Matthieu Saumard (Cnam) : Deux applications des données fonctionnelles

Lieu: CNAM 33.1.19
Date et Heure de début: 17-11-2016

 In this talk, I will present one application of functional models to astrophysics and another to econometrics. The rst paper investigates the problem of prediction of stellar parameters, based on the star's electroagnetic spectrum. The knowledge of these parameters permits to infer on the evolutionary state of the star.

From a statistical point of view, the spectra of di erent stars can be represented as functional data. Therefore, a two-step procedure decomposing the spectra in a functional basis combined with a regression method of prediction is proposed. We also use a bootstrap methodology to build prediction intervals for the stellar parameters. This is a joint work with Sylvain Robbiano and Michel Cure. In the second part, we investigate the causality in the sense of Granger for functional time series. The concept of causality for functional time series is de ned and a statistical procedure of testing the hypothesis of non-causality is proposed.

Organise: MSDMA
Contact: Avner Bar-Hen