Identification-Robust Subvector Inference

Andrews, Donald W.K.

doi:10.2139/ssrn.3032675

Cited by 15 publications

(31 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… Inference procedures for subvectors have been further developed by Chaudhuri and Zivot (), Kaido, Molinari, and Stoye (), Andrews (), and Bugni, Canay, and Shi (). …”

mentioning

confidence: 99%

Inference for VARs identified with sign restrictions

Granziera¹,

Moon²,

Schorfheide³

2018

Quantitative Economics

View full text Add to dashboard Cite

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.

show abstract

“… Inference procedures for subvectors have been further developed by Chaudhuri and Zivot (), Kaido, Molinari, and Stoye (), Andrews (), and Bugni, Canay, and Shi (). …”

mentioning

confidence: 99%

Inference for VARs identified with sign restrictions

Granziera¹,

Moon²,

Schorfheide³

2018

Quantitative Economics

View full text Add to dashboard Cite

show abstract

“…We investigate this issue by comparing the power of our conditional subvector AR test against a comparable test that controls size under general forms of heteroskedasticity. We use a Bonferroni‐type test as in Chaudhuri and Zivot () and Andrews (), which controls asymptotic size under heteroskedasticity and is asymptotically efficient under strong instruments. The test requires two steps.…”

Section: Power Loss For Robustness To Heteroskedasticitymentioning

confidence: 99%

“…The first step constructs a confidence set for γ of size

1 - α_{1}

, and the second step performs a size

α_{2}

subvector

C false(α false)

‐type test on β for each value of γ in the first‐step confidence set. To avoid conservativeness under strong identification, the second‐step size

α_{2}

is chosen using the identification category selection (ICS) rule proposed by Andrews (); see Appendix D.4 in the SM for details. We report results only for the just‐identified case, in which the various

C false(α false)

‐type tests all coincide.…”

Section: Power Loss For Robustness To Heteroskedasticitymentioning

confidence: 99%

“…In ongoing work, Kleibergen () provided power improvements over projection for the conditional likelihood ratio test for a subvector hypothesis in the linear IV model. Building on the approach of Chaudhuri and Zivot (), Andrews () proposed a two‐step Bonferroni‐like method that applies more generally to nonlinear models with non‐i.i.d. heteroskedastic data, and is asymptotically efficient under strong identification.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A more powerful subvector Anderson Rubin test in linear instrumental variables regression

Guggenberger

Kleibergen

Mavroeidis

2019

View full text Add to dashboard Cite

We study subvector inference in the linear instrumental variables model assuming homoskedasticity but allowing for weak instruments. The subvector Anderson and Rubin (1949) test that uses chi square critical values with degrees of freedom reduced by the number of parameters not under test, proposed by Guggenberger, Kleibergen, Mavroeidis, and Chen (2012), controls size but is generally conservative. We propose a conditional subvector Anderson and Rubin test that uses datadependent critical values that adapt to the strength of identification of the parameters not under test. This test has correct size and strictly higher power than the subvector Anderson and Rubin test by Guggenberger et al. (2012). We provide tables with conditional critical values so that the new test is quick and easy to use. Application of our method to a model of risk preferences in development economics shows that it can strengthen empirical conclusions in practice.

show abstract

“…Most of these works focus on uniform size control for moment inequality models and the resulting CSs for μ are generally conservative under point identification. Recently, Andrews () considered identification‐robust inference on

μ \in M_{I}

that is efficient in strongly point‐identified regular models.…”

mentioning

confidence: 99%

Monte Carlo Confidence Sets for Identified Sets

Chen¹,

Christensen²,

Tamer³

2018

Econometrica

View full text Add to dashboard Cite

It is generally difficult to know whether the parameters in nonlinear econometric models are point‐identified. We provide computationally attractive procedures to construct confidence sets (CSs) for identified sets of the full parameter vector and of subvectors in models defined through a likelihood or a vector of moment equalities or inequalities. The CSs are based on level sets of “optimal” criterion functions (such as likelihoods, optimally‐weighted or continuously‐updated GMM criterions). The level sets are constructed using cutoffs that are computed via Monte Carlo (MC) simulations from the quasi‐posterior distribution of the criterion. We establish new Bernstein–von Mises (or Bayesian Wilks) type theorems for the quasi‐posterior distributions of the quasi‐likelihood ratio (QLR) and profile QLR in partially‐identified models. These results imply that our MC CSs have exact asymptotic frequentist coverage for identified sets of full parameters and of subvectors in partially‐identified regular models, and have valid but potentially conservative coverage in models whose local tangent spaces are convex cones. Further, our MC CSs for identified sets of subvectors are shown to have exact asymptotic coverage in models with singularities. We provide local power properties and uniform validity of our CSs over classes of DGPs that include point‐ and partially‐identified models. Finally, we present two simulation experiments and two empirical examples: an airline entry game and a model of trade flows.

show abstract

Identification-Robust Subvector Inference

Cited by 15 publications

References 49 publications

Inference for VARs identified with sign restrictions

Inference for VARs identified with sign restrictions

A more powerful subvector Anderson Rubin test in linear instrumental variables regression

Monte Carlo Confidence Sets for Identified Sets

Contact Info

Product

Resources

About