TGM AL MAMUN
Empirical Research Guide · Bayesian Econometrics

Which Bayesian model fits your data?

The right Bayesian model depends on the structure of your data and on what the tests find, not on preference. Test a real dataset, upload your own, or enter your test results, and follow the decision tree to the model your paper needs.

5 real example datasetsTests run in your browserPython · statsmodels

Choose a dataset

Five real datasets. Each one leads to a different model, and the decision tree shows why.

Method guides

Routes to a finished paper

Each guide takes one real dataset through pre-estimation tests, estimation, diagnostics, robustness and sample text for the paper, with Python code and real output.

How the tool decides. Panels go to the panel VAR; a regression equation to Bayesian regression; a series observed at mixed frequencies to the mixed-frequency BVAR; 15 or more indicators to the FAVAR. For a set of macro series the tool checks whether the series are stationary and, if they are not I(1) in levels, tests three kinds of nonlinearity on a VAR(1): changing volatility (variance ratio, Levene and ARCH tests), unstable coefficients (CUSUM and sup-F) and a threshold (a bootstrap sup-LR test). The strongest rejection (p < 0.01 for volatility, p < 0.05 for the others) decides between the stochastic-volatility, time-varying-parameter and threshold VAR; if none rejects, a constant-parameter Bayesian VAR is adequate. A two-regime Markov-switching fit with LR above about 14 sends you to the Markov-Switching Guide. The tests are screening devices on a VAR(1) and do not replace the diagnostics inside each guide.