DAMSL-103 BAYESIAN Statistics

Syllabus

• Belief, Probability and Exchangeability
• One Parameter Models
• Monte Carlo Approximation
• The Normal Model
• Gibbs Sampling
• Multivariate Normal Model
• Hierarchical Modeling
• Linear Regression
• Metropolis Hastings
• Binomial and Poisson Regression

Learning Outcomes

Upon successful completion of this course students will be able to

• Compute Bayesian estimates for a wide variety of statistical models, using R software.
• Knowledge of fundamental sampling algorithms for performing posterior inference based on alternative prior distributions.
• Computer implementation using real and synthetic data.
• Applied problem solving using Bayesian statistical methodologies.