Vcemway: A One-Stop Solution for Robust Inference with Multi-Way Clustering

Forthcoming, The Stata Journal

12 Pages Posted: 27 Jun 2019

See all articles by Ariel Gu

Ariel Gu

Durham University Business School

Hong Il Yoo

Durham Business School

Date Written: June 24, 2019

Abstract

Most Stata commands allow cluster(varname) as an option, popularizing the use of standard errors that are robust to one-way clustering. But when it comes to adjusting standard errors for multi-way clustering, there is no solution that is as widely applicable. While several user-written packages support multi-way clustering, each package is compatible with only a subset of models that Stata's ever-expanding library of commands allows the researcher to estimate. We introduce a command vcemway that provides a one-stop solution for multi-way clustering. vcemway works with any estimation command that allows cluster(varname) as an option, and adjusts standard errors, individual significance statistics and confidence intervals in output tables for multi-way clustering in specified dimensions. The covariance matrix used in making this adjustment is stored in e(V), meaning that any subsequent call to postestimation commands that use e(V) as input (e.g. test and margins) will also produce results that are robust to multi-way clustering.

Keywords: st0001, vcemway, ivreg2, cmgreg, reghdfe, boottest, two-way clustering, multi-way clustering

Suggested Citation

Gu, Ariel and Yoo, Hong Il, Vcemway: A One-Stop Solution for Robust Inference with Multi-Way Clustering (June 24, 2019). Forthcoming, The Stata Journal, Available at SSRN: https://ssrn.com/abstract=3409489 or http://dx.doi.org/10.2139/ssrn.3409489

Ariel Gu (Contact Author)

Durham University Business School ( email )

Mill Hill Lane
Durham, DH1 3LB
United Kingdom

Hong Il Yoo

Durham Business School ( email )

Mill Hill Lane
Durham, Durham DH1 3LB
United Kingdom

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
58
Abstract Views
323
rank
402,928
PlumX Metrics