Facebook pixel
Info
Foto sezione
Logo Bocconi

Course 2023-2024 a.y.

20886 - FOUNDATIONS OF SOCIAL SCIENCES - MODULE I (EMPIRICAL RESEARCH METHODS AND DATA ANALYSIS)

DES-ESS
Department of Social and Political Sciences

Course taught in English

Go to class group/s: 20 - 21

DES-ESS (6 credits - I sem. - OB  |  SECS-P/07)
Course Director:
GIOVANNI FATTORE

Classes: 20 (I sem.) - 21 (I sem.)
Instructors:
Class 20: GIOVANNI FATTORE, Class 21: GIOVANNI FATTORE


Synchronous Blended: Lessons in synchronous mode in the classroom (for a maximum of one hour per credit in remote mode)

Mission & Content Summary
MISSION

This intermediate level course introduces students to empirical methods in economics and social sciences in general. The overall objective of the course is to provide students with an understanding of the foundational empirical methods and research designs used by social scientists. It also intends to familiarise students with the opportunities and challenges for social scientists in the digital era by providing an overview of the emerging big data techniques used in current social science research. This is an applied course; it systematically refers to scientific publications and equips students with the necessary introductory knowledge to perform state-of-the-art data analysis. Being at the first semester of the MSc program and with students with heterogeneous previous knowledge of statistics/econometrics, the course aims at providing overview and intuition for different methods which students will be able to pursue in further compulsory and elective methods courses. An understanding of the basics of probability theory and statistical analysis is required for this course.

CONTENT SUMMARY

Part 1. Main analytical approaches and principles of causal interference:

Economics, Social Sciences and Big Data

Systematic reviews and meta-analysis

Validity of research designs

The counterfactual model

Randomization and its discontents

Surveys

Instrumental variables

Regression discontinuity design

Difference-in-differences design

Social Network Analysis
 

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

Introduction to machine learning

Big data analytics

Data retrieval

Finding patterns in big data

Data reduction

Model fit and validity

Text as data

Large language models


Intended Learning Outcomes (ILO)
KNOWLEDGE AND UNDERSTANDING
At the end of the course student will be able to...
  • To be familiar with a scientific approach to conduct literature reviews
  • To master the main research designs in economics and other social sciences
  • To understand research question, the content and the methods of scientific papers
  • To understand the opportunity and challenges of social science research in the digital age
APPLYING KNOWLEDGE AND UNDERSTANDING
At the end of the course student will be able to...
  • To be able to produce their own research design by the identification of scientific research questions and the selection of the most appropriate method to answers to these questions.
  • To work with data and to apprehend the basics of machine learning
  • To learn how to work in groups and to write a short research project 

Teaching methods
  • Face-to-face lectures
  • Exercises (exercises, database, software etc.)
  • Group assignments
DETAILS

Students will be asked to work in group to develop a research question and answer it with appropriate data and data analysis techniques (see Assessment for details). The presentations in class give the opportunity to think of your own and be exposed to a variety of research designs and methods in the social sciences in general and in economics in particular. Collaboration between peers also offers the opportunity to foster creativity, acquire presentation skills, learn from peers, and understand the criteria used to assess research proposals in scientific international settings.

 

20886 - FSS promotes a flexible, ‘problem-based’ approached to the choice of the computing environment. This is not a coding class so students should not expect to learn coding during the class, however, activities and methods covered during the class will make use of statistical and programming software. Some activities will involve coding in either R or Python. Students are welcome to use other languages that may allow them to efficiently solve problems, but we cannot guarantee that we can support them. Students are required to install a modern, stable-release version of R and RStudio, as well as Anaconda with Python 3.10 and make sure it is running. The instructors will provide code and data that illustrate the application of specific methods, and TA support will be provided throughout the course.


Assessment methods
  Continuous assessment Partial exams General exam
  • Written individual exam (traditional/online)
  •     x
  • Group assignment (report, exercise, presentation, project work etc.)
  •     x
  • Mid-term assignment developing an original susrvey instrument
  • x    
    ATTENDING STUDENTS

    Students' assessment will be based on three elements to assess the overall comprehension of the content of the course: a) testing that they fully understand the essential approaches of research methods, b) developing a short survey; c) conceptualizing an original research paper to be presented in class. Each of these elements tests different competences and provides students with the essential approaches to master research design in the social sciences

     

    The grading will be composed of three elements:

    Mid-term assignment (10%): Develop an original survey instrument (not graded; max grade obtained if submitted)

     

    Group Project Presentation (40%): Develop and original research paper presented by 5 students in the last four sessions of the course. Students are also required to submit the paper in the style of a PNAS Brief Report, using one or more of the methods and techniques covered in class. PNAS Brief Reports are limited to 3 pages, which is approximately 1,600 words including the manuscript text, title page, abstract, and figure legends, and 15 references (https://www.pnas.org/author-center/submitting-your-manuscript)

     

    Final written exam. One-hour exam with multiple choice and one opened ended question (50%).

    NOT ATTENDING STUDENTS

    Final written exam. One-hour exam with multiple choice and one open-ended question (50%.) Individual research paper (50%), in the style of a PNAS Brief Report, using one or more of the methods and techniques covered in class. PNAS Brief Reports are limited to 3 pages, which is approximately 1,600 words including the manuscript text, title page, abstract, and figure legends, and 15 references (https://www.pnas.org/author-center/submitting-your-manuscript


    Teaching materials
    ATTENDING AND NOT ATTENDING STUDENTS

    The list of readings will be made available in the syllabus

     

    For the first part of the course two textbooks cover most of the material

    Agrist JD % Pischke J-S. Mastering metrics. The path from cause to effects. Princeton University Press. (more basic)

    Cunningham S. Causal Inference. The Mixtape (https://mixtape.scunning.com)

    Last change 23/05/2023 14:39