Search

Summary: The COVID‐19 pandemic caused an unprecedented excess mortality. Since 2020, many studies have focussed on the characteristics of COVID‐19 patients who did not survive. From the statistical point of view, what seems to dominate is the large heterogeneity of the populations affected by COVID‐19 and the extreme difficulty in identifying subpopulations who died affected by a plurality of contemporary characteristics. In this paper, we propose an extremely flexible approach based on a cluster‐weighted model, which allows us to identify latent groups of patients sharing similar characteristics at the moment of hospitalisation as well as a similar mortality. We focus on one of the hardest hit areas in Italy and study the heterogeneity in the population of patients affected by COVID‐19 using administrative data on hospitalisations in the first wave of the pandemic. Results highlighted that a model‐based clustering approach is essential to understand the complexity of the COVID‐19 patients treated by hospitals and who die during hospitalisation. [ABSTRACT FROM AUTHOR]

This article discusses Mother Teresa, canonized as Saint Teresa of Calcutta on September 4, 2016, by Pope Francis. The author comments on the criticism of Mother Teresa, particularly the unsanitary conditions of the medical clinics she established cited in Christopher Hitchens' "The Missionary Position." He dismisses these criticisms and highlights her acts of charity.

We propose a new approach with which to measure school efficiency by including student Non-Cognitive Skills in the analysis. In classical analysis, efficiency is measured separately from effectiveness. In our framework, we jointly consider efficiency and effectiveness, including both Cognitive Skills and Non-Cognitive Skills. We call our approach "Non-Cognitive Skills Efficiency" and we propose two analyses. The first is called "Static Non-Cognitive Skills Efficiency" and measures the efficiency of transforming Non-Cognitive Skills into Cognitive Skills, by means of a Stochastic Frontier Approach. We verify that some Non-Cognitive Skills have effect on Cognitive Skills and contribute to increase school efficiency. The second is defined "Dynamic Non-Cognitive Skills Efficiency" and measures the efficiency of school educational programmes aimed at improving Non-Cognitive Skills. The statistical method is a Difference-in-Differences model based on a Stochastic Frontier Approach. We find that these educational programmes (treatment) have a positive effect on Non-Cognitive Skills. The survey concerns 8th grade students attending 25 schools in the Provincia Autonoma di Trento, in Italy. The dataset comprises both survey data and the administrative data of local authorities, thus providing a complete set of information at student level on CS and NCS skills, social capital variables, in particular the socioeconomic background of families, and teaching parameters. We measure school efficiency at class level, because this level is less affected by unobserved environmental factors. The results provide new perspectives on education in schools. • We jointly consider efficiency and effectiveness, including Cognitive Skills (CS) and Non-Cognitive Skills (NCS). • The first analysis "Static Non-Cognitive Skills Efficiency" measures the efficiency of transforming NCS into CS. • The second analysis "Dynamic Non-Cognitive Skills Efficiency" measures the efficiency of school programmes in improving NCS. • We verify that in many cases NCS have effect on CS, contributing to increase school efficiency. • Results open new perspectives on teaching policies - programs and methods - to improve students' NCS. [ABSTRACT FROM AUTHOR]

Over years, there has been an increase in the prescription of psychotropic drugs (PDs), particularly antidepressants (ADs). The aim of the study was to evaluate the consumption of PDs in adult employees in a productive area of Italy and the possible changes induced by the “economic crisis”. The study is a retrospective survey in all adult employees in Lombardy, Northern Italy, aged >18 years in the period 2007–2011, classified by gender, age class, nationality, education and province. During the 5-year period, there were 3,554,860 employed adults in Lombardy, of whom 277,865 (7.8%) used PDs. The use of PDs (particularly ADs) was associated with being an Italian woman aged >55 years with a basic education, a blue collar job, and an unstable working position. In 39% of cases, the use of PDs was limited to one trimester. The increase in the number of prescriptions of PDs after the economic crisis was the same as before it. The increase in PD use can be attributed more to ADs and anti-epileptic drugs with anxiolytic properties. Although continuously increasing, the use of AD fluctuated and was greater during the fall and winter. The increase involved all the provinces in Lombardy in a similar manner. [ABSTRACT FROM AUTHOR]

