Analyse BayésienneOutils du Management de la Qualité 2 (ERE)
Bayesian Analysis
Séquencement
Learning objectives
Master: • Basic Concepts of Bayesian Decision Theory • Traditional methods of analysis and data classification • Concepts of machine learning by Bayesian models Recognize: The tools of Bayesian theory to apply them to data analysis
Prerequisites
| Module | Teaching unit | Semester |
|---|---|---|
| Mathematical Tools 1 | Fundamental Sciences 1 | S5 |
| Mathematical Tools 2 | Fundamental Sciences 2 | S6 |
Program
From frequent inference to Bayesian inference • Frequent inference - Pre-experimental approach Construction of confidence interval Hypothesis test • Bayesian Inference - Post-experimental approach o Hypothesis Test Principles of Bayesian Inference • Bayes' theorem in discrete and continuous • Bayesian approach to operational safety The different types of a priori - Construction of a priori Interpretation of ex post facto Bayes Decision Theory • Rules of decision • Errors on models • Bayesian cost and risk functions Functions of discrimination • Uniform models • Multivariate models • Linear and non-linear separation functions Calculation of Bayesian models • Maximum likelihood method • Bayesian estimate Bayesian networks • Graphic models • Concepts of independence • Inference in Bayesian networks
Assessment
Table control (Duration 1h)
Skills
1| Ref. | Verb | Description | Level |
|---|---|---|---|
| C9 | analyze | Structure continuous progress of processes, equipment or technologies | 3 |