Ambrogio Cesa-Bianchi
A toolbox for the analysis of DSGE models estimated with Bayesian techniques
This toolbox uses the standard output of Dynare to:
(i) plot the Markov chain Monte Carlo (MCMC),
(ii) plot the ergodic distribution of the posterior distribution,
(iii) plot the prior versus the posterior distribution, together with the mode of the posterior,
(iv) assess the convergence of the MCMC chain through CUSUM procedure, and
(v) compare the correlation between the parameters implied by the Hessian and the chain.
The toolbox makes use of few Matlab routines of Dynare.
The following example uses as an input the replication of F. Schorfheide (2000) “Loss function-based evaluation of DSGE models“ Journal of Applied Econometrics, 15, 645-670, available on the Dynare website. The convergence of the Markov chain Monte Carlo is assessed with the DSGE Bayesian Toolbox.
A toolbox for VAR analysis
The VAR Toolbox is a collection of Matlab codes to perform Vector Autoregression (VAR) analysis. Estimation is performed with OLS. The VAR Toolbox allows for identification of structural shocks with zero short-run restrictions; zero long-run restrictions; sign restrictions; external instruments (proxy SVAR); and a combination of external instruments and sign restrictions. Impulse Response Functions (IR), Forecast Error Variance Decomposition (VD), and Historical Decompositions (HD) are computed according to the chosen identification. Confidence intervals are obtained with bootstrapping methods.
Vector Autoregressions: A Primer
A simple primer on VARs (slides and accompanying Matlab codes) using VAR Toolbox is available at the following links:
[Matlab Code] [Slides]
The BEAR toolbox
Dieppe, Alistair, van Roye, Björn
The Bayesian Estimation, Analysis and Regression toolbox (BEAR) is a comprehensive (Bayesian Panel) VAR toolbox for forecasting and policy analysis.
BEAR is a MATLAB based toolbox which is easy for non-technical users to understand, augment and adapt. In particular, BEAR includes a user-friendly graphical interface which allows the tool to be used by country desk economists.
Furthermore, BEAR is well documented, both within the code as well as including a detailed theoretical and user’s guide. BEAR includes state-of-the art applications such as FAVARs, stochastic volatility, time-varying parameters, mixed-frequency, sign and magnitude restrictions, conditional forecasts, Bayesian forecast evaluation measures, Bayesian Panel VAR using different prior distributions (for example hierarchical priors).
BEAR is specifically developed for transparently supplying a tool for state-of-the-art research and is planned to be further developed to always be at the frontier of economic research.
BEAR Toolbox
Empirical macro toolbox
The empirical macro toolbox is a new package that contains MATLAB functions and routines to estimate VARs, FAVARs, local projections and other models with classical or Bayesian methods. The toolbox allows a researcher to conduct inference under various prior assumptions on the parameters, to produce point and density forecasts, and to trace out the causal effect of shocks using a number of identification schemes. The toolbox is equipped to handle missing observations. It can also deal with panels of time series. We describe the methodology employed and implementation of the functions. We illustrate the main features with a number of practical examples.
A hitchhiker guide to empirical macro models (Reference Document) by Ferroni F. and Canova F.
