Spring School 2014 short course: 'Bayesian Hierarchical Models for Social Research'

Description:

The Spring School Short course for 2014, 'Bayesian Hierarchical Models for Social Research', will run for three days, Monday 23 June to Wednesday 25 June. Location: Department of Politics & International Relations, Manor Road Building, Oxford.

Course Tutor: Professor Jeff Gill (Washington University in St. Louis).

ABSTRACT:
This course covers statistical model development with explicitly defined hierarchies from a Bayesian perspective.  We will concentrate on specifications that allow researchers to account for different structures in the data and to provide for the modeling of variation between groups.
The emphasis is on generalized linear models using multiple nested and non-nested hierarchies. The course will be practical and applied, with steps for specifying, fitting, and checking multilevel models.
Significant time will be spent on the details of computation in the BUGS environment.

SCHEDULE:
Day 1: introduction to Bayesian inference, Bayesian linear models Day 2: introduction to MCMC, Bayesian hierarchical models Day 3: introduction to JAGS, specifying multilevel models in JAGS

COMPETENCIES:
At the conclusion of this course participants will: be able to specify and estimate Bayesian multilevel (hierarchical) models with linear and nonlinear outcomes, treat missing data in a principled and correct manner using multiple imputation, gain facility in the bugs statistical language, know how to compute the appropriate sample size and power calculations for multilevel models, gain exposure to Bayesian approaches including MCMC computation, and be able to assess model reliability and fit in complex models.

BIOGRAPHY:
Jeff Gill (Professor of Political Science, Professor of Biostatistics, Professor of Surgery) does extensive work in the development of Bayesian hierarchical models, nonparametric Bayesian models, elicited prior development from expert interviews, as well in fundamental issues in statistical inference.  He has extensive expertise in statistical computing, Markov chain Monte Carlo (MCMC) tools in particular.  Most sophisticated Bayesian models for the social or medical sciences require complex, compute-intensive tools such as MCMC to efficiently estimate parameters of interest, and he concentrates these statistical and computational techniques.  Current theoretical work builds on prior applied work to develop new hybrid algorithms for statistical estimation with multilevel specifications and complex time-series and spatial relationships.  Current applied work includes:
energetics and cancer, long-term mental health outcomes from children's exposure to war, pediatric head trauma, analysis of mouse models, molecular models of sickle cell disease, models of bureaucracy, and spatial specifications of ideology and attitudes.

Course Fee: £300 (Members of Academic Institutions) £480 (Members of Non-Academic Institutions)

Online registration is now open.

Cost:

£300 (Members of Academic Institutions) £480 (Members of Non-Academic Institutions)

Website and registration:

http://springschool.politics.ox.ac.uk/courses/2014/ss_short_June14.asp

Region:

South East

Keywords:

Quantitative Data Handling and Data Analysis, Statistical Theory and Methods of Inference, Multilevel Modelling , Modelling of variation between groups

Related publications and presentations:

Quantitative Data Handling and Data Analysis
Statistical Theory and Methods of Inference
Multilevel Modelling

Back to archive...