Piattaforma Kiro - Didattica Curriculare 3+2 e Lauree Magistrali Ciclo Unico

Il corso indagherà le relazioni tra diritto e società attraverso l’analisi di alcuni testi-chiave (di sociologi, filosofi e giuristi) dedicati ai principali problemi della sociologia del diritto.

Verranno trattati, in particolare, i seguenti argomenti: il metodo della sociologia, il rapporto tra norma giuridica e azione sociale, il principio di effettività, le funzioni del diritto, il diritto come mezzo di controllo sociale, la sanzione, il rapporto tra il diritto e i mass-media.

OPTIONAL THREE-YEAR DEGREES

Statistical Learning (Educational Seminars)

University of Pavia

2022/2023

Instructor Daniel Felix Ahelegbey

Email danielfelix.ahelegbey@unipv.it

Webpage https://sites.google.com/site/danielfelixahey

Class Meetings Fridays (9:00 – 11:00 am)

Classroom Room 15

The general purpose of the proposed educational seminars is to introduce students to the discovery of the most popular statistical learning methods, both on the theoretical and practical sides.

The cycle of seminars is organized in 16 hours of lectures (8 lectures). Specifically: the first part presents the basic statistical learning models (linear and logistic regression models) and an overview of the main metrics used for comparing different models and selecting the best one; the second part of the course is addressed to the introduction of a set of more complex statistical learning models and classification techniques (cluster analysis, neural network and tree models).

The statistical software R is used throughout. Case studies and dataset examples will be used extensively to give students an appreciation for the application of statistical and computer science methodologies to the financial and credit scoring settings.

At the end of the cycle of seminars, students have to describe and discuss in a written report the results provided by the analysis of a real dataset implemented in R.

The detailed program and the related schedule is reported below.

1. Introduction to R Programming

2. Linear Regression

3. Logistic Regression

4. Model Selection

5. Networks

6. Cluster Analysis

7. Tree Models

8. Neural Networks