Among the many good points about being in two different countries is that I am able to connect researchers and students of both places. I see this as a contribution to expanding collaborations in Statistics. I spend the Spring Term in Rome where I teach at "Sapienza" Università di Roma. In the Fall Term I can be reached at Carnegie Mellon University, in Pittsburgh, where I do most of my research work at the Department of Statistics. I have two homes, two workplaces, two sets of collegues, and two sets of friends.

If I leave out the time (a few years) that I was in England, and in the US, I have spent most of my life in Rome, working in the Deparment of Statistical Sciences. First as a student, then as a postdoc, as assistant and associate professor, and eventually as full professor.

I did my Master Degree at the University College in London and my Ph.D at Carnegie Mellon University. I did research with many different people from different countries. I even thought I could spend the rest of my life in the US. From 1992 to 1998 I got an extended leave of absence from the University of Rome and I was at Carnegie Mellon full time, both teaching and doing research. But, later on, I changed my mind as I realized that the best way for me was to be in both places. Home will always be Rome, and Pittsburgh too!

Statistics to me is a lot of fun and excitement. It is great to try discover new ways to solve problems, and to know that a statistician can help in so many different places. The topic that interested me at the beginning was how to design an experiment. What is great about Experimental Design (but also about the whole field of Statistics) is that one can apply the theory to the most diverse areas: from clinical trials, to reliability, from engineering to astrophisics. It is important to try to account for the special needs that are specific to every different field.

Since I spent time in the US, I have become more interested first in the applications and then in noparametric methods. These are important areas where using theoretically sound Statistical methods can be very useful and revarding. Now that the amount of data being collected in all applied sciences is so wide, myself and others are working to expand the use of Statistics in al data driven fields.

Some Related Publications

C. Genovese, M. Perone-Pacifico, I. Verdinelli, and L. Wasserman (2010). Minimax Manifold Estimation. arXiv:1007.0549v2 [math.ST].

C. Genovese, M. Perone-Pacifico, I. Verdinelli, and L. Wasserman (2010). Nonparametric Filament Estimation. arXiv:1003.5536v1 [math.ST].

C. Genovese, M. Perone-Pacifico, I. Verdinelli and L. Wasserman (2009). On the path density of a gradient field. The Annals of Statistics, 37, 6A, 3236-3271.

M. Perone-Pacifico, C. Genovese, I. Verdinelli and L. Wasserman. (2007). Scan Clustering: A False Discovery Approach. Journal of Multivariate Analysis. 98, 1441-1469.

F. Spezzaferri, I. Verdinelli, M. Zeppieri (2007). Bayes Factors for Goodness of Fit Testing. Journal of Statistical Planning and Inference. 137, 43-56.

I. Verdinelli. (2000). Bayesian Design for the Normal Linear Model with Unknown Error Variance. Biometrika. 87, 222-227.

I. Verdinelli and L. A. Wasserman. (1998). Bayesian Goodness of fit Testing using Infinite Dimensional Exponential Families. The Annals of Statistics. 26, 1215-1241.

K. Chaloner and I. Verdinelli. (1995). Bayesian Experimental Design: A Review. Statistical Science. 10, 237-304.

I. Verdinelli. (1992). Advances in Bayesian Experimental Design (with Discussion). Bayesian Statistics 4 , J.M. Bernardo, J.O. Berger, A.P. Dawid, and A.F.M. Smith eds. 467-481.
Oxford University Press, Oxford.

A. Giovagnoli and I. Verdinelli. (1983). Bayes D-Optimal and E-Optimal Block Designs. Biometrika, 70, 695-706.

A.F.M. Smith and I. Verdinelli. (1980). A Note on Bayes Designs for Inference using a Hierarchical Linear Model. Biometrika, 67, 613-619.