STATISTICAL INFERENCE AND LEARNING

This course belongs to the educational activities of the Master in Computer Science that allow the student to acquire advanced instruments for data analysis and machine learning. The objective of the course is to develop statistical skills for the analysis of high dimensional data and for solving forecasting and classification problems occurring in a wide variety fields, including technological, scientific, biomedical, economic and business fields.

Regular and active participation in the teaching activities offered by the course and in independent research activities will enable students to:
1. (knowledge and understanding)
- know and understand advanced statistical learning methods for synthesis, prediction and classification
2. (applying knowledge and understanding)
- autonomously apply advanced statistical methods to synthetize information, make predictions and classifications even with data characterized by high-dimensionality
- autonomously use statistical software to analyse datasets characterized by high dimensionality
3. (making judgements)
- formulate autonomous judgements on the validity and feasibility of different statistical techniques and understand their impact on the results of the analyses

It is assumed that students have achieved the educational objectives of the Applied Probability for Computer Science course (https://www.unive.it/data/educazione/335487 ) even without having necessarily passed the exam. In particular, it is important that students are thoroughly familiar with the basic concepts of probability calculus, random variables, simulation techniques and the basic tools of statistical inference.

The course program includes presentation and discussion of the following topics:
1. linear prediction models
2. classification techniques
3. resampling methods
4. model selection and regularization
5. nonlinear models
Applications with R language (www.r-project.org) are an integral part of the course.

- James G, Witten D, Hastie T, Tibshirani R (2015). An Introduction to Statistical Learning. 2n edition. Springer. Webpage https://www.statlearning.com/
- Readings and supplementary materials distributed during the course via the Moodle platform

The achievement of the course objectives is assessed through the oral discussion of a project agreed with the teacher. The project consists in the analysis of a data set using the methods learned in the course. The student is required to prepare a report describing the analyses and then discuss the report with the teacher.

Students will be evaluated in terms of
- quality of their statistical analyses
- correct use of the technical terminology
- correct conclusions
- quality of presentation (report)
- quality of the oral discussion

Rules:
1) if the student fails the exam, they can try another session with the *same* project. However, if the exam is failed again, then a *new* project must be considered for the subsequent exam sessions
2) if the student passes the exam but decides to decline the score, then a *new* project must be considered for the subsequent exam sessions

oral

The overall score is given by the sum of the evaluation assigned to the report describing the statistical analyses carried out (60%) and the evaluation assigned to the oral presentation and discussion of the results described in the report (40%). During the discussion, students may also receive questions on course topics not covered in the project.

The exam result is graded as follows:
- sufficient (18-22 points), if the student demonstrates a sufficient knowledge and understanding of the course methods, is able to apply and interpret them adequately, and uses technical terminology correctly;
- fair (23-25 points), if the student shows a good knowledge and understanding of the course methods, applies and interprets them convincingly, and uses technical terminology with fair accuracy;
- good (26-28 points), if the student possesses a solid knowledge and understanding of the course methods, applies and interprets them in a thoroughly convincing manner, and employs technical terminology accurately;
- excellent (29-30 points), if the student demonstrates an excellent knowledge and understanding of the course methods, applies and interprets them brilliantly, and uses technical terminology with extreme accuracy.

Distinction (lode) is reserved for students who, in addition to having achieved an excellent result, demonstrate an exceptional commitment in the execution and presentation of the project, providing original contributions or insights.

Conventional theoretical lectures complemented by exercises, discussion of case studies and computer labs. Teaching material prepared by the teacher will be distributed during the course through the Moodle platform. The statistical software used in the course is R (www.r-project.org).