In the current era of big data and data science, data are generated at an unprecedented pace, offering vast opportunities for discovery while simultaneously posing new scientific and methodological challenges. The new generation of researchers in Statistics will be called upon to address these challenges by contributing to the advancement of modern statistics and data science through the development of novel tools and methodologies capable of fully harnessing the potential of data.

The objective of the Data Research Camp is to bring together researchers in statistics and data science in an intellectually stimulating setting that encourages the exchange of ideas, promotes discussion, and fosters new scientific connections and interdisciplinary collaborations.
The Camp is expected to have both short- and long-term impacts, laying the groundwork for new interdisciplinary research directions and leading to cutting-edge contributions to modern statistics from both methodological and applied perspectives.

The Research Camp is supported by the excellence program “Rethinking Data Science (ReDS): advances in causal inference and statistical learning across domains” and it is endorsed by the PhD programs in Statistics of the University of Florence , Bocconi University, University of Bologna, University of Padova and Politecnico di Milano.

The Data Research Camp 2026 builds on the success of three previous editions. The 2024 edition was organized by the Department of Statistics, Computer Science, Applications and the Florence Center for Data Science at the University of Florence, while the earlier 2019 and 2022 editions were organized by the Department of Statistical Sciences of the University of Padua (see the websites of the 2019 and 2022 editions).

---

Senior Group Leaders

Leopoldo Catania

Aarhus University, Denmark

Andreas Groll

Dortmund University, Germany

Mohammad Jafari Jozani

University of Manitoba, Canada

Omiros Papaspiliopoulos

Bocconi University, Italy

Davide Risso

University of Padova, Italy

Laura M. Sangalli

Politecnico di Milano, Italy

Veronica Vinciotti

University of Trento, Italy

L'articolo The Data Research Camp 2026 proviene da Rethinking Data Science.

PRIN 2022 PNRR
UNIFI local PI: Andrea Marino
UNIFI personnel: Ana Shirley Ferreira Da Silva, Jason Schoeters
Coordinator: Università degli Studi di Pisa (PI: Laura Ricci)
Participants: Università degli Studi di Firenze, CNR (local PI: Paolo Mori)

Brief description of the proposal

Our project is aimed at creating an environment to provide the widespread public with direct access to the main Distributed Ledgers behind the decentralized protocols at the base of the Web 3.0. We propose to achieve this by leveraging cutting edge research in several Computer Science fields (distributed systems, graph theory, and data visualization) to achieve ambitious results perfectly aligned with the PNRR goals.
Distributed Ledger Technology (DLT) is well aligned with the PNRR principles, especially for, but not limited to, what concerns empowering users in the digital sphere. In fact, DLT trustworthiness, transparency, and automation are properties highly desirable when attempting to digitize traditional processes or improve existing digital ones. By encouraging and supporting digitization without compromising security alone, for example for state administrations, DLT helps in reducing paperwork and information storage and sharing, in turn reducing the impact on the environment. But the unique properties of DLTs can even enable novel processes or business models impossible with traditional centralized solutions.
Let us consider for example the ‘circular economy’ strategic emerging topic of the PNRR Mission 4 this project is framed in. Circular economy is based on the concept of recycling, but often not enough incentives are given to end users in taking part in it, besides moral ones. A DLT could, instead, add a whole system of incentives based on users rewarding, for example through a token economy. Similarly, it could increase transparency of the whole carbon credit system, as well as cutting its cost. DLT can enhance supply chains as well, another key pillar of the circular economy, by providing the full tracking of components life cycle through complete supply chain traceability. This could include tamper resistant carbon footprint information as well, further aligning with the PNRR goals.
But all DLT protocols ultimately rely on the ability of users to read data on the Ledger, and that is not that can be assumed possible for the wider public, either due to lack of resources or technical know-how. Existing applications to achieve this on behalf of the user are not a good solution, as they are third party components that reintroduce the need for user trust. This is why we propose a novel environment that enables users to access DLT data in a trustworthy, user-friendly way and formats the results in an easy to understand graphical way. The toolset is flexible and powerful enough to be used by researchers, decentralized applications, and the widespread public alike. Among its theoretical contributions, the toolset will introduce a uniform representation for transactional data coming from heterogeneous ledgers and will provide advanced state-of-the-art temporal graph analysis and visualization tools.

