Course 2025-2026 a.y.

Part 1. Causal inference, principles of surveys and modern literature review:

Economics, Social Sciences and the digital data revolution

Systematic reviews and meta-analysis

Survey methods (data from survey, sampling and post-stratification)

The potential counterfactual outcome model

Randomization and its internal and external validity

From experiment to observational data

Part 2. Foundations of social science research in the digital era and big data analysis:

Introduction to machine learning (unspervised and supervised learning)

Predictions and explanation

Data scraping

Large language models

Modelling

Social Network Analysis

Emerging ethical issues in social science research

Define the role of quantitative research in the social sciences

Recognize the strenghts and limitations of randomized experiment

List the main quasi-sperimental research designs

Recognize the variety of digital data available, their potential and their limits

Explain some computational methods

Reproduce computational applications

Develop a systematic review and run a meta-analsyis

Design and draw up a survey

Recognize internal and external biases in randomized experiments

Apply STATA to simple research questions

Analyze data through machine learning

Use web sources

Apply textual analysis to simple datasets

Prepare a presentation and draw up scientific paper

• Lectures
• Practical Exercises
• Individual works / Assignments
• Collaborative Works / Assignments

The practical exercises will involve utilizing a dataset for analysis using STATA and employing user-friendly applications for tasks such as machine learning and web scraping (using Python, Stata or R). Instructors will assign students to groups of five, tasking them with formulating a research question and employing suitable data analysis techniques to address it (refer to the Assessment section for more details).

In the preparation of the paper and the class presentations, students will have the opportunity to develop their critical thinking skills, enhance team-building abilities, and gain exposure to a diverse range of research designs and methods within the social sciences. Collaborating with peers will not only foster creativity but also provide a platform for learning from one another and gaining insights into the criteria used to evaluate research proposals in international scientific settings.

Groups will have the flexibility to choose from three options for their final group project: 1) conducting a systematic review (with the option to include a meta-analysis), 2) designing, implementing, and analyzing data from an online survey experiment, or 3) undertaking a big data study (utilizing machine learning applications, textual analysis, or other relevant techniques).

If you are looking to learn Python, or to refresh the basics, make sure to take Bocconi course “20683- Python preparatory course”. The official Python website also lists a number of excellent online tutorials and textbooks. For STATA there is an in-person course offered by Bocconi at the end of August. 

Students' assessment in this course will encompass three key elements to gauge their overall understanding of the content:

1. Comprehensive grasp of essential research methodologies with big data.
2. Proficiency in conducting basic data analysis using common softwares.
3. Development of an original research paper for presentation in class.

Each of these components evaluates distinct competencies and equips students with the foundational skills needed to excel in research design within the social sciences.

The grading structure will consist of the following components:

1. Two problem sets (5% each, individual assessment).
2. Group Project Presentation (40%): Collaborative creation and presentation of an original research paper by a group of five students during the final four sessions of the course. For projects involving an online survey experiments, surveys or other type of data, students must also submit a paper formatted as short scientific report including the manuscript text (background, methods results, discussion), title page, abstract, figure legends, and max 15 references). Alternatively, groups can  opt for a Systematic Review that should adhere to PRISMA guidelines. SR can be compelemented with a meta-analysis. Any type of paper should not exceed 3000 words.

3. Final written exam: A one-hour examination comprising multiple-choice questions and open-ended questions, accounting for 50% of the total grade.

Students' assessment in this course will encompass three key elements to gauge their overall understanding of the content:

1. Comprehensive grasp of essential research methodologies with big data.
2. Proficiency in conducting basic data analysis using common softwares.
3. Development of an original research paper for presentation in class.

Each of these components evaluates distinct competencies and equips students with the foundational skills needed to excel in research design within the social sciences.

The grading structure will consist of the following 2 components:

1. Individual Project Presentation (50%): Creation and presentation of an original research. For projects involving an online survey experiments, surveys or other type of daya,  data, students must also submit a paper formatted as short scientific report including the manuscript text (backround, methods results, cdiscussion), title page, abstract, figure legends, and max 15 references). Alternatively, individual students can  opt for a Systematic Review that should adhere to PRISMA guidelines.If appropriate, SR can be compelemented with a meta-analysis. Papers should not exceeding 3,000 words, excluding references.

Individual papers should be send to the instructor one week before the date of the exam.

2. Final written exam: A one-hour examination comprising multiple-choice questions and open-ended questions, accounting for 50% of the total grade.

Part of the reading material for this course can by found in Salganik MJ Bit By Bit (Social Research in the digital age). In addition we will use books' chapters, articles and web sources. The list of readings will be available in the syllabus. They will be downloadable from Blackboard or through links in the syllabus