Jackknife inference with two-way clustering

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: MacKinnon, James G., Nielsen, Morten Ørregaard, Webb, Matthew D.
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910049823096832
author MacKinnon, James G.
Nielsen, Morten Ørregaard
Webb, Matthew D.
author_facet MacKinnon, James G.
Nielsen, Morten Ørregaard
Webb, Matthew D.
contents For linear regression models with cross-section or panel data, it is natural to assume that the disturbances are clustered in two dimensions. However, the finite-sample properties of two-way cluster-robust tests and confidence intervals are often poor. We discuss several ways to improve inference with two-way clustering. Two of these are existing methods for avoiding, or at least ameliorating, the problem of undefined standard errors when a cluster-robust variance matrix estimator (CRVE) is not positive definite. One is a new method that always avoids the problem. More importantly, we propose a family of new two-way CRVEs based on the cluster jackknife and prove that they yield valid inferences asymptotically. Simulations for models with two-way fixed effects suggest that, in many cases, the cluster-jackknife CRVE combined with our new method yields surprisingly accurate inferences. We provide a software package, twowayjack for Stata, that implements our recommended variance estimator.
format Preprint
id arxiv_https___arxiv_org_abs_2406_08880
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Jackknife inference with two-way clustering
MacKinnon, James G.
Nielsen, Morten Ørregaard
Webb, Matthew D.
Econometrics
For linear regression models with cross-section or panel data, it is natural to assume that the disturbances are clustered in two dimensions. However, the finite-sample properties of two-way cluster-robust tests and confidence intervals are often poor. We discuss several ways to improve inference with two-way clustering. Two of these are existing methods for avoiding, or at least ameliorating, the problem of undefined standard errors when a cluster-robust variance matrix estimator (CRVE) is not positive definite. One is a new method that always avoids the problem. More importantly, we propose a family of new two-way CRVEs based on the cluster jackknife and prove that they yield valid inferences asymptotically. Simulations for models with two-way fixed effects suggest that, in many cases, the cluster-jackknife CRVE combined with our new method yields surprisingly accurate inferences. We provide a software package, twowayjack for Stata, that implements our recommended variance estimator.
title Jackknife inference with two-way clustering
topic Econometrics
url https://arxiv.org/abs/2406.08880