L'articolo DLT-FRUIT – A user centered framework for facilitating DLTs FRUITion proviene da Rethinking Data Science.

Brief description of the proposal

Recent demographic trends, such as declining fertility and mortality rates and changes in union stability, will lead to larger numbers of middle-aged adults with fewer family members. Such a trend is of paramount relevance, given that individuals who have no kin may face greater risks of mental health deterioration and lack of personal care in later life. Yet, much of contemporary research has only focused on a small part of the family network, i.e. the nuclear family, or on vertical ties between parents, children and grandchildren. This focus ignores the potential effect of extended kinship relations on individuals’mental health and wellbeing.

The KinHealth project investigates whether the extended kinship, including in-laws, siblings, cousins, nieces/nephews, and uncles/aunts, plays a relevant role, over and above the nuclear family, in promoting individuals’ wellbeing. Focusing on a specific cohort of adults aged 50-65 who are relatively free from health needs and likely to have both older and younger relatives alive, we articulate this overarching question into three research objectives.

Objective 1: to uncover the extended kinship and describe its characteristics, i.e. the quantity of living kin and patterns of
residential proximity, contact and support exchange between relatives.
Objective 2: to assess the association between the extended kinship – i.e., the quantity and the geographical spread of kinship – and an individual’s mental health and wellbeing. The kinship network is a web of potential support that may promote feelings of reassurance and wellbeing, whether or not family members need it.
Objective 3: to assess whether providing support and care to older and younger relatives is associated with declines in mental health and wellbeing. This will provide new evidence on kinship as a social environment of shared responsibility and commitment to provide support, which may either increase or reduce the mental-health stress of support givers.
We will integrate the best secondary data sources on Italian families with primary data collection to address data limitations. The results of the project will have implications for public health services and the demand for institutional care.

L'articolo KinHealth – Beyond the nuclear family: Extended kinship and mental health in Italy  proviene da Rethinking Data Science.

A special , interdisciplinary, international  Symposium on Causality  has been organized by the Department of Statistics, Computer Sciences and Applications of the University of Florence in collaboration with the Harvard Data Science Initiative, the European University Institute, and other stakeholders.

The Symposium on Causality  was hosted at the Museo Galileo.

The event was one of several planned to celebrate the centenary of the University of Florence.

The Symposium has been a collection of contributions on the state of the art and future challenges in causality and causal inference for the new era of Data Science.

Four keynote lectures (Guido Imbens, Elizabeth Stuart, Mihaela van der Schaar, Alessandro De Angelis) on the field’s past, present and future from different perspectives and disciplines, plus four roundtables on hot topics in causality and causal inference with experts from academia and the industry have been planned.

Program

List of Participants

Photos

Video

Keynote Speakers

Guido Imbens

Applied Econometrics Professor and Professor of Economics, Graduate School of Business, Stanford University

Causal Inference with Panel Data: New Methods and Remaining Challenges

In recent years much work has been done on methods for credibly estimating causal effects in settings with panel data. These methods, including synthetic control methods, matrix completion methods and variations thereon have have greatly improved our understanding of the challenges in estimating causal effects with longitudinal data. In this presentation I will describe some of these insights, and also discuss shortcomings of the existing methods. In particular these include the lack of accounting for the time series aspect of the longitudinal data and the challenges for inference. I will discuss new estimators that take the time series dimension more seriously and show how they improve estimation. I will also discuss new methods for inference that improve the power of testing for the presence of causal effects. (based on joint work with Alex Almeida,  Susan Athey, Alexia Olaizola,  Zhaonan Qu, Alex Almeida,  Eva Lestant, and Davide Viviano).

Elizabeth A. Stuart

Frank Hurley and Catherine Dorrier Professor of Biostatistics, Johns Hopkins Bloomberg School of Public Health

Integrating data for causal inference

Many causal questions of interest cannot be answered through analysis of a single dataset, and as data becomes increasingly available, there is more and more interest in leveraging that data to answer nuanced questions. Such questions might include examining the generalizability of randomized trial results to target populations, to better understanding of effect heterogeneity by combining small (unbiased) randomized trials with large (but confounded) non-experimental data sources. This talk will discuss methods for causal inference in such integrated datasets, including both the promise and potential for doing so, as well as implementation challenges, such as when the measures in the different data sources are discordant. Motivating examples will come from medicine and public health, and with lessons for a range of fields, and with final comments on the broader field of evidence synthesis for causal inference.

