This subject extends the investigation of modern statistical modelling techniques initiated in Statistical Learning and Regression Models. Topics include models for correlated data including spatial and mixed-effects models, as well as Bayesian hierarchical models including discussion of Markov chain Monte Carlo (MCMC) techniques for calculating posterior estimates, and modern applied re-sampling methods for developing robust measures of model accuracy. The programming language R will be used in this subject.
|Faculty||Bond Business School|
1. Demonstrate knowledge of the statistical issues associated with correlated data and random effects.
2. Evaluate and choose between a variety of advanced statistical model structures.
3. Diagnose key aspects of data structures to assess the need for correlational(?) or hierarchical structure.
4. Apply the Bayesian modelling framework, including the use of Markov chain Monte Carlo techniques to find posterior estimates.
5. Apply resampling methods to develop robust measures of model accuracy.
6. Explain the meaning and importance of the results of statistical models with random effects and hierarchical structure.
There are no co-requisites.
Future offerings not yet planned.