This volume on statistical methods for data analysis and decision sciences showcases the interplay between statistics and data science, reflecting a broad spectrum of data-driven challenges, innovative approaches, methodological developments and applications. It gathers peer-reviewed short papers presented at the 3rd Conference of the Statistics and Data Science Group of the Italian Statistical Society, SDS 2025, held in Milan, Italy, April 2-3, 2025.
The papers cover a wide variety of topics focused on modeling and analyzing complex data, including structured, non-structured and mixed data, offering fresh perspectives tailored to diverse research goals. The contributions propose innovative methods and approaches in causal inference, sampling and big data, Bayesian methods, functional data analysis, unsupervised learning, robust statistics and penalized regression, spatio-temporal methods, clustering, time series analysis, text analysis and image processing. A wide range of applications in several areas are presented, including environmental issues and sustainability, earth and geohazards, official statistics, social issues and inequality, health informatics, medicine, health and well-being, statistical process monitoring, financial statistics and econometrics, and artificial intelligence, addressing matters of particular relevance for sustainable development, including Sustainable Development Goals (SDGs) 1, 3, 5, 7, and 13, among others.
About the Author :
Francesca De Battisti is a Professor of Statistics at the Department of Economics, Management and Quantitative Methods of the University of Milan, Italy. Her main research interests focus on analysis of inequality measures, evaluation of service quality, evaluation of customer and job satisfaction, evaluation of occupational outcome, PLS-SEM models to investigate latent constructs and their relationships, and in general on statistics for the social sciences.
Samantha Leorato is a Professor in Statistics at the Department of Economics, Management and Quantitative Methods, University of Milan, Italy. Her research interests span spatial econometric modeling (Bayesian and non-Bayesian), optimal design, nonparametric and semiparametric statistical inference, and divergence-based inference.
Chiara Masci is a Tenure-track Researcher at the Department of Economics, Management and Quantitative Methods at the University of Milan, Italy. Her research is primarily in the statistical analysis of data with hierarchical structures. Specifically, her expertise lies in mixed-effects models, tree-based methods, nonparametric statistics, survival analysis, maximum likelihood estimation, and, more recently, cluster-weighted models. Her research in methodological statistics is deeply rooted in two key application areas, namely education and health.
Federica Nicolussi is a Professor in Statistics at the Department of Mathematics, Politecnico di Milano, Italy. Her research focuses on the study of relationships between categorical and ordinal variables through the development of graphical models, density distribution of continuous random variables, compartmental models, and image analysis. Her research has been applied to social and economic sectors as well as covid-19 data.
