Objectifs :
• Understand the Bayesian framework and its advantages
• Specify, fit, and interpret hierarchical and mixed Bayesian models
• Incorporate spatial and temporal dependencies into models
• Evaluate, compare, and validate Bayesian models
• Understand and apply ensemble modelling approaches
• Apply Bayesian tools to own research data
• Report results transparently and reproducibly

Programme :
• THEORETICAL BACKGROUND AND INTRODUCTION TO THE BAYESIAN FRAMEWORK
• FITTING AND INTERPRETING BAYESIAN MIXED EFFECT MODELS
• SPACE AND TIME MODELLING CONCEPTS AND APPROACHES IN THE BAYESIAN FRAMEWORK
• FITTING AND EVALUATION MODELS WITH EXPLICIT SPACE AND/OR TIME COMPONENTS
• INTRODUCTION TO ENSEMBLE MODELLING METHODS WITH A FOCUS ON THE BAYESIAN MODEL AVERAGE
• APPLY AND EVALUATE BAYESIAN MODEL AVERAGE ON REAL-WORLD MODELS

Pré-requis :
BASIC STATISTICAL CONCEPTS (MEANS, CORRELATION, DISTRIBUTIONS, PROBABILITY) AND TOOLS (REGRESSION, CORRELATION)
KNOWLEDGE OF AT LEAST ONE PROGRAMMING SOFTWARE (R, PYTHON …)

Méthode pédagogique :
SHORT PRESENTATIONS OUTLINING THE MAJOR CONCEPTUAL KNOWLEDGE NEEDED
SIMULATED AND REAL-WORLD CASE STUDIES
LIVE CODING SESSION (R AND PYTHON)
HANDS-ON PRACTICAL WORK IN SMALL GROUPS

La formation participe à l'objectif suivant :être directement utile pour la réalisation des travaux personnels de recherche