### Teachings

Select Academic Year:     2016/2017 2017/2018 2018/2019 2019/2020 2020/2021 2021/2022
Professor
FRANCESCO MOLA (Tit.)
CLAUDIO CONVERSANO
Period
First Semester
Teaching style
Convenzionale
Lingua Insegnamento
ITALIANO

Informazioni aggiuntive

Course Curriculum CFU Length(h)
[60/65]  MATHEMATICS [65/60 - Ord. 2020]  MATEMATICA APPLICATA 9 72

### Objectives

The main objective of the course is to provide the student with statistical and data analysis methods that depart from the classical approach the student has acquired during the first level statistics courses.
The approach adopted belongs to the typical setting of statistical learning, namely the statistical methods that are based on learning from data. At the end of the course, the students will know, both at a methodological and applied level, the methods developed in the last 20 years, thanks to the continuous increase of the available computational power, useful to analyze data, even in big quantities, and to identify the main factors that drive choices in the economic sector.

### Prerequisites

Knowledge of basic statistics, basic computer science, and basic mathematics are required. Knowledge of Linear Algebra (basic elements) and Econometrics are equally useful although not mandatory.

### Contents

- Introduction to the concept of Statistical Learning and Data Science;
- Applicability of Statistical Learning methods to economic problems;
- The problem of prediction from a Regression and Classification perspective;
- Simple and quadratic discriminating analysis;
- Resampling methods (Bootstrap and Cross-Validation);
- Model selection (Forward and Backward model selection);
- Lasso and Ridge regression;
- Unsupervised learning methods (Clustering and Principal Components Analysis).

### Teaching Methods

The course comprehends 36 hours of remote learning. Classes include a theoretical discussion and practical applications of the methodologies considered through the use of different softwares.

### Verification of learning

In view of both the theoretical and applied nature of the course, the final evaluation includes two main moments:
a) writing (40%) and submitting (10%) a final report of at least 5000 words focused on solving a real problem. Students will be allowed to work in pairs or individually. The report will be discussed in the oral exam. In this phase, the ability to apply the acquired knowledge, autonomy of judgment and technical communication skills will be assessed.
b) Oral exam (50%) which focuses on a critical analysis of the report and on the methodologies included in the program. Communication skills, acquired knowledge and understanding skills will be assessed.

### Texts

Gareth James, Daniela Witten, Trevor Hastie and Robert Tibshirani
An Introduction to Statistical Learning with Applications in R. Springer (free e-book available).

Not mandatory: The Elements of Statistical learning. Data Mining, Inference and Prediction. Trevor Hastie , Robert Tibshirani, Jerome Friedman - Springer. 2nd Edition