The Department has broad and diversified expertise.  Statistics: Bayesian statistics, Bayesian graphical models and networks, causal inference, functional data analysis, multivariate analysis, regression models, sampling plans, experiment design, spatial data and geostatistics,  time series and extreme values, sequential analysis, clustering, ranking, copulation models, risk models, textual data. Some application areas of the methodologies developed are: genetics and personalized medicine, finance  and insurance.     

Regarding Economic Statistics: data quality, spatial econometrics, health economics, economic inequality, microeconomics.

As regards Demography and Social Statistics: Fertility, intentions,  life planning, youth and neet status, ageing and new stages of life, work-family balance, impact of the SARS-CoV2 pandemic, personal and support networks, social media data and youth unemployment, family and relational structures, social isolation, composite indicators with categorical data, Bayesian demography, validation of psychometric scales, multidimensional Rasch model, multilevel models. 

As far as Computer Science is concerned: Computational complexity, Balanced clustering algorithms, Image Recognition, Deep learning.

Rosina recounts how, after the lively growth of the post-war period, Italy slipped into a regressive demographic spiral with very concrete repercussions: pensions under pressure, shortage of health personnel, social balance increasingly entrusted to immigration. The demographer also indicates the steps - political, collective and individual - necessary to keep the future of the new generations open.

The volume, published by Vita e Pensiero (December 2025) and edited by Riva and Chiriatti,  is divided into four sections. In the chapter Causal Reasoning for Artificial Intelligence of section 3, Guido Consonni and Federico Castelletti argue for the need to combine the simple identification of patterns in data - typical of AI -  with the understanding of the underlying mechanisms of cause and effect in order to meet the growing needs for interpretability, explainability and fairness of machine learning systems in real-world applications. To this end, in the chapter they introduce the fundamental ideas and methods of causal modeling and causal discovery as a conceptual framework and reasoning support tool.

Federico Castelletti and Lucia Paci won the 2025 High Quality Award in Area 13 - Economics and Statistics  with the following publications:

• Castelletti, F., Consonni, G., Bayesian Sample Size Determination for Causal Discovery, STATISTICAL SCIENCE, 2024; 39 (2): 305-321. [doi:10.1214/23-STS905]
• Argiento, R., Filippi-Mazzola, E., Paci, L., Model-Based Clustering of Categorical Data Based on the Hamming Distance, JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 2025; 120 (550): 1178-1188. [doi:10.1080/01621459.2024.2402568] 

Giuseppe Arbia has been appointed to the ISTAT Scientific Committee and to the Agenas Scientific Committee.