Alessandro De Angelis

Full Professor of Experimental Physics, University of Padova and University of Lisboa

Causality in physics: from Galileo to Einstein

Galileo’s work established a formal concept of causality in physics by using mathematical descriptions of physical processes to predict the evolution of systems from causes. Building on Galileo’s ideas, Newton formalized this concept within the framework of classical mechanics. In the 19th century, Faraday introduced the concept of field, a region of space where a force operates. Maxwell’s equations formalized this idea, describing how electric and magnetic fields propagate through space, leading to a new understanding of causality. Finally, Einstein revolutionized the concept of causality with his theories of relativity.

Mihaela van der Schaar

John Humphrey Plummer Professor of Machine Learning, Artificial Intelligence and Medicine at the University of Cambridge

The Causal Discovery Ladder: Unravelling Governing Equations and Beyond using Machine Learning

While recent strides in machine learning and statistics have advanced causal inference, several frontiers await exploration in order to make real-world impact. First, I will show how unraveling governing equations from temporal trajectories can deepen our understanding of dynamical systems through causal inference over time. Second, I will explore how causal deep learning can help close the gap between theory and practice, providing practitioners with powerful new ways of thinking and tools. Finally, I will discuss how leveraging real-world observational data can transform various aspects of clinical trials. By pushing these boundaries, we aim to bring causality into practical use, unlocking insights with transformative potential in fields like medicine.

Organizing Committee

L'articolo Symposium on Causality proviene da Rethinking Data Science.

It was an exciting free 4-day meeting where young scholars were prompted to explore statistics and data science to extract new knowledge from data. During the camp, the young scholar participants worked in teams under the guidance of five senior researchers Bianca De Stavola, Daniele Durante, Laura Forastiere, Antonio Gasparrini and Corwin Zigler with leading experience in different areas of Statistics, including  statistical methods for long-term longitudinal studies, Bayesian methods, models for complex, high–dimensional and network–related phenomena, causal inference in complex settings involving spatial and network data, methods for investigating causal pathways through intermediate variables or mechanisms, development of study designs and statistical for  time series data, quasi-experimental studies, and survival analysis. 

The senior researchers worked hard with the young scholars to develop innovative methods and models to analyze a common dataset, to answer scientific questions arising from a cancer genomics case study. The publicly available data of lower grade glioma from the Cancer Genome Atlas (TCGA) data portal was used as motivating application study. Francesco Stingo, who previously worked on these data, was invited to introduce them on the first day of the Data Research Camp. After the presentation of the dataset and Q&A session on the data, the groups started to work! Innovative ideas, new questions and cutting-age statistical methods were proposed to analyze the data as shown by the mid and final presentations. 

The DiSIA is proud to have organized this exciting event; it laid the groundwork for new interdisciplinary pathways that can lead to cutting-age contributions to the modern Statistics from both methodological and applied perspectives. 

The Data Research Camp was supported by the excellence program “Rethinking Data Science (ReDS): advances in causal inference and statistical learning across domains” and it is endorsed by the PhD programs in Statistics of the University of Florence, Bocconi University, University of Bologna and University of Padova. It followed two successful editions organized by the Department of Statistical Sciences of the University of Padua (see the websites of the 2019 and 2022 editions).

Programme

Participants

Photos

---

Senior Group Leaders

Bianca De Stavola

UCL University College London, UK

Daniele Durante

Bocconi University, Italy

Laura Forastiere

Yale University, USA

Antonio Gasparrini

LSHTM – London School of Hygiene & Tropical Medicine

Corwin Zigler

The University of Texas at Austin, USA

L'articolo The Data Research Camp of DiSIA 2024 proviene da Rethinking Data Science.

