Bayesian modeling

Summary

 * Q: How do we approach realistic systems as a Bayesian? How do we reason about causality and independence in such systems? How do we compute posteriors in such systems?
 * Ideas:


 * Graphical models
 * Causality
 * MCMC
 * Exercises:


 * Build causal models for informally specified systems
 * Conceptual problems on independence/causality

Logistics

 * Time: rough guess ~1.5 hours [Paul]
 * Teacher: probably Jacob
 * Relations:


 * Requires Bayes
 * Pairs with qualitative/quantitative Bayes units as wells

Outline
None yet.

Notes

 * <span style="font-size: 15px; font-family: Arial; color: rgb(0, 0, 0); font-weight: normal; font-style: normal; font-variant: normal; text-decoration: none; vertical-align: baseline;">Implicitly pretty grouped with basic Bayes unit. [Paul]
 * I think this should probably be split into a unit on modeling and a unit on inference, if possible. [Jacob]