A recent method to specify and fit structural equation modeling in the Redundancy Analysis framework based on so-called Extended Redundancy Analysis (ERA) has been proposed in the literature. In this approach, the relationships between the observed exogenous variables and the observed endogenous variables are moderated by the presence of unobservable composites, estimated as linear combinations of exogenous variables. However, in the presence of direct effects linking exogenous and endogenous variables, or concomitant indicators, the composite scores are estimated by ignoring the presence of the specified direct effects. To fit structural equation models, we propose a new specification and estimation method, called Generalized Redundancy Analysis (GRA), allowing us to specify and fit a variety of relationships among composites, endogenous variables, and external covariates. The proposed methodology extends the ERA method, using a more suitable specification and estimation algorithm, by allowing for covariates that affect endogenous indicators indirectly through the composites and/or directly. To illustrate the advantages of GRA over ERA we propose a simulation study of small samples. Moreover, we propose an application aimed at estimating the impact of formal human capital on the initial earnings of graduates of an Italian university, utilizing a structural model consistent with well-established economic theory. [ABSTRACT FROM AUTHOR]

Dagum and Slottje (2000) estimated household human capital (HC) as a latent variable (LV) and proposed its monetary estimation by means of an actuarial approach. This paper introduces an improved method for the estimation of household HC as an LV by means of formative and reflective indicators in agreement with the accepted economic definition of HC. The monetary value of HC is used in a recursive causal model to obtain short- and long-term multipliers that measure the direct and total effects of the variables that determine household HC. The new method is applied to estimate US household HC for year 2004. [ABSTRACT FROM AUTHOR]

Abstract: In Dagum and Slottje''s breakthrough contribution of on human capital (2000), the authors combine its microeconomic estimation as a standardized latent variable with the macroeconomic estimation of its average value in the population. The standardized latent variable is obtained applying the partial least squares method after transforming the qualitative indicators considered as investments in human capital and called formative indicators. This approach, however, does not take into account the effects of investing in human capital (reflective indicators), hence ignoring its economic definition. The main purpose of this paper is to introduce an improved statistical method of household human capital estimation as a standardized latent variable which is a function of both formative and reflective indicators. The latter is measured by household earned income, excluding income generated from wealth. A comparison of the new results with those obtained by Dagum and Slottje [Dagum, C., Slottje, D.J., 2000. A new method to estimate the level and distribution of the household human capital with applications. Journal of Structural Change and Economic Dynamics 11, 67–94] using the same data clearly show the advantages of the new approach. [Copyright &y& Elsevier]

In this paper we propose a methodology for measuring the ‘relative effectiveness’ of healthcare services (i.e. the effect of hospital care on patients) under general conditions, in which: 6) a healthcare outcome underlies qualitative and quantitative observable indicators; β) we are interested in studying the simultaneous dependency of multiple outcomes on covariates (where the outcomes can also be correlated to each other); γ) the relative effectiveness is adjusted for hospital-specific covariates; 8) we hypothesise a general distribution for random disturbances and the random parameters of relative effectiveness. For this topic, a generalisation of the SURE (seemingly unrelated regression equations) multilevel model is proposed. The solutions are obtained by means of Bayesian inference methods. Since there is currently no software available to estimate this model, an SAS procedure based on Markov Chain Monte Carlo methods has been developed by the authors, in line with Goldstein & Spiegelhalter (1996, .L R. Stat. Soc. Set A, 159, 385–443), Spiegelhalter et al. (1996, Bayesian Using Gibbs Sampling Manual. Cambridge: MRC Bio-statistic Unit, Institute of Public Health) and Albert & Chib (1997, J. Am. Stat. Assoc., 92, 916–925). In addition, a new theoretical result regarding the joint posterior distribution for the parameters is provided. The model proposed has been implemented for an effectiveness study of a selection of Lombard hospitals. [ABSTRACT FROM AUTHOR]

The latent variables and errors of the Lisrel model are indeterminate even when the parameters of the model are perfectly identified. The reason for the indeterminacy is that the Lisrel model gives a solution in terms of estimation of latent variables by means of observed variables. The indeterminacy is relevant also in practice; the minimum correlation between equivalent latent variables, is often negative in empirical examples. The degree of indeterminacy of the latent variables depends on the data. The average minimum correlation is a linear combination of the eigenvalues of the correlation matrix of solutions and it is always included in weak bounds which depend on the same eigenvalues. [ABSTRACT FROM AUTHOR]

The article presents the author's views on various G20 countries that can help in improving the economic, social and demographic conflicts in Africa. Various topics discussed include education in Africa, misuse of natural resources found over there, arms exports and business activities in the country.

This article discusses the political impact of Brexit, the decision by Great Britain to leave the European Union. The author comments on the thoughts of Pope Francis on the topic and describes the relationship between Brexit, education, and the Marshall Plan. The importance of international relations and cooperation is also emphasized.