Brief description of the proposal

The quality of an educational system is strictly related to its capability to enhance the performances of students and to reduce inequality related to their initial conditions. Many researchers document the persistence in Italy of marked differences across educational institutions and geographical areas. The family, the school environment and the peers have also an important influence on educational choices and outcomes, as well as in the transmission of inequalities.
The project aims to study some facets of the mechanisms of reproduction of inequalities within the Italian educational system, with particular attention to the study of the role that the school and academic environment play in shaping interactions between peers, aiming at reducing initial disadvantages and gender gaps. In this context, intangible assets such as the so-called soft skills (as leadership, creativity, self-efficacy, and risk-propensity) are recognised as key variables, fundamental for the development of an innovative mind-set of young people, and consequently their personal development. The study intends to define how and in which contexts the effect of peers, observed at micro and meso level, interacts in the process of reproduction of inequalities in learning outcomes, in the persistence and transmission of intergenerational and gender disparities at school and in the subsequent transition to the university; to attain these objectives, we will take into account the geographical differences and the heterogeneity in the teaching programs. Finally, a further aim is to detect which schools and universities have been able to develop institutional arrangements and practices in such a way to perform as social equalisers, identifying those that have also triggered virtuous and egalitarian processes.

L'articolo From high school to university: Assessing peers’ influence in educational inequalities and performances proviene da Rethinking Data Science.

Brief description of the proposal

This project concerns the development of novel principled statistical tools for the analysis of complex networks under non-standard experimental setups (e.g. relaxing the i.i.d. assumption).
The methodological innovations that can be achieved with this proposal are as follows:

1. Development of multiple, paired, and covariate-dependent graphical models for heterogeneous networks for both continuous and discrete variables
2. Development of single and multiple graphical models for causal inference based on observational and interventional data
3. Development of graphical models for non-normal (e.g., continuous but not Gaussian or circular data) and censored random variables.

The proposed research is expected to provide a methodological foundation for novel types and classes of graphical models. Compared to existing approaches, the additional benefits of our approaches include their interpretability (such as similarity measures between groups for both graph structures and edge values), their ability to assimilate information from several dimensions and to borrow strength only between related groups and/or units, to include prior information such as known biological regulatory mechanisms, and to provide interpretable measures of uncertainty both for single network structures and similarities between groups. We will develop both Bayesian and penalized likelihood approaches.

The proposed statistical models and computational algorithms are flexible and efficient quantitative tools for the analysis of dependence structures of biological networks, including co-expression, gene regulatory, mutations, and protein interaction networks.
Classical approaches to graphical models are not suited to capture and model the heterogeneous multi-dimensional data structures commonly observed in cancer genomics, nor can take into account intervention or missing data.
The methodology proposed in this application along with the companion software will provide medical researchers with a powerful new set of tools for determining the associations between a large number of genetic variables under a variety of complex data generating mechanisms. The application of the proposed methodology will result in a better understanding of the biological mechanisms of cancer, and other disease types.

Impact. The proposed methods are meant to advance knowledge, both theoretical and applied, in the broad areas of multivariate models for the analysis of high-dimensional complex data. In particular we will provide new methodology for graphical models in a variety of settings: non-standard experimental setups, non-Gaussian distributions, heterogeneous data, causal inference, various regimes for biological networks, using frequentist and Bayesian approaches. Our methods are broadly applicable, and are often motivated by investigations in cancer genomics.

L'articolo Complex graphical models for biological network science proviene da Rethinking Data Science.

Brief description of the proposal

Graph-based models are pervasive in many fields of science and technology and their visualization plays a crucial role in the analysis and exploration of complex datasets. In this scenario, graph drawing is a key research area whose ultimate goal is to construct valuable visualizations of graphs and networks. Despite a great effort over the last thirty years, the problem of computing effective visualizations remains a largely elusive and pressing one. The objective of project NextGRAAL is to develop new algorithmic results and novel visualization paradigms that will provide the scientific groundwork for the next generation of software and tools, which will be able to efficiently compute high-quality graph visualizations with application-driven constraints of various kinds. Besides methodological contributions, the project will experimentally validate the algorithmic solutions on two relevant application domains and will be consequently organized into two main workparts.

