Il ricevimento degli studenti può essere svolto in presenza ed a distanza. In entrambi i casi, lo studente è pregato di contattare il docente all'indirizzo mail istituzionale.
Since 2019 Associate Professor, s.s.d. SECS/S-01, Dipartimento di Scienze Statistiche, Sapienza Università di Roma, Rome (Italy).
2012-2019 Assistant Professor, s.s.d. SECS/S-01, Dipartimento di Scienze Statistiche, Sapienza Università di Roma, Rome (Italy).
2010-2012 – Post-Doctoral position, Dipartimento di Scienze Statistiche, Sapienza Università di Roma, Rome (Italy). Research project title: “Metodologia statistica relativa alle tecniche di analisi esplorative e inferenziali”. Supervisor: Prof. M. Vichi.
2008-2010 – Post-Doctoral position, Department of Medical Statistics and Bioinformatics (Leiden University Medical Centre) Leiden (The Netherlands). Supervisor: Prof. J.J. Houwing Duistermaat.
2007-2008 – Post-Doctoral position, ESAT Department, Katholieke Universiteit Leuven (Belgium).Supervisors: Prof. Y. Moreau and Prof. J. Vermeesch.
2007 – Visiting researcher at Department of Methodology and Statistics (Prof. J.K. Vermunt), Tilburg University, Tilburg (The Netherlands).
2003-2007 – PhD in Statistical Methodology” (XIX ciclo), Dipartimento di Statistica, Probabilità e Statistiche Applicate (Sapienza Università di Roma), thesis title “Model-based double clustering for high dimensional data”. Supervisor: Prof. M. Vichi.
2005 – Visiting researcherat INAPG (Institut national agronomique Paris-Grignon- France, Prof. J.-J. Daudin), Paris (France).
2005- Visiting researcherat Departement of mathematics Equipe Probabilities, Statistique et Modelisation", Universitè de Paris-Sud, (Prof. G. Celeux) Orsay CEDEX (France).
2003 - University graduation. GPA: 110/110 summa cum laude, thesis title: “Model-based approach to clustering Microarray Data”. Supervisor: Prof. R. Coppi.
RESEARCH INTERESTS
The research programme shows a coherent progression from early model-based biclustering and factor-mixture models for high-dimensional continuous and genomic data to a broader class of parsimonious latent-variable methods for complex data.
Recent developments address longitudinal and dynamic structures through Hidden Markov models, discrete and ordinal outcomes, mixed-type data, bipartite networks, sample-weighted mixtures and applications in public health, well-being, digital inequalities and environmental sciences.