MASTER CLASS IN ECONOMETRICS - BAYESIAN MODELLING AND INFERENCE
Dr. Melvyn Weeks, Fellow of Clare College, University of Cambridge
Location: Clare College, University of Cambridge, Cambridge
Duration: 2 days (23rd March 2016 - 24th March 2016)
This course will provide an introduction to Bayesian methods for
empirical analysis. The course covers a mix of theory and applications.
We will start with a number of theoretical issues including
exchangeability, prior-posterior analysis, model comparison and
hypothesis testing, and models for missing data. We will also examine
the fundamental problem of prior elicitation.
We present the basic ideas behind Monte Carlo integration and
demonstrate the use of these techniques in both maximising a likelihood
and sampling from a posterior distribution. We will examine the
fundamentals of MCMC from both a theoretical and applied setting. We
provide a brief introduction to simple Accept-Reject sampling methods,
moving onto the Gibbs sampler and Metropolis- Hastings.
Applications will be taken from medical statistics, economics, treatment
models, and consumer heterogeneity in marketing applications. In each
case we consider the particular advantages of a Bayesian approach, how
to implement, and how data augmentation can be a useful tool in
designing a posterior simulators.
Practical sessions will be provided using both Python and Stata.
Students will have access to a fully functional computational
environment for both Python and Stata. Instruction on how to access this
will be provided during the first session.
It's a great course, great location and something for both the novice
and those with some previous exposure to Bayesian Modelling
Hope to see you there!
Melvyn
You may leave the list at any time by sending the command
SIGNOFF allstat
to [log in to unmask], leaving the subject line blank.
|