Inference for VARs identified with sign restrictions

Eleonora Granziera; Hyungsik Roger Moon; Frank Schorfheide

doi:10.3982/QE978

Inference for VARs identified with sign restrictions

Eleonora Granziera, Hyungsik Roger Moon, Frank Schorfheide

Department of Economics

Research output: Contribution to journal › Article › peer-review

19 Citations (Scopus)

Abstract

There is a fast growing literature that set-identifies structural vector autoregressions (SVARs) by imposing sign restrictions on the responses of a subset of the endogenous variables to a particular structural shock (sign-restricted SVARs). Most methods that have been used to construct pointwise coverage bands for impulse responses of sign-restricted SVARs are justified only from a Bayesian perspective. This paper demonstrates how to formulate the inference problem for sign-restricted SVARs within a moment-inequality framework. In particular, it develops methods of constructing confidence bands for impulse response functions of sign-restricted SVARs that are valid from a frequentist perspective. The paper also provides a comparison of frequentist and Bayesian coverage bands in the context of an empirical application—the former can be substantially wider than the latter.

Original language	English
Pages (from-to)	1087-1121
Number of pages	35
Journal	Quantitative Economics
Volume	9
Issue number	3
DOIs	https://doi.org/10.3982/QE978
Publication status	Published - 2018 Nov

Bibliographical note

Funding Information:
Eleonora Granziera: eleonora.granziera@bof.fi Hyungsik Roger Moon: moonr@usc.edu Frank Schorfheide: schorf@ssc.upenn.edu We thank Andres Santos (coeditor), Fabio Canova, Eric Renault, Paul Sangrey, James Stock, several anonymous referees, as well as participants at various conferences and seminars for helpful comments. We also thank Mihye Lee for her contributions to the first draft of this paper and Minchul Shin for research assistance. Schorfheide gratefully acknowledges financial support from the National Science Foundation under Grants SES 1061725 and 1424843. The views expressed in this paper are those of the authors and do not necessarily reflect those of the Bank of Finland. The Online Technical Appendix as well as data and software to replicate the empirical analysis are available in the Supplementary Material (Granziera, Moon, and Schorfheide (2018)).

Publisher Copyright:
Copyright © 2018 The Authors.

All Science Journal Classification (ASJC) codes

Economics and Econometrics

Access to Document

10.3982/QE978

Cite this

@article{07527dc0cd2e43a6be71f5ad908f616b,

title = "Inference for VARs identified with sign restrictions",

abstract = "There is a fast growing literature that set-identifies structural vector autoregressions (SVARs) by imposing sign restrictions on the responses of a subset of the endogenous variables to a particular structural shock (sign-restricted SVARs). Most methods that have been used to construct pointwise coverage bands for impulse responses of sign-restricted SVARs are justified only from a Bayesian perspective. This paper demonstrates how to formulate the inference problem for sign-restricted SVARs within a moment-inequality framework. In particular, it develops methods of constructing confidence bands for impulse response functions of sign-restricted SVARs that are valid from a frequentist perspective. The paper also provides a comparison of frequentist and Bayesian coverage bands in the context of an empirical application—the former can be substantially wider than the latter.",

author = "Eleonora Granziera and Moon, {Hyungsik Roger} and Frank Schorfheide",

note = "Funding Information: Eleonora Granziera: eleonora.granziera@bof.fi Hyungsik Roger Moon: moonr@usc.edu Frank Schorfheide: schorf@ssc.upenn.edu We thank Andres Santos (coeditor), Fabio Canova, Eric Renault, Paul Sangrey, James Stock, several anonymous referees, as well as participants at various conferences and seminars for helpful comments. We also thank Mihye Lee for her contributions to the first draft of this paper and Minchul Shin for research assistance. Schorfheide gratefully acknowledges financial support from the National Science Foundation under Grants SES 1061725 and 1424843. The views expressed in this paper are those of the authors and do not necessarily reflect those of the Bank of Finland. The Online Technical Appendix as well as data and software to replicate the empirical analysis are available in the Supplementary Material (Granziera, Moon, and Schorfheide (2018)). Publisher Copyright: Copyright {\textcopyright} 2018 The Authors.",

year = "2018",

month = nov,

doi = "10.3982/QE978",

language = "English",

volume = "9",

pages = "1087--1121",

journal = "Quantitative Economics",

issn = "1759-7323",

publisher = "The Economic Society",

number = "3",

}

TY - JOUR

T1 - Inference for VARs identified with sign restrictions

AU - Granziera, Eleonora

AU - Moon, Hyungsik Roger

AU - Schorfheide, Frank

N1 - Funding Information: Eleonora Granziera: eleonora.granziera@bof.fi Hyungsik Roger Moon: moonr@usc.edu Frank Schorfheide: schorf@ssc.upenn.edu We thank Andres Santos (coeditor), Fabio Canova, Eric Renault, Paul Sangrey, James Stock, several anonymous referees, as well as participants at various conferences and seminars for helpful comments. We also thank Mihye Lee for her contributions to the first draft of this paper and Minchul Shin for research assistance. Schorfheide gratefully acknowledges financial support from the National Science Foundation under Grants SES 1061725 and 1424843. The views expressed in this paper are those of the authors and do not necessarily reflect those of the Bank of Finland. The Online Technical Appendix as well as data and software to replicate the empirical analysis are available in the Supplementary Material (Granziera, Moon, and Schorfheide (2018)). Publisher Copyright: Copyright © 2018 The Authors.

PY - 2018/11

Y1 - 2018/11

N2 - There is a fast growing literature that set-identifies structural vector autoregressions (SVARs) by imposing sign restrictions on the responses of a subset of the endogenous variables to a particular structural shock (sign-restricted SVARs). Most methods that have been used to construct pointwise coverage bands for impulse responses of sign-restricted SVARs are justified only from a Bayesian perspective. This paper demonstrates how to formulate the inference problem for sign-restricted SVARs within a moment-inequality framework. In particular, it develops methods of constructing confidence bands for impulse response functions of sign-restricted SVARs that are valid from a frequentist perspective. The paper also provides a comparison of frequentist and Bayesian coverage bands in the context of an empirical application—the former can be substantially wider than the latter.

AB - There is a fast growing literature that set-identifies structural vector autoregressions (SVARs) by imposing sign restrictions on the responses of a subset of the endogenous variables to a particular structural shock (sign-restricted SVARs). Most methods that have been used to construct pointwise coverage bands for impulse responses of sign-restricted SVARs are justified only from a Bayesian perspective. This paper demonstrates how to formulate the inference problem for sign-restricted SVARs within a moment-inequality framework. In particular, it develops methods of constructing confidence bands for impulse response functions of sign-restricted SVARs that are valid from a frequentist perspective. The paper also provides a comparison of frequentist and Bayesian coverage bands in the context of an empirical application—the former can be substantially wider than the latter.

UR - http://www.scopus.com/inward/record.url?scp=85057495703&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85057495703&partnerID=8YFLogxK

U2 - 10.3982/QE978

DO - 10.3982/QE978

M3 - Article

AN - SCOPUS:85057495703

SN - 1759-7323

VL - 9

SP - 1087

EP - 1121

JO - Quantitative Economics

JF - Quantitative Economics

IS - 3

ER -

Inference for VARs identified with sign restrictions

Abstract

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this