Learn probabilistic programming, how to build and apply Bayesian statistical models, and provide statistical support to researchers and professionals.
- The process and limitations of statistical inference (experiment design, data gathering, model selection, computation, interpretation, what can and can’t we claim …).
- Probabilistic thinking.
- Probabilistic programming and Stan basics.
- General linear models (GLM), regularization.
- Survey sampling.
- Hierarchical (multilevel) models.
- Questionnaire design.
- Choosing priors and eliciting probabilities from experts.
- Objective/subjective Bayesian statistics.
- Time series models (seasonality, trends, AR, MA, ARMA, ARIMA).
- Model evaluation and selection.
- Modelling censored data (survivability, reliability).
- Hamiltonian Monte Carlo (HMC), No U-Turn Sampler (NUTS), advanced Markov Chain Monte Carlo (MCMC) diagnostics.
- Combining models.
- Hands on work and projects.
- nosilec: Jure Demšar
- nosilec: Erik Štrumbelj