immagine esempio

Regularization, penalization techniques and local modelling


Cycle of 5 seminars held by Professor Irene Gijbels (Department of Mathematics, Section of Statistics at the University of Leuven) at the IAC seminar hall in Rome, according to the following schedule: - Monday 2/07/2018 10:00 - 13:00 - Tuesday 3/07/2018 9:00 - 12:00 - Wednesday 4/07/2018 9:00 - 11:00 - Thursday 5/07/2018 9:00 - 11:00


(I). Multiple linear regression: regularization and penalization methods

* least squares regression and Ridge regression

* regularization and penalization techniques

(II). Flexible mean regression: regularization and penalizations methods

* penalized likelihood regression for generalized linear models

* additive regression models and penalization techniques

* varying coefficient models and penalization techniques

* grouped regularization methods.

(III). Regularization and penalizations methods in mean and dispersion regression

* mean and dispersion estimation and P-splines approximations

* mean and dispersion estimation in a framework of proper dispersion models.

(IV). Nonparametric mean regression using local polynomial fitting

* from parametric polynomial regression to local polynomial regression

* asymptotic properties of local polynomial regression

* selection of procedure parameters

(V). Local likelihood methods and nonparametric logistic regression

(VI). Elements of nonparametric inference for functional data analysis.