B0138 - ECONOMICS AND DATA SCIENCE

Learning outcomes

The course is designed to develop students’ abilities to address causal and predictive questions in the modern age of Data Science applied to Social Sciences. At the end of the course, students will be able to: Understand the differences and complementarities between the Data Science and Economics approach to research; Be familiar with the Big Data revolution; Use Big Data and machine learning for causal inference; Be familiar with the most important approaches to program evaluation to inform decision making; Understand the advantages and value added of using Big Data for applied research in Social Sciences.

Course contents

This course introduces the emerging field that merges Data Science and Economics to answer policy relevant questions. We begin with a discussion of causal and predictive models. We then discuss how the big data revolution has shaped research in Social Sciences, and how to use Data Science to address research questions of policy relevance.

The detailed syllabus is available on the course's page on Virtuale.

IMPORTANT:

PRE-REQUISITES: in order to attend this course it is necessary to have a solid knowledge of the core elements of statistics, and to be able to use stastistical softwares for data analysis. There are two main pre-requisites:

1. The course is designed for students that have previously attended the course B0136 - RESEARCH METHODS (A) or RESEARCH METHODS (B). Alternatively, students must have attended an advanced statistics class.

2. It is necessary to be familiar with the statistical software STATA for data analysis, and to have an introductory knowledge of the statistical software R.

NOTE: the course is open exclusively to exchange students (Erasmus, Turing, Overseas, …) enrolled in Master’s level degrees.

Readings/Bibliography

There is no given recommended textbook for this course. For each topic, a full list of readings is posted on the class website on Virtuale. The expectation is that students will have read the assigned readings before the class meetings.

Teaching methods

The course is organized over 10 weeks and discusses 5 main topics. Each topic is presented and discussed for 2 consecutive weeks using two teaching components. The first component is made by 2 lectures of 2 hours each and introduces students to the theory and core concepts of each topic. The second component is made by 2 seminars of 2 hours each. To promote an active participation to the seminars, students will be divided in 2 groups and will attend one seminar for each topic. The main goal of the seminars is to discuss how to bring the theory to the data. The seminars provide an opportunity for an active participation through presentations, discussions, and group projects. During the seminars, students will improve their understanding of the key concepts and methods introduced in the lectures by evaluating arguments in the discussions as well as by applying the concepts and methods in the analysis of existing work and in solving empirical exercises.

Assessment methods

There are 2 different exam formats, one for students that regularly attend and participate to classes and seminars, and one for students that do not regularly attend classes and seminars.

Regularly attending students

Students are “regularly attending students” if they skip a maximum of 5 classes. Regularly attending students must also attend all seminars.

Exam for regularly attending students

The exam has 2 parts.

The first part consists of responses to weekly (individual or group) assignments assigned during the seminars. Three of these assignments will be marked and graded pass/fail. All passing marks will provide 1 point to add to the final grade.

The second part consists in a take-home assignment at the end of the course. This take-home assignment exam represents 100% of the final grade (plus a maximum of three points from the passing marks of the weekly assignments).

Students will have to take this second part by the final exam session scheduled for the 2023-2024 course's edition. To take the second part of the exam, students have to sign up on Almaesami. If regularly attending students do not take the second part of the exam by the final exam session scheduled for the 2023-2024 course's edition, their grade achieved in the first part will be automatically deleted and they will have to take the entire exam as non-attending students.

Exam for non-attending students

Take-home assignment.

To take the exam, students have to sign up on Almaesami.

For all students

The only valid mark is the one achieved in the most recent attempt to pass the exam.

REJECTION OF A VALID MARK: students who pass the exam can refuse the final mark (thus requesting to re-take the exam) only once, in accordance with the university’s teaching regulations. After having rejected one passing mark, any other subsequent passing mark will be recorded in the candidate’s transcripts.

Each student is personally responsible for his/her registration to the exam session on AlmaEsami. Registration closes 5 days before the exam. Therefore, it is not possible to sign up for the exam in the 5 days before the exam date.

Teaching tools

The lecture slides will be provided.

Office hours

See the website of Chiara Binelli