This paper analyses the future prospects of statistics as a profession and how data science will change it. Indeed, according to Hadley Wickham, Chief Scientist at Rstudio, "a data scientist is a useful statistician", establishing a strong connection between data science and applied statistics. In this direction, the aim is to look to the future by proposing a structural approach to future scenarios. Some possible definitions of data science are then discussed, considering the relationship with statistics as a scientific discipline. The focus then turns to an assessment of the skills required by the labor market for data scientists and the specific characteristics of this profession. Finally, the phases of a data science project are considered, outlining how these can be exploited by a statistician. [ABSTRACT FROM AUTHOR]

• SP-D is a marker of COVID-19 disease and its outcome. • SP-D has a prognostic value in terms of mortality in COVID-19 hospitalized patients. • Cut-off values of 150 ng/mL and 250 ng/mL SP-D in plasma are proposed to predict the disease incidence and mortality, respectively. • The early detection of SP-D levels should be determinant for an adequate preventive treatment of COVID-19. Surfactant protein-D (SP-D) is a lung-resident protein that has emerged as a potential biomarker for COVID-19. Previous investigations on acute respiratory distress syndrome patients demonstrated a significant increment of SP-D serum levels in pathological conditions. Since SP-D is not physiologically permeable to alveoli-capillary membrane and poorly expressed by other tissues, this enhancement is likely due to an impairment of the pulmonary barrier caused by prolonged inflammation. A retrospective study on a relatively large cohort of patients of Hospital Pio XI of Desio was conducted to assess differences of the hematic SP-D concentrations among COVID-19 patients and healthy donors and if SP-D levels resulted a risk factor for disease severity and mortality. The first analysis, using an ANOVA-model, showed a significant difference in the mean of log SP-D levels between COVID-19 patients and healthy donors. Significant variations were also found between dead vs survived patients. Results confirm that SP-D concentrations were significantly higher for both hospitalized COVID-19 and dead patients, with threshold values of 150 and 250 ng/mL, respectively. Further analysis conducted with Logistic Mixed models, highlighted that higher SP-D levels at admission and increasing differences among follow-up and admission values resulted the strongest significant risk factors of mortality (model predictive accuracy, AUC = 0.844). The results indicate that SP-D can be a predictive marker of COVID-19 disease and its outcome. Considering its prognostic value in terms of mortality, the early detection of SP-D levels and its follow-up in hospitalized patients should be considered to direct the therapeutic intervention. [ABSTRACT FROM AUTHOR]

We study inter‐regional migration flows due to hospital admissions and focus on the impact of migration beaten paths. We estimate a gravity model applied to Italian data for the period 2010–2016. We find that beaten paths have a positive effect on inter‐regional patient flows, with estimated elasticity equal to +0.32%. Therefore, family and social ties among people living in the region of origin and destination for hospital admissions may explain the concentration of health migration (HM) in some regions. Moreover, the beaten path effect is stronger for private hospitals. We also find that HM patients are more sensible to hospital quality than those admitted in local hospitals. [ABSTRACT FROM AUTHOR]

Cluster-weighted models (CWMs) are a flexible family of mixture models for fitting the joint distribution of a random vector composed of a response variable and a set of covariates. CWMs act as a convex combination of the products of the marginal distribution of the covariates and the conditional distribution of the response given the covariates. In this paper, we introduce a broad family of CWMs in which the component conditional distributions are assumed to belong to the exponential family and the covariates are allowed to be of mixed-type. Under the assumption of Gaussian covariates, sufficient conditions for model identifiability are provided. Moreover, maximum likelihood parameter estimates are derived using the EM algorithm. Parameter recovery, classification assessment, and performance of some information criteria are investigated through a broad simulation design. An application to real data is finally presented, with the proposed model outperforming other well-established mixture-based approaches. [ABSTRACT FROM AUTHOR]

Cluster-weighted models (CWMs) are a flexible family of mixture models for fitting the joint distribution of a random vector composed of a response variable and a set of covariates. CWMs act as a convex combination of the products of the marginal distribution of the covariates and the conditional distribution of the response given the covariates. In this paper, we introduce a broad family of CWMs in which the component conditional distributions are assumed to belong to the exponential family and the covariates are allowed to be of mixed-type. Under the assumption of Gaussian covariates, sufficient conditions for model identifiability are provided. Moreover, maximum likelihood parameter estimates are derived using the EM algorithm. Parameter recovery, classification assessment, and performance of some information criteria are investigated through a broad simulation design. An application to real data is finally presented, with the proposed model outperforming other well-established mixture-based approaches. [ABSTRACT FROM AUTHOR]

