Statistical Inference for Spherical Functional Autoregressions
A hacking day of Mathematics for Data Science at the Department of Mathematics

Bio
My name is Alessia Caponera and I am currently a Postdoctoral Researcher at the Department of Mathematics, University of Rome Tor Vergata, in the research team of Prof. Domenico Marinucci. I received my Ph.D. in Statistics from the Department of Statistical Sciences, Sapienza University of Rome, in February 2020 I am also an elected member of the board (20182020) of the young group (y−SIS, youngsis.github.io) of the Italian Statistical Society. My main research interests are spacetime spherical random fields and related topics, such as spectral representations, spherical wavelets and needlets, functional timeseries analysis on the sphere.Syllabus
In recent years, timevarying spherical random fields are naturally becoming an important tool, especially for applications in Climate and Atmospheric Sciences, Cosmology and Astrophysics. Here, we focus on the class of spherical functional autoregressions, which can be interpreted as a functional extension to the sphere of the wellknown realvalued autoregressive processes, and we discuss two estimation procedures for the corresponding autoregressive kernels. The former is based on a functional minimisation criterion, the latter on its penalised version, leading to a LASSOtype estimator. We present some asymptotic results and concentration bounds. Then, we compare their performances through simulations.
References
 Caponera, A., Marinucci, D. (2020+) Asymptotics for spherical functional autoregressions. Annals of Statistics. In press. arXiv:1907.05802
 Caponera, A., Durastanti, C., Vidotto, A. (2019) LASSO estimation for spherical autoregressive processes. arXiv preprint. Submitted for publication. arXiv:1911.11470
Schedule
 26 June 2020, 10:0012:00
Details
 Poster: PDF
 The participation is free, however a notification by email to Prof. Claudio Agostinelli is mandatory
 For further information, please contact Prof. Claudio Agostinelli
 Venue: Webinar, credentials will be sent to the participants the day before of the event
 Language: English