A5054448743- Statistical Methods and Bayesian Inference
- Bayesian Methods and Mixture Models
- Regional Socio-Economic Development Trends
- COVID-19, Geopolitics, Technology, Migration
- Impact of AI and Big Data on Business and Society
- Statistical Methods and Inference
- Spatial and Panel Data Analysis
- Advanced Causal Inference Techniques
- Advanced Statistical Methods and Models
- Bayesian Modeling and Causal Inference
- Psychometric Methodologies and Testing
- Census and Population Estimation
- Advanced Statistical Modeling Techniques
- Economic and Environmental Valuation
- Financial Risk and Volatility Modeling
- Data-Driven Disease Surveillance
- Regional Economics and Spatial Analysis
- Statistical Distribution Estimation and Applications
- Statistical Methods in Clinical Trials
- COVID-19 epidemiological studies
- Health disparities and outcomes
- Advanced Chemical Physics Studies
- Urban, Neighborhood, and Segregation Studies
- Markov Chains and Monte Carlo Methods
- demographic modeling and climate adaptation
University of Perugia
2015-2024
University of Teramo
2016
University of Florence
2011
Einaudi Institute for Economics and Finance
2011
University of Urbino
2003-2005
University of Palermo
2001
Forschungszentrum Jülich
1995-2000
Université de franche-comté
1998
Centre National de la Recherche Scientifique
1998
University of Ferrara
1996
Short-term forecasts of infectious disease burden can contribute to situational awareness and aid capacity planning. Based on best practice in other fields recent insights epidemiology, one maximise the predictive performance such if multiple models are combined into an ensemble. Here, we report ensembles predicting COVID-19 cases deaths across Europe between 08 March 2021 07 2022.
Nowadays, practitioners extensively apply quick and reliable scales of user satisfaction as part their experience analyses to obtain well-founded measures within time budget constraints. However, in the human–computer interaction literature relationship between outcomes standardized amount product usage has been only marginally explored. The few studies that have investigated this typically shown users who interacted more with a higher satisfaction. purpose article was systematically analyze...
For the analysis of multivariate categorical longitudinal data, we propose an extension dynamic logit model. The resulting model is based on a marginal parameterization conditional distribution each vector response variables given covariates, lagged variables, and set subject-specific parameters for unobserved heterogeneity. latter ones are assumed to follow first-order Markov chain. maximum likelihood estimation parameters, outline EM algorithm. data approach proposed illustrated by...
Latent Markov (LM) models represent an important class of for the analysis longitudinal data, especially when response variables are categorical. These have a great potential application in many fields, such as economics and medicine. We illustrate R package LMest that is tailored to deal with basic LM model some extended formulations accounting individual covariates presence unobserved clusters units having same initial transition probabilities (mixed model). The main functions parameter...
Errors-in-variables curves are where errors exist not only in the independent variable but also dependent variable. We address challenge of constructing simultaneous confidence bands (SCBs) for such curves. Our method finds application Lorenz curve, which represents concentration income or wealth. Unlike ordinary regression curves, curve incorporates its explanatory and requires a fundamentally different treatment. To best our knowledge, development SCBs has been explored previous research....
A compact high-current 50 kV ion accelerator facility including a windowless gas target system, beam calorimeter, and detector telescopes in close geometry has been built tested. The data acquisition analysis involved multiparameter system Monte Carlo program. LUNA facility, presently installed at the Gran Sasso underground laboratory, is pilot project focused initially on cross section measurements of 3He(3He, 2p)4He reaction within thermal energy region sun. To achieve this goal,...
Performance evaluation of nursing homes is usually accomplished by the repeated administration questionnaires aimed at measuring health status patients during their period residence in home. We illustrate how a latent Markov model with covariates may effectively be used for analysis data collected this way. This relies on not directly observable process, whose states represent different levels status. For maximum likelihood estimation we apply an EM algorithm implemented means certain...
We propose a class of multidimensional Item Response Theory models for polytomously-scored items with ordinal response categories. This extends an existing dichotomously-scored in which the latent abilities are represented by random vector assumed to have discrete distribution, support points corresponding different classes population. In proposed approach, we allow parameterizations conditional distribution variables given traits, depend on type link function and constraints imposed item...
Summary Mixed latent Markov (MLM) models represent an important tool of analysis longitudinal data when response variables are affected by time-fixed and time-varying unobserved heterogeneity, in which the latter is accounted for a hidden chain. In order to avoid bias using model this type presence informative drop-out, we propose event-history (EH) extension approach that may be used with multivariate data, one or more outcomes different nature observed at each time occasion. The EH...
An extension of the latent Markov Rasch model is described for analysis binary longitudinal data with covariates when subjects are collected in clusters, such as students clustered classes. For each subject, a process used to represent characteristic interest (e.g., ability) conditional on effect cluster which he or she belongs. The latter modeled by discrete variable associated cluster. maximum likelihood estimation parameters, an Expectation-Maximization algorithm outlined. Through set...
The considerable increase of non-standard labor contracts, unemployment and inactivity rates raises the question whether job insecurity lack opportunities affect physical mental well-being differently from being employed with an open-ended contract. In this paper we offer evidence on relationship between self-reported health employment status in Italy using Survey Household Income Wealth (SHIW); another aim is to investigate these potential inequalities have changed recent economic downturn...
Summary The paper investigates the problem of determining patterns criminal behaviour from official histories, concentrating on variety and type offending convictions. analysis is carried out basis a multivariate latent Markov model which allows for discrete covariates affecting initial transition probabilities process. We also show some simplifications reduce number parameters substantially; we include Rasch-like parameterization conditional distribution response variables given process...
Summary For a class of latent Markov models for discrete variables having longitudinal structure, we introduce an approach formulating and testing linear hypotheses on the transition probabilities process. maximum likelihood estimation model under this type, outline EM algorithm that is based well-known recursions in hidden literature. We also show that, certain assumptions, asymptotic null distribution ratio statistic hypothesis model, against less stringent same χ¯2 type. As particular...
Summary Motivated by an application to a longitudinal data set coming from the Health and Retirement Study about self-reported health status, we propose model for which is based on latent process account unobserved heterogeneity between sample units in dynamic fashion. The modelled mixture of auto-regressive AR(1) processes with different means correlation coefficients, but equal variances. We show how perform maximum likelihood estimation proposed joint use expectation–maximization...