On identification of Bayesian DSGE models

Gary Koop, M. Hashem Pesaran, Ron Smith

Research output: Contribution to journalArticle

19 Citations (Scopus)

Abstract

This article is concerned with local identification of individual parameters of dynamic stochastic general equilibrium (DSGE) models estimated by Bayesian methods. Identification is often judged by a comparison of the posterior distribution of a parameter with its prior. However, these can differ even when the parameter is not identified. Instead, we propose two Bayesian indicators of identification. The first follows a suggestion by Poirier of comparing the posterior density of the parameter of interest with the posterior expectation of its prior conditional on the remaining parameters. The second examines the rate at which the posterior precision of the parameter gets updated with the sample size, using data simulated at the parameter point of interest for an increasing sequence of sample sizes (T). For identified parameters, the posterior precision increases at rate T. For parameters that are either unidentified or are weakly identified, the posterior precision may get updated but its rate of update will be slower than T. We use empirical examples to demonstrate that these methods are useful in practice. This article has online supplementary material.
LanguageEnglish
Pages300-314
Number of pages15
JournalJournal of Business and Economic Statistics
Volume31
Issue number3
Early online date22 Jul 2013
DOIs
Publication statusPublished - 2013

Fingerprint

General Equilibrium
Equilibrium Model
equilibrium model
Stochastic Dynamics
Sample Size
Dynamic stochastic general equilibrium model
Monotonic increasing sequence
Bayesian Methods
Posterior distribution
Update

Keywords

  • New Keynesian Phillips Curve
  • Bayesian identification
  • DSGE models
  • posterior updating

Cite this

Koop, Gary ; Pesaran, M. Hashem ; Smith, Ron. / On identification of Bayesian DSGE models. In: Journal of Business and Economic Statistics. 2013 ; Vol. 31, No. 3. pp. 300-314.
@article{45792cfa818b4a5ebf19aac2700beb0b,
title = "On identification of Bayesian DSGE models",
abstract = "This article is concerned with local identification of individual parameters of dynamic stochastic general equilibrium (DSGE) models estimated by Bayesian methods. Identification is often judged by a comparison of the posterior distribution of a parameter with its prior. However, these can differ even when the parameter is not identified. Instead, we propose two Bayesian indicators of identification. The first follows a suggestion by Poirier of comparing the posterior density of the parameter of interest with the posterior expectation of its prior conditional on the remaining parameters. The second examines the rate at which the posterior precision of the parameter gets updated with the sample size, using data simulated at the parameter point of interest for an increasing sequence of sample sizes (T). For identified parameters, the posterior precision increases at rate T. For parameters that are either unidentified or are weakly identified, the posterior precision may get updated but its rate of update will be slower than T. We use empirical examples to demonstrate that these methods are useful in practice. This article has online supplementary material.",
keywords = "New Keynesian Phillips Curve, Bayesian identification, DSGE models, posterior updating",
author = "Gary Koop and Pesaran, {M. Hashem} and Ron Smith",
year = "2013",
doi = "10.1080/07350015.2013.773905",
language = "English",
volume = "31",
pages = "300--314",
journal = "Journal of Business and Economic Statistics",
issn = "0735-0015",
number = "3",

}

On identification of Bayesian DSGE models. / Koop, Gary; Pesaran, M. Hashem; Smith, Ron.

In: Journal of Business and Economic Statistics, Vol. 31, No. 3, 2013, p. 300-314.

Research output: Contribution to journalArticle

TY - JOUR

T1 - On identification of Bayesian DSGE models

AU - Koop, Gary

AU - Pesaran, M. Hashem

AU - Smith, Ron

PY - 2013

Y1 - 2013

N2 - This article is concerned with local identification of individual parameters of dynamic stochastic general equilibrium (DSGE) models estimated by Bayesian methods. Identification is often judged by a comparison of the posterior distribution of a parameter with its prior. However, these can differ even when the parameter is not identified. Instead, we propose two Bayesian indicators of identification. The first follows a suggestion by Poirier of comparing the posterior density of the parameter of interest with the posterior expectation of its prior conditional on the remaining parameters. The second examines the rate at which the posterior precision of the parameter gets updated with the sample size, using data simulated at the parameter point of interest for an increasing sequence of sample sizes (T). For identified parameters, the posterior precision increases at rate T. For parameters that are either unidentified or are weakly identified, the posterior precision may get updated but its rate of update will be slower than T. We use empirical examples to demonstrate that these methods are useful in practice. This article has online supplementary material.

AB - This article is concerned with local identification of individual parameters of dynamic stochastic general equilibrium (DSGE) models estimated by Bayesian methods. Identification is often judged by a comparison of the posterior distribution of a parameter with its prior. However, these can differ even when the parameter is not identified. Instead, we propose two Bayesian indicators of identification. The first follows a suggestion by Poirier of comparing the posterior density of the parameter of interest with the posterior expectation of its prior conditional on the remaining parameters. The second examines the rate at which the posterior precision of the parameter gets updated with the sample size, using data simulated at the parameter point of interest for an increasing sequence of sample sizes (T). For identified parameters, the posterior precision increases at rate T. For parameters that are either unidentified or are weakly identified, the posterior precision may get updated but its rate of update will be slower than T. We use empirical examples to demonstrate that these methods are useful in practice. This article has online supplementary material.

KW - New Keynesian Phillips Curve

KW - Bayesian identification

KW - DSGE models

KW - posterior updating

UR - http://www.scopus.com/inward/record.url?scp=84885010675&partnerID=8YFLogxK

U2 - 10.1080/07350015.2013.773905

DO - 10.1080/07350015.2013.773905

M3 - Article

VL - 31

SP - 300

EP - 314

JO - Journal of Business and Economic Statistics

T2 - Journal of Business and Economic Statistics

JF - Journal of Business and Economic Statistics

SN - 0735-0015

IS - 3

ER -