer effects). At later stages, the diffusion should spread through knowledge awareness of the innovation, i.e. communication with previous generations (pre-cohort effects), so that also less selected individuals are prone to adopt the new behaviour. In the specific Italian context—a Catholic, “familistic” setting, with high normative pressure and importance of parental approval—we surmise the influence of previous generations to be dominant. We use data from the “Family and Social Subjects” survey carried out by Istat (2009) and apply Event History Analysis in the form of competing-risks exponential models to study Italian women’s transition to cohabitation as first partnership. Results suggest that the most important driver of the spreading of cohabitation in Italy is represented by the degree of its diffusion among older cohorts. However, we find a positive and significant interaction between women’s education and peer effects at the onset of the phenomenon, in line with the Second Demographic Transition (SDT) hypothesis. Cohabitation is also more likely if parents experienced separation/divorce and, more generally, if the environment of the family of origin can be described as “SDT-friendly”.     

A blocked Gibbs sampler for NGG-mixture models via a priori truncation

We define a new class of random probability measures, approximating the well-known normalized generalized gamma (NGG) process. Our new process is defined from the representation of NGG processes as discrete measures where the weights are obtained by normalization of the jumps of Poisson processes and the support consists of independent identically distributed location points, however considering only jumps larger than a threshold \(\varepsilon \). Therefore, the number of jumps of the new process, called \(\varepsilon \)-NGG process, is a.s. finite. A prior distribution for \(\varepsilon \) can be elicited. We assume such a process as the mixing measure in a mixture model for density and cluster estimation, and build an efficient Gibbs sampler scheme to simulate from the posterior. Finally, we discuss applications and performance of the model to two popular datasets, as well as comparison with competitor algorithms, the slice sampler and a posteriori truncation.     

Bayesian isotonic logistic regression via constrained splines: an application to estimating the serve advantage in professional tennis

Statistical Methods & Applications - In professional tennis, it is often acknowledged that the server has an initial advantage. Indeed, the majority of points are won by the server, making the...     

Levels of uric acid in erectile dysfunction of different aetiology

Erectile dysfunction is a common disease characterized by endothelial dysfunction. The aetiology of ED is often multifactorial but evidence is being accumulated in favor of the proper function of the vascular endothelium that is essential to achieving and maintaining penile erection. Uric acid itself causes endothelial dysfunction via decreased nitric oxide production. This study aims to evaluate the serum uric acid (SUA) levels in 180 ED patients, diagnosed with the International Index of Erectile Function-5 (IIEF-5) and 30 non-ED control. Serum uric acid was analyzed with a commercially available kit using ModularEVO (Roche, Monza, Italy). Within-assay and between-assay variations were 3.0% and 6.0%, respectively. Out of the ED patients, 85 were classified as arteriogenic (A-ED) and 95 as non-arteriogenic (NA-ED) with penile-echo-color-Doppler. Uric acid levels (median and range in mg/dL) in A-ED patients (5.8, 4.3–7.5) were significantly higher (p?p?相似文献