Asymptotic theory and wild bootstrap inference with clustered errors

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperJournal articleResearchpeer-review

Standard

Asymptotic theory and wild bootstrap inference with clustered errors. / Djogbenou, Antoine A.; MacKinnon, James G.; Nielsen, Morten Ørregaard.

In: Journal of Econometrics, Vol. 212, No. 2, 10.2019, p. 393-412.

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperJournal articleResearchpeer-review

Harvard

Djogbenou, AA, MacKinnon, JG & Nielsen, MØ 2019, 'Asymptotic theory and wild bootstrap inference with clustered errors', Journal of Econometrics, vol. 212, no. 2, pp. 393-412. https://doi.org/10.1016/j.jeconom.2019.04.035

APA

CBE

MLA

Vancouver

Author

Djogbenou, Antoine A. ; MacKinnon, James G. ; Nielsen, Morten Ørregaard. / Asymptotic theory and wild bootstrap inference with clustered errors. In: Journal of Econometrics. 2019 ; Vol. 212, No. 2. pp. 393-412.

Bibtex

@article{57e744d3ba5343bab373ed9f7b332b71,
title = "Asymptotic theory and wild bootstrap inference with clustered errors",
abstract = "We study inference based on cluster-robust variance estimators for regression models with clustered errors, focusing on the wild cluster bootstrap. We state conditions under which asymptotic and bootstrap tests and confidence intervals are asymptotically valid. These conditions put limits on the rates at which the cluster sizes can increase as the number of clusters tends to infinity. We also derive Edgeworth expansions for the asymptotic and bootstrap test statistics. Simulation experiments illustrate the theoretical results and suggest that alternative variants of the wild cluster bootstrap may perform quite differently. The Edgeworth expansions explain the overrejection of asymptotic tests and shed light on the choice of auxiliary distribution and whether to use restricted or unrestricted estimates in the bootstrap data-generating process.",
keywords = "Clustered data, Cluster-robust variance estimator, Edgeworth expansion, Inference, Wild cluster bootstrap",
author = "Djogbenou, {Antoine A.} and MacKinnon, {James G.} and Nielsen, {Morten {\O}rregaard}",
year = "2019",
month = "10",
doi = "10.1016/j.jeconom.2019.04.035",
language = "English",
volume = "212",
pages = "393--412",
journal = "Journal of Econometrics",
issn = "0304-4076",
publisher = "Elsevier BV",
number = "2",

}

RIS

TY - JOUR

T1 - Asymptotic theory and wild bootstrap inference with clustered errors

AU - Djogbenou, Antoine A.

AU - MacKinnon, James G.

AU - Nielsen, Morten Ørregaard

PY - 2019/10

Y1 - 2019/10

N2 - We study inference based on cluster-robust variance estimators for regression models with clustered errors, focusing on the wild cluster bootstrap. We state conditions under which asymptotic and bootstrap tests and confidence intervals are asymptotically valid. These conditions put limits on the rates at which the cluster sizes can increase as the number of clusters tends to infinity. We also derive Edgeworth expansions for the asymptotic and bootstrap test statistics. Simulation experiments illustrate the theoretical results and suggest that alternative variants of the wild cluster bootstrap may perform quite differently. The Edgeworth expansions explain the overrejection of asymptotic tests and shed light on the choice of auxiliary distribution and whether to use restricted or unrestricted estimates in the bootstrap data-generating process.

AB - We study inference based on cluster-robust variance estimators for regression models with clustered errors, focusing on the wild cluster bootstrap. We state conditions under which asymptotic and bootstrap tests and confidence intervals are asymptotically valid. These conditions put limits on the rates at which the cluster sizes can increase as the number of clusters tends to infinity. We also derive Edgeworth expansions for the asymptotic and bootstrap test statistics. Simulation experiments illustrate the theoretical results and suggest that alternative variants of the wild cluster bootstrap may perform quite differently. The Edgeworth expansions explain the overrejection of asymptotic tests and shed light on the choice of auxiliary distribution and whether to use restricted or unrestricted estimates in the bootstrap data-generating process.

KW - Clustered data

KW - Cluster-robust variance estimator

KW - Edgeworth expansion

KW - Inference

KW - Wild cluster bootstrap

U2 - 10.1016/j.jeconom.2019.04.035

DO - 10.1016/j.jeconom.2019.04.035

M3 - Journal article

VL - 212

SP - 393

EP - 412

JO - Journal of Econometrics

JF - Journal of Econometrics

SN - 0304-4076

IS - 2

ER -