Mener une étude statistique dans un domaine d'application

Course Overview

This course places students in a real-world statistical study context within a specific sector of activity (healthcare, marketing, insurance, quality control, demography, sociology, etc.). Starting from data provided by a client, students implement all steps of a complete data analysis.

Students will:

• Understand and translate the client’s needs into a statistical analysis framework
• Clean and prepare data for quality results
• Apply descriptive (univariate, bivariate, multivariate) and modelling methods
• Communicate results through reports, presentations and critical analysis

Target Skills

• Model data in a statistical framework
• Process data for decision-making purposes
• Statistically analyse data
• Valorise a production in a professional context

Critical Learning Outcomes

• AC31.01

  Identify technological solutions for data collection and dissemination

• AC32.01

  Choose appropriate statistical tools

• AC32.02

  Apply methods adapted to specific domains (Marketing, Biostatistics, Spatial Statistics)

• AC33.03

  Identify keys to good communication

• AC34.01EMS

  Understand statistical approaches for data validation and reliability

Years Taught

2023–2024, 2024–2025, 2025–2026 - name: Review Materials url: /assets/pdf/example_pdf.pdf

• week: 6 date: Oct 10 topic: Midterm Exam description: Covers weeks 1-5.

• week: 7 date: Oct 17 topic: Neural Networks Fundamentals description: Perceptrons, multilayer networks, and backpropagation. materials:
  • name: Lecture Notes url: /assets/pdf/example_pdf.pdf
  • name: Assignment 3 url: /assets/pdf/example_pdf.pdf
• week: 8 date: Oct 24 topic: Deep Learning description: Convolutional neural networks, recurrent neural networks, and applications. materials:
  • name: Lecture Notes url: /assets/pdf/example_pdf.pdf
  • name: Coding Lab url: https://github.com/ —

Course Overview

This introductory course on machine learning covers fundamental concepts and algorithms in the field. By the end of this course, students will be able to:

• Understand key machine learning paradigms and concepts
• Implement basic machine learning algorithms
• Evaluate and compare model performance
• Apply machine learning techniques to real-world problems

Prerequisites

• Basic knowledge of linear algebra and calculus
• Programming experience in Python
• Probability and statistics fundamentals

Textbooks

• Primary: “Machine Learning: A Probabilistic Perspective” by Kevin Murphy
• Reference: “Pattern Recognition and Machine Learning” by Christopher Bishop

Grading

• Assignments: 40%
• Midterm Exam: 20%
• Final Project: 30%
• Participation: 10%

Schedule

Week	Date	Topic	Materials
1		Compréhension du besoin commanditaire Identifier les variables d’intérêt, la population d’étude et les enjeux de l’étude statistique.
2		Collecte et nettoyage des données Mise en œuvre des méthodes de collecte de données et nettoyage pour la qualité des résultats.
3		Statistiques descriptives univariées et bivariées Analyse exploratoire des données, sélection de variables pertinentes.
4		Méthodes de modélisation statistique Modélisation à des fins de prévision, sélection du modèle le plus adapté.
5		Statistiques multivariées Méthodes avancées d’analyse de données multivariées.
6		Valorisation des résultats Rapport d’étude, document de synthèse, présentation orale et approche critique des biais.