Statistics / L3-M1 level / HEC Paris 

This course introduces business students (with a limited or non-existing mathematical background) to basic notions of inferential statistics, including: confidence intervals, one-sample and two-sample tests, chi-square tests, and simple and multiple linear regression (without residual analysis). I have been designing and teaching it since September 2007; in particular, I wrote the textbook and created dozens of cases, some based on real data. 

Matériel de cours en français (mise à jour : été 2024)
Polycopié 

Course material in English (last updated: summer 2022)
Textbook (condensed course + statements of the exercices)
Corrections of the exercices (alas, handwritten ones)
 

Data science with Python / M1 level / HEC Paris 

12 sessions of 1h30, with a focus on data sets and ethics

Notebooks written in Fall 2024
Basics of exploratory data analysis [EDA] = session 1 + session 2 + session 3
Two case studies in EDA = session 4 + session 5
Mid-term examen (in French) = session 6 
Classification = session 7 + session 8
Regression = session 9 + session 10
Clustering = session 11 
Mock exam (in French) = session 12 

 

Material of selected past courses 

Learning and sequential optimization (M2 level)
Université Paris-Saclay, years 2016 to 2022, about 20h every year 
This is the material of the last edition
- Homework #1 (due March 4) -- Exercise 1 and instructions, Exercise 2, Exercise 3, Exercise 4, Exercise 5
- Homework #2 (due April 1) -- Exercise 1 and instructions, Exercise 2, Exercise 3, Exercise 4, Problem
- Lecture notes #1 = lecture notes + corrections of the exercises 
- Lecture notes #2 = lecture notes + corrections of the exercises  
- Lecture notes #3 = lecture notes + corrections of the exercises  
- Lecture notes #4 = lecture notes + corrections of the exercises
- Lecture notes #5 -= lecture notes + corrections of the exercises + some complements 
- Lecture notes #6 = lecture notes (with no exercise statement) + some complements 

Lower bounds in sequential learning (M2 level)
ENSAE ParisTech, January 2017 within 'offre de formation par la recherche'
Lecture notes (2h30-long sessions) : session #1, session #2, session #3, session #4 

Mesure, intégration et probabilités, travaux dirigés (niveau L3) 
Ecole normale supérieure, année 2004-05 : énoncés compilés + corrigés compilés 

Probabilités et statistique illustrées avec Matlab, travaux pratiques (niveau M1)
Université Paris-Sud, année 2003-04 
TP1 (prise en main de Matlab et quelques exercices élémentaires), TP2 (convergence de variables aléatoires, théorèmes limite, méthodes de Monte-Carlo), TP3 (simulation de variables aléatoires), TP4 (chaînes de Markov), TP5 (tests statistiques)
Sujet d'examen et corrigé (dont un exercice sur le processus de Galton-Watson), oral de rattrapage