Bayesian Estimation of DSGE Models

Edward Herbst and Frank Schorfheide

Princeton University Press, 2015

1. Table of Contents

Can be downloaded here: [pdf]

2. Corrections

Can be downloaded here: [pdf]
Please email us if you find typos, errors, etc.

3. Slides

We prepared some slides for each book chapter that can be used for teaching and study purposes:

Part I: Introduction to DSGE Modeling and Bayesian Inference
Slides for Chapter 1: DSGE Modeling
Slides for Chapter 2: Turning a DSGE Model into a Bayesian Model
Slides for Chapter 3: A Crash Course in Bayesian Inference

Part II: Estimation of Linearized DSGE Models
Slides for Chapter 4: Metropolis-Hastings Algorithms for DSGE Models
Slides for Chapter 5: Sequential Monte Carlo Methods
Slides for Chapter 6: Three Applications

Part III: Estimation of Nonlinear DSGE Models
Slides for Chapter 7: From Linear to Nonlinear Models
Slides for Chapter 8: Particle Filters
Slides for Chapter 9: Combining Particle Filters with MH Samplers
Slides for Chapter 10: Combining Particle Filters with SMC Samplers

4. Computer Code

We performed the computations in the textbook using a mix of PYTHON and FORTRAN. Sample codes are provided on Ed Herbst’s website at
http://edherbst.net/bayesian-book.
Please note that not all the codes are running properly yet and check for updates!

We are also providing some MATLAB codes:
DSGE Estimation.zip: These programs estimate the small-scale DSGE model using a random walk Metropolis-Hastings algorithm, see Chapters 4.1 and 4.2.
SMC.zip: These programs implement the sequential Monte Carlo algorithm discussed in Chapter 5.1 for the stylized state-space model. A new file was posted on 5/12/2017. Thanks to Mark Bognanni (FRB Cleveland) for correcting bugs in an earlier version of the code.
DSGE SMC.zip: These programs implement the sequential Monte Carlo algorithm for the small-scale DSGE model, see Chapter 5.3.
Nonlinear Filtering.zip: These programs implement the bootstrap particle filter and the conditionally optimal particle filter for the small scale DSGE model, see Chapter 8.6

Marco Del Negro, Michael Cai, Chris Rytting, Abhi Gupta, Pearl Li, and Erica Moszkowski from the FRB New York wrote Julia code that implements the SMC computations for the small-scale DSGE model, see Chapter 5.3. This code is available here: https://github.com/FRBNY-DSGE/DSGE.jl/tree/SMC-replication

5. Data Sets Used in the Book

The data sets for the empirical illustrations are available here: [zip]