[Forum SIS] Università G. d’Annunzio di Chieti-Pescara – Seminari Goia e Boungiorno

[dibattis a unich.it]

Si avvisa che in data 22-11-2018, alle ore 12:00, presso l'Aula  
Dottorandi del Dipartimento di Scienze Filosofiche, Pedagogiche ed  
Economico-Quantitative (Sezione di Economia e Metodi Quantitativi, 1º  
piano - Viale Pindaro - n. 42 – Pescara), Università “G.d’Annunzio” di  
Chieti-Pescara, si svolgeranno i seguenti seminari:

Titolo: Small-Ball Probability: theory and application to Functional  
Data Analysis
Relatore: Aldo Goia

Abstract: With Small-Ball Probability (SmBP) we mean the behavior of  
the probability that a random process X is contained in a ball  
centered in a fixed point and whose radius tends to zero. A classical  
hypothesis assumes that the SmBP can be factorized into two terms that  
isolate the spatial contribution (i.e. the dependence on the center of  
the ball) and the volumetric contribution (i.e. the dependence on the  
radius) respectively. The first factor plays the role of  
pseudo-density for X and allows to define some classification  
methodologies. The second factor allows to evaluate the complexity of  
the underlying process X and can be used in building some  
goodness-of-fit test procedures.


Titolo: Functional Principal Component Analysis for Lorenz curves
Relatore: Enea Bongiorno

Abstract: Lorenz curves are widely used in economic studies  
(inequality, poverty, differentiation, etc.). From a model point of  
view, such curves can be seen as constrained functional data for which  
functional principal component analysis (FPCA) could be defined.  
Although statistically consistent, performing FPCA using the original  
data can lead to a suboptimal analysis from a mathematical and  
interpretation point of view. In fact, the family of Lorenz curves  
lacks very basic (e.g., vectorial) structures and, hence, must be  
treated with ad hoc methods. This work aims to provide a rigorous  
mathematical framework via an embedding approach to define a coherent  
FPCA for Lorenz curves. This approach is used to explore a functional  
dataset from the Bank of Italy income survey.


Tutti gli interessati sono invitati a partecipare.

Cordiali saluti,
Tonio Di Battista