MGT-618 / 4 crédits

Enseignant: Younge Kenneth

Langue: Anglais

Remark: Schedule: Nov 3, Nov 10, Nov 17, Nov 24, Dec 1, Dec 8, Dec 15 Wednesdays: 9:15 – 12:00


Frequency

Every year

Summary

The objective of this course is to introduce doctoral students to computational methods for data-driven research in the social sciences.

Content

Note

Download the complete syllabus from the "Teaching" section of the Chair for Technology and innovation Strategy:

https://www.epfl.ch/labs/tis/teaching/

Keywords

Data Processing, Visualization, Cloud Computing, Data Analysis, Text Analysis, Simulation, Machine Learning.

Learning Prerequisites

Important concepts to start the course

1. Statistics:

This course requires a basic understanding of Generalized Linear Models such as Ordinary Least Squares (OLS), the Logit Model, and the Poisson Model. You need to have taken a graduate-level course in statistics, or otherwise have sufficient probability theory and optimization theory to understand OLS, MLE, and basic statistics.


2. Python:

This course requires you to program in Python. If you do not know how to program in Python, then you must take a self-directed, online course in Python before the start of this course.

For students new to programming, we recommend the JetBrains Academy track on Python (https://hi.hyperskill.org). This course takes about 34 hours to complete and will prepare an
absolute beginner up to the level required for this course. The JetBrains course also presents the material in interactive, bite-sized exercises, and provides powerful tools to track the concepts you have studied (https://hyperskill.org/knowledge-map), which are helpful for beginners.

For students with experience in programming, but who are new to Python, we recommend the Kaggle course: https://www.kaggle.com/learn/python. The course takes ~ 7 hours to complete.


For students already familiar with Python, we recommend you prepare with advanced training on “Pandas” by taking the following Kaggle course: https://www.kaggle.com/learn/pandas.

Assessment methods

70% Assignments:

Students must complete seven take-home assignments, each worth 10% of the overall grade. Each assignment should take around five hours to complete and is due before the start of the next class. The final assignment is due one week after the final class.


30% Project:

Students should also complete an individual, self-directed semester project worth 30% of the overall grade. The self-directed project should take around 15 hours to complete and is due 6 weeks after the last class. Ideally, the project will complement other aspects of your doctoral research and use real data.

Dans les plans d'études

  • Forme de l'examen: Pendant le semestre (session libre)
  • Matière examinée: Computational research methods for social sciences
  • Cours: 56 Heure(s)

Semaine de référence