Install this application on your home screen for quick and easy access when you’re on the go.
Just tap then “Add to Home Screen”
Install this application on your home screen for quick and easy access when you’re on the go.
Just tap then “Add to Home Screen”
Member rate £492.50
Non-Member rate £985.00
Save £45 Loyalty discount applied automatically*
Save 5% on each additional course booked
*If you attended our Methods School in Summer/Winter 2024.
Monday 5 to Friday 9 March 2018
09:00-12:30
15 hours over 5 days
Political scientists increasingly apply the Bayesian approach to diverse kinds of research topics. To motivate further political scientists to use this approach, this course provides participants the following three points: First, the course provides a conceptual background for Bayesian inference. Second, participants will be guided how to read the literature using Bayesian statistics and interpret the results. Third, this course introduces to a software for Bayesian analysis with political science examples. The course consists of lectures (morning) and lab sessions (afternoon). The lecture deals with relevant background knowledge as well as specific skills for Bayesian analysis. In lab sessions, these skills are applied to political and social science data. Hence, course participants also learn the basic knowledge of JAGS, which is needed to conduct Bayesian estimation.
Tasks for ECTS Credits
For 2 ECTS, you have to successfully submit daily assignments.
For 3 ECTS, you have to successfully submit daily assignments and a short take home exam.
For 4 ECTS, you have to successfully submit daily assignments and a long take home exam.
Susumu Shikano is Professor of Political Methodology at the University of Konstanz. His research interests are spatial models of politics and various topics in political behaviour.
His work has appeared in journals including Public Choice, Political Psychology, Party Politics, West European Politics, and the British Journal of Political Science.
Political scientists increasingly apply the Bayesian approach to diverse kinds of research topics. This development is due to a series of its attractive features: e.g. handling aggregate data without sampling processes, analysing small N data, estimating models with complex likelihood functions. Furthermore, the increasing capacity of modern computers enables a wider range of researchers to conduct such computationally intensive estimations.
Despite of these advantages there is still backlog demand in respect to several points: First, it is not enough acknowledged that Bayesian statistics and conventional statistics are based on different views concerning theory and data. Second, the literature, including text books, is in general too technical to motivate most political scientists to apply Bayesian analysis to their own research questions. Third, the programs needed for Bayesian analysis is not user friendly enough for most political scientists.
The course aims to close these gaps. First, the course provides a conceptual background for Bayesian analysis. Second, participants will be guided how to read the literature using Bayesian statistics and interpret the results. Third, this course introduces to a specific software for Bayesian analysis with political science examples.
More specifically, the course covers the following topics: Fundamentals of Bayesian analysis, estimation of linear regression models using conjugacy and Markov Chain Monte Carlo (MCMC), estimation of various regression models (binary logit/probit, poisson, multi-level, robust regression etc.) in Bayesian framework. The course consists of lectures and lab sessions. The lecture deals with relevant background knowledge as well as specific skills for Bayesian analysis. In lab sessions, these skills are applied to political and social science data. Hence, course participants also learn the basic knowledge of JAGS, which enables to conduct Bayesian estimation using MCMC.
Participants are required to have knowledge in statistical analysis including regression models with different types of dependent variables. Further, they are also required to have knowledge about maximum likelihood estimation (MLE). At least, participants have to know how to calculate the likelihood of certain parameter sets of a statistical model given observed data. In lab sessions participants learn how to use JAGS from R. Therefore, the basic knowledge in R is also required.
Note that this is an introductory one week course. This course, therefore, cannot thoroughly treat the wide range of statistical models and further advanced topics in Bayesian statistics. For those who have basic knowledge in Bayesian statistics and can conduct regression analysis using JAGS, this course is not adequate.
Prior knowledge of statistics including regression models with different types of dependent variables. Knowledge about maximum likelihood estimation (MLE), in particular the participants should be able to distinguish likelihood . Basic knowledge of R.
Day | Topic | Details |
---|---|---|
1 | General introduction, Basics of Bayesian inference, Conjugacy analysis, Markov-Chain-Monte-Carlo |
3 hour lecture |
2 | Introduction to JAGS. Linear and discrete regression models |
3 hour lab session |
3 | Regression models for discrete dependent variables |
1.5 hours lecture, 1.5 hours lab time on R programming |
4 | Further advanced topics (model selection, Bayes factor, model averaging and data augmentation) |
1.5 hour lecture, 1.5 hour lab time on R programming |
5 | Bayesian multilevel models | |
3 | Advanced regression models |
1.5 hours lecture, 1.5 hours lab time on R programming |
Day | Readings |
---|---|
1 |
Shikano (2014), Jackman (2009) Chapter 1-2 |
2 |
Shikano (2014), Jackman (2009) Chapter 4 |
3 |
Shikano (2014), Jackman (2009) Chapter 5 |
4 |
Jackman (2009) Chapters 1 and 7 |
5 |
Gelman & Hill (2007) |
R - free from http://cran.r-project.org/
JAGS - free from http://mcmc-jags.sourceforge.net/
Students bring their own laptops.
Shikano, Susumu, Bayesian estimation of regression models, Henning Best and Christof Wolf, eds. Regression Analysis and Causal Inference, Sage, 2014; p.31-54
Jackman, S. Bayesian Analysis for the Social Sciences. Wiley: New York. 2009.
Gelman, Andew and Hill, Jennifer. Data Analysis using Regression and Multilevel/Hierarchical Models. Cambridge University Press; 2007.
Summer School
Introduction to R
Event History and Survival Analysis
Advanced Topics in Applied Regression Multiple Regression
Multiple Regression
Winter School
Introduction to Statistics
Introduction to R
Summer School
Advanced Discrete Choice Modelling
Panel Data Analysis
Handling missing data
Winter School
Advanced Discrete Choice Modelling
Panel Data Analysis
Handling missing data