Course objective: This course introduces the fundamental concepts of statistical learning, with a focus on building classification models starting from logistic regression. It covers key methodological aspects, including maximum likelihood estimation, statistical tests for assessing the significance of predictors, and strategies for selecting the most relevant subset of explanatory variables. Participants will also learn how to use the model to predict class labels and evaluate classification performance using appropriate metrics.
Organization: The course is structured into five sessions, each comprising a lecture and a practical component. During the in-class practical sessions, students engage in hands-on problem-solving exercises using R, allowing them to apply the concepts introduced in the lectures.
The following documents are provided for each session:
Past exams:
To start with Rmarkdown: brief introduction.
Objective: A post on the blog of a French radio channel reports that the risk of being infected by COVID19 is 33% lower in people with blood type O. What does this assertion means?
The session introduces a statistical method to compare groups of items regarding their exposition to a given risk.
Objective: How to use colorimetry to evaluate the maturity of a fruit? The session introduces a mathematical framework and related statistical methods to address this issue.
Objective: Are the components of a colorimetry profile all equally important to predict the maturity of a fruit? The session introduces the test for the significance of effects in the general setup for modeling class probabilities introduced in Session 2.
Objective: How to choose the best subset of explanatory variables to explain class probabilities in a large profile of possibly correlated features?