1,720,974 research outputs found
Predicting bankruptcy of local government: A machine learning approach
No full textIn this paper we analyze the predictability of the bankruptcy of 7795 Italian municipalities in the period 2009–2016. The prediction task is extremely hard due to the small number of bankruptcy cases, on which learning is possible. Besides historical financial data for each municipality, we use alternative institutional data along with the socio-demographic and economic context. The predictability is analyzed through the performance of the statistical and machine learning models with a receiver operating characteristic curve and the precision-recall curve. Our results suggest that it is possible to make out-of-sample predictions with a high true positive rate and low false-positive rate. The model shows that some non-financial features (e.g. geographical area) are more important than many financial features to predict the default of municipalities. Among financial indicators, the important features are mainly connected to the Deficit and the Debt of Municipalities. Among the socio-demographic characteristics of administrators, the gender and the age of members in council are among the top 10 features in terms of importance for predicting municipal defaults
Measuring health inequality in US: a composite index approach
No full textIn 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 1980–2014 interval. We aggregate mortality rates by the stochastic multi-criteria acceptability analysis (SMAA), in order to avoid any a priori judgement on the importance given to a specific cause of death. The total observed inequality among counties is then decomposed to estimate the variability between and within states by means of the Theil index on SMAA outcomes. On average, there has been a decrease in the Composite Index of mortality from 1980 to 2014, but while the majority of counties had an increase in health conditions, some counties have shown a decrease in health performances in the same interval. This may be the reason of a persistent increase of total inequality among counties, with inequality within states constantly higher than inequality between states, both responsible of the growing inequality levels of health performances in the period analysed
Sulle relazioni tra dimensione, ambiente e performance finanziaria dei comuni italiani
No full textNel presente lavoro la dimensione dei comuni italiani non è posta in relazione all’efficienza bensì alla performance finanziaria. L'analisi proposta si svolge in due stadi. Nel primo, si utilizza un approccio di valutazione multi-criteriale (Ishizaka e Nemery, 2013; Greco et al., 2016) combinando le tecniche introdotte da Cohen et al. (2012) e Galariotis et al. (2016), al fine di indagare le performance finanziarie dei comuni italiani utilizzando gli indicatori finanziari ISTAT (2019). In particolare, si è seguito lo stesso approccio già adottato in Paradiso et al. (2019), al quale si rimanda per una diffusa esposizione, ma modificato per consentire l’analisi specifica della dimensione demografica dei comuni. Nel secondo stadio (esplicativo), gli indici ottenuti dal primo stadio sono stati analizzati per ottenere informazioni sulle relazioni strutturali tra le performance finanziarie e diversi fattori ambientali (interni ed esterni) che caratterizzano i comuni italiani. In particolare, sono stati considerati sia specifici fattori interni riconducibili al contesto politico-istituzionale, sia fattori esterni riconducibili al contesto socio-economico, incidenti sulle performance finanziarie dei comuni
Miti e realtà della condizione finanziaria dei comuni italiani: un approccio multi-criteriale
No full textThis paper proposed a Multi-Criteria Benchmarking (Ishizaka, Nemery, 2013; Greco et al. 2016) combing the techniques introduced by Cohen et al. (2012) and Galariotis et al. (2016) to study the financial performances of the Italian municipalities using the ISTAT (2019) financial indicators. This Multi-Criteria Benchmarking is used to measure financial performances in a peer assessment context over time. This approach allows to summarise a multitude of indicators in order to identify the strengths and financial problems of municipalities
The impact of air pollution on hospital admissions: Evidence from Italy
Full text linkIn this paper we study the impact of air pollution on hospital admissions for chronic obstructive pulmonary disease for 103 Italian provinces, over the period from 2004 to 2009. We use information on annual mean concentrations of carbon monoxide, nitrogen dioxide, particulate matter, and ozone measured at monitoring station level to build province-level indicators of pollution. Hence, we estimate a regression model for hospital admissions, where we allow our aggregate measures of pollution to be subject to measurement error and correlated with the error term. We also adopt standard errors for estimates that are robust to serial and spatial correlation in the error term, to allow for temporal persistence and geographical concentration of unobservable risk factors.We find that higher levels of particulate matter are associated with higher levels of hospitalisation for children, while ozone plays an important role in explaining hospital admissions of the elderly. Other factors that appear to have an effect on hospital admissions for chronic obstructive pulmonary disease are precipitation and provincial unemployment rate
Health Care Expenditure and Income: A Global Perspective
No full textThis paper investigates the long-run economic relationship between healthcare expenditure and income in the world using data on 167 countries over the period 1995–2012, collected from the World Bank data set. The analysis is carried using panel data methods that allow one to account for unobserved heterogeneity, temporal persistence, and cross-section dependence in the form of either a common factor model or a spatial process. We estimate a global measure of income elasticity using all countries in the sample, and for sub-groups of countries, depending on their geo-political area and income. Our findings suggest that at the global level, health care is a necessity rather than a luxury. However, results vary greatly depending on the sub-sample analysed. Our findings seem to suggest that size of income elasticity depends on the position of different countries in the global income distribution, with poorer countries showing higher elasticity. Copyright © 2016 John Wiley & Sons, Ltd
- …