Cluster-weighted modeling (CWM) is a mixture approach to modeling the joint probability of data coming from a heterogeneous population. Under Gaussian assumptions, we investigate statistical properties of CWM from both theoretical and numerical point of view; in particular, we show that Gaussian CWM includes mixtures of distributions and mixtures of regressions as special cases. Further, we introduce CWM based on Student- t distributions, which provides a more robust fit for groups of observations with longer than normal tails or noise data. Theoretical results are illustrated using some empirical studies, considering both simulated and real data. Some generalizations of such models are also outlined. [ABSTRACT FROM AUTHOR]

The aim of the paper is to show evidence of possible inconsistencies of PLS-PM as a statistical tool to estimate structural equation models with formative-reflective schemes. We pursue this goal, discussing a real-data example where PLS-PM fails to identify existing causal links between the variables concerned. We also suggest a possible formal interpretation of this fact, focusing on the way PLS-PM represents the link between reflective latent variables and their indicators. [ABSTRACT FROM AUTHOR]

Background: The first Covid-19 epidemic outbreak has enormously impacted the delivery of clinical healthcare and hospital management practices in most of the hospitals around the world. In this context, it is important to assess whether the clinical management of non-Covid patients has not been compromised. Among non-Covid cases, patients with Acute Myocardial Infarction (AMI) and stroke need non-deferrable emergency care and are the natural candidates to be studied. Preliminary evidence suggests that the time from onset of symptoms to emergency department (ED) presentation has significantly increased in Covid-19 times as well as the 30-day mortality and in-hospital mortality. Methods: We check, in a causal inference framework, the causal effect of the hospital's stress generated by Covid-19 pandemic on in-hospital mortality rates (primary end-point of the study) of AMI and stroke over several time-windows of 15-days around the implementation date of the State of Emergency restrictions for COVID-19 (March, 9th 2020) using two quasi-experimental approaches, regression-discontinuity design (RDD) and difference-in-regression-discontinuity (DRD) designs. Data are drawn from Spedali Civili of Brescia, one of the most hit provinces in Italy by Covid-19 during March and May 2020. Findings: Despite the potential adverse effects on expected mortality due to a longer time to hospitalization and staff extra-burden generated by the first wave of Covid-19, the AMI and stroke mortality rates are overall not statistically different during the first wave of Covid-19 than before the first peak. The obtained results provided by RDD models are robust also when we account for seasonality and unobserved factors with DRD models. Interpretation: The non-statistically significant impact on mortality rates for AMI and stroke patients provides evidence of the hospital ability to manage -with the implementation of a dual track organization- the simultaneous delivery of high-quality cares to both Covid and non-Covid patients. [ABSTRACT FROM AUTHOR]

We study an airport cost function with a four-random components stochastic frontier model that split the inefficiency in two parts: (1) persistent (long-run) and (2) temporary (short-run). We analyze as determinant of both inefficiency types several exogenous factors such as the airport ownership and LCCs share. We apply the model to the Italian airport system during the period 2010–15. We find that (1) average total cost inefficiency is 14%, and that a it is mainly due to temporary inefficiency, (2) that work load units have the largest cost–output elasticity (+0.31%), (3) that price of airport services has the largest cost-input elasticity (+0.50%) while labor has a +0.41% cost elasticity and capital only a +0.09% cost elasticity. There is also evidence of economies of scale. Moreover we find that LCCs reduce both types of inefficiency and that private airports are more cost efficient than public ones. These findings have interesting managerial (e.g., strictly monitoring service costs, expand LCCs flights) and policy (e.g., provide incentive to reduce temporary inefficiency, push airport privatization) implications. [ABSTRACT FROM AUTHOR]

A correction to the article "Local Statistical Modeling via a Cluster-Weighted Approach with Elliptical Distributions" that was originally published in the 2012 issue is presented.

Psychiatric disorders and in particular depression have increased during the 'Great Recession'. The aim of this study was to investigate the consumption of psychotropic drugs in people who lost their permanent employment, using administrative data. The study considered all of the subjects domiciled in Lombardy, Northern Italy, who lost a permanent employment between 2008 and 2010, not assuming psychotropic drugs and who did not find a new job within the following 12 months. The control group included people who did not lose permanent job in the study period, matched to the cases for gender, age, nationality, skill level, education and economic sector, using propensity score matching. The subjects who lost their permanent employment were 17 % more likely to receive one or more drug prescriptions than the controls, but the difference was significant only for males. Females, subjects aged >50 years, low skill level workers and Italians were more likely to have received a prescription for psychotropic drugs than respectively males, subjects aged 20-29 years or aged 30-39 years, low skill level workers and non-Italians. The average number of drugs prescribed for those who lost their job and those who continued working was respectively 2.9 and 3.1. In conclusion, losing a permanent job increases significantly psychotropic drugs consumption in males but not in females. [ABSTRACT FROM AUTHOR]