UNIL MSc course: Data Science 2025
Introduction This course is for MSc students from the Medical Biology (MB) master program. The goal is to review fundamental notions in statistics and show how they are useful for basic data analysis challenges in biology and medicine.
Prerequisites Students who follow this course should already have some basic knowledge in statistics and R equivalent to the one achieved by bachelor students at the University of Lausanne.
Resources The following software is required for this course:
- a recent version of R (in doubt, simply download and install the latest version from the R website at https://stat.ethz.ch/CRAN/ -- many potential problems are solved by simply upgrading to the latest R version)
- RStudio (which you can download from http://www.rstudio.com/products/rstudio/download/)
- Introduction video "R programming for ABSOLUTE beginners": https://youtu.be/FY8BISK5DpM
Schedule and content This course includes four 2h frontal lectures:
- 24.02.2025 8:15-10:00 Basic notions of probability theory, Central Limit Theorem (Slides)
- 25.02.2025 8:15-10:00 Important distributions and tests, sampling and estimates (Slides)
- 26.02.2025 8:15-10:00 Introduction to linear regression (Slides)
- 27.02.2025 8:15-09:00 Multiple-choice test of understanding for lectures 1-3
- 27.02.2025 9:15-12:00 Work on Exercises 1-3
- 28.02.2025 8:15-10:00 Introduction to generalised linear models (Slides)
Exercises To practise there will be four exercise sessions - one for each lecture. These sessions take place from 10:15 to 12:00 (except for Thursday: 9:15-12:00, see below). Each session is thematically linked to the morning lecture on the same day. There will be assistants to help students with practical questions.
Grades This course has no oral or written exam; instead students are given a multiple-choice test of understanding for lectures 1-3 on 27.2.2025 8:15-9:00. The test has 13 questions with possible answers each. No external help (laptops/phones) are permitted. To pass the test students must have at least 75% of their answers correct.