WP1: Algorithmic methodologies with theoretical guarantees for constrained graph visualization and exploration. We plan to exploit parameterized and exact algorithms, possibly coupled with complexity lower bounds, to efficiently compute provably-good solutions for hard problems dealing with constrained graph layouts. We will also pioneeringly design enumeration algorithms to explore solutions stemming from layout problems with relaxed constraints.

WP2: Validation of algorithmic solutions for constrained graph visualization and exploration. While our algorithms can be beneficial for multiple applications, we will validate them on two relevant scenarios, i.e., socio-semantic and transportation networks. Exploring the former brings together the study of two intertwined data generation processes: a social community and a content-creation process. Visualizing the latter is crucial to make complex infrastructures easily accessible to a broad set of users.

Impact. Given the ubiquity of graphs in science and technology, as well as the key role of visualization in graph processing pipelines, NextGRAAL has a great potential to make a strong impact on research, industry, and society.

Research team and budget. The project is participated by 4 research units: UniPG, UniFI, LUISS, UniRM3. All researchers share a common algorithmic background and yet provide fundamental and complementary expertise on the research topics and methodologies involved in the project. The project budget will be mostly devoted to recruiting young researchers; other resources are either already available (e.g. lab hardware and software) or will be charged to the overhead.

L'articolo NextGRAAL: Next-generation algorithms for constrained GRAph visuALization proviene da Rethinking Data Science.

Brief description of the proposal

Progress in mortality decline has slowed down after 2008.
With this research we intend to:

1. Measure the extent of the deceleration, in general and by area, gender and age group.
2. Link this deceleration to four main possible, not alternative, explanations/causes:

1. Crisis and austerity, budget cuts on public health expenses.
2. Causes of death: are we observing a change in the prevalence of the most important causes of death, and may this change explain the slowdown?
3. Spatial issues. What is happening to the traditional North-South divide? And what about “internal areas”, i.e. small municipalities far away from the centres that provide the most basic services, such as health assistance?
4. Tempo effects. What type of distortion may derive from observing things only cross-sectionally?

The policy implications of our research are potentially large. After the COVID-19 pandemic, there is renewed awareness of the importance of efficient, universal health care systems. With this research project, we intend to identify the most critical aspects of some recent health policy decisions, pointing at successes and failures, if any can be identified.

Project Web site: https://sites.google.com/unifi.it/elesti/home-page

L'articolo The pre-Covid-19 stall in life expectancy in Italy: looking for explanations proviene da Rethinking Data Science.

Brief description of the project

Since 2016, the Italian population has been declining, and Italy is leading global population aging. Children are essential for ensuring the continuity of society and for reducing the old-age dependency ratio to maintain the balance of the welfare state accounts. Low fertility is largely involuntary in Italy. The vast majority of Italians desire to have two children but, on average, end up having only slightly more than one. The gap between desired and actual fertility is the highest in Europe. Similarly, even though only a small percentage of Italian women declare that they do not want children, more than one in five end up having none. The disparities between ideal and actual family sizes and between voluntary and actual childlessness raise two concerns. First, a well-being penalty linked to the unmet desire for children may exist. Second, obstacles preventing couples from having (more) children may exist, constituting an opportunity for policy reforms.

This project, WelFerPoli, will: 1) shed light on eventual well-being penalties among individuals with smaller-than-desired family size or who are involuntarily childless; 2) investigate to what extent public policies can intervene to remove the obstacles preventing individuals from achieving their desired fertility, thereby improving their wellbeing and ensuring a just society and a sustainable welfare state in the future.

These two objectives will be achieved by analyzing secondary data sources for Italy, including underused longitudinal studies. This analysis will be complemented by primary data collection, integrated with a factorial survey experiment conducted on a representative sample of over 5,000 Italian men and women. The project will carry out an ex-ante evaluation of possible fertility-friendly policy reforms as well as the ex-post evaluation of an Italian best practice: the integrated set of policies implemented since the 1990s in the Autonomous Province of Trento.

By raising awareness of the well-being penalties associated with unmet desires for children, WelFerPoli has the potential to justify investments in family and fertility policies. It can also provide valuable insights to policymakers on the policy mix that could boost fertility rates in Italy.

L'articolo Well-being and Fertility Policies (WelFerPoli) proviene da Rethinking Data Science.