Bayesian econometrics


General linear and hierarchical models

General linear models models

· Hetekoskedasticity example

· Student-t errors example

· Autoregressive errors example

Seemingly Unrelated Regression (SUR) Model ( R code for Grunfeld’s data (Zellner, 971) + (Grunfeld’s data)

Hierarchical linear models


Linear regression, general covariance and SUR

· Linear regression with general covariance matrix (Koop, chapter 6)

  • o Heteroskedasticity of known form (Koop, section 6.3)
  • o Student’s t errors (Koop, section 6.4)
  • o Autocorrelated errors (Koop, section 6.5)

· Seemingly unrelated regression (Koop, section 6.6 and Zellner, section 8.5)


Hierarchical models/panel data

· Pooled model

· Individual effects with (i) non-hierarchical and (ii) hierarchical priors

· Random coefficients model

· Koop, chapter 7, and Lancaster, section 7.3

· Example: cost of airline companies (R code and dataset)

· WinBUGS and R2WinBUGS


A few additional references

· Zellner (1971) An Introduction to Bayesian Inference and Econometrics, Wiley.

· Koop (2003) Bayesian Econometrics, Wiley.

· Lancaster (2004) An Introduction to Modern Bayesian Econometrics, Blackwell Publishing.

· Meyer, R., and R.B. Millar (1999): BUGS in Bayesian Stock Assessments. Can. J. Fish. Aquat. Sci., 56, 1078-1087.

· Meyer, R., and R.B. Millar (1999): BUGS for Bayesian State-Space Modeling. In: Statistical Modeling, (H. Friedl and G.Goeran Eds.), 588-592.

· Meyer, R., and J.Yu (2000): BUGS for a Bayesian analysis of stochastic volatility models. The Econometrics Journal, 3(2), 198-215.

· Griffin, J. and Steel, M. (2005) Bayesian Stochastic Frontier Analysis Using WinBUGS .

· Manda, S.O.M., Meyer, R. (2005) WinBUGS code for Gibbs sampling to estimate parameters for a three-level discrete time to event model. J. R. Statist. Soc. A. 168.