Introduction to Statistical Learning

Bachelor’s Degree Programme in Philosophy, International and Economic Studies, Ca’ Foscari University of Venice.

Author
Affiliation

Aldo Solari

Department of Economics, Ca’ Foscari University of Venice

This is the website of the Introduction to Statistical Learning course of the Bachelor’s Degree Programme in Philosophy, International and Economic Studies, Ca’ Foscari University of Venice.

Teaching material

Required

Optional

Slides and lecture notes

The slides are meant to be used in HTML. However, if you really want to convert the HTML slides into pdf files, you can follow the instruction of the quarto documentation.

Topic Notes Slides & Code
Introduction Unit A Slides Unit A
Lab 1 Lab 1 Code Lab 1
Exercises Exercises A - Conceptual Exercises A - Applied
The Bias-Variance Trade-Off Unit B Slides Unit B
Lab 2 Lab 2 Code Lab 2
Exercises Exercises B - Conceptual Exercises B - Applied
Linear Regression Unit C Slides Unit C
Lab 3 Lab 3 Code Lab 3
Exercises Exercises C - Conceptual Exercises C - Applied
Tree-Based Methods Unit D Slides Unit D
Lab 4 Lab 4 Code Lab 4
Exercises Exercises D - Conceptual Exercises D - Applied
PCA and Matrix Completion Unit E Slides Unit E
Lab 5 Lab 5 Code Lab 5
Exercises Exercises E - Conceptual Exercises E - Applied

Prerequisites

  • Basic mathematical background (no advanced mathematics needed)

  • Elementary knowledge of statistics is strongly recommended but not required (e.g., Introduction to Probability for Economics)

  • Familiarity with linear regression is helpful but not required

  • No detailed knowledge of matrix operations is required

  • Previous exposure to a programming language (e.g., R or Python) is useful but not required

Labs

The course is delivered in a lecture format, with selected sessions devoted to programming activities (``labs’’). Students must bring their own laptop to these sessions and have R and RStudio installed.

Exam

The exam consists of two parts:

  • Data analysis project, which aims to evaluate your ability to build predictive models. You must submit:

    • your predictions, together with the code used to reproduce them;
    • a report (maximum 4 pages) describing your analysis.

    The data analysis must be uploaded on the course Moodle page at least three days before the exam date and can be submitted only once per academic year.

  • Oral exam, which may include a discussion of your data analysis and questions on the topics covered in class, including assigned exercises and programming.

Office hours

Office hours are held on Fridays at 11:00 AM in office C2.111, San Giobbe Economic Campus. Please book an appointment in advance by email.

Acknowledgments

The primary source of this website’s content is the textbook Gareth, Witten, Hastie and Tibshirani (2023). A few pictures have been taken from the textbook; in these cases the original source is cited.

I am also grateful to Tommaso Rigon for the use of his Quarto template.

All the mistakes still present are mine.