ANLY 505 - Data Simulation, Bayesian Modeling, and Inference

(3 semester hours)
Prerequisites: ANLY 500
Description: This course covers the basic principles of statistical modeling and inference. The course focuses on developing and fitting several types of regression models, multilevel models, and everything in between. Topics included in the class cover, prior predictive simulation, sampling from the posterior, interaction terms, covariance, information criteria, and Markov Chain Monte Carlo estimation. The course also covers measurement error, missing data, and Gaussian process models for spatial and network autocorrelation. This course outlines step-by-step calculations that would normally be automated in the modeling process. This approach ensures that the student understands the details of statistical modeling in order to make reasonable choices and interpretations of their own modeling work. The class utilizes interdisciplinary source material, Program R, and easy to understand metaphors to develop and interpret statistical models. The course’s emphasis is on how Bayesian data analysis can be used for causal inference and predicting new data.