Fast and wild: Bootstrap inference in Stata using boottest

By D. Roodman, Morten Ørregaard Nielsen, James G. MacKinnon, Matthew D. Webb. The Stata Journal, 2018

706 citations recorded by the source corpus.

The wild bootstrap was originally developed for regression models with heteroskedasticity of unknown form. Over the past 30 years, it has been extended to models estimated by instrumental variables and maximum likelihood and to ones where the error terms are (perhaps multiway) clustered. Like bootstrap methods in general, the wild bootstrap is especially useful when conventional inference methods are unreliable because large-sample assumptions do not hold. For example, there may be few clusters, few treated clusters, or weak instruments. The package boottest can perform a wide variety of wild bootstrap tests, often at remarkable speed. It can also invert these tests to construct confidence sets. As a postestimation command, boottest works after linear estimation commands, including regress, cnsreg, ivregress, ivreg2, areg, and reghdfe, as well as many estimation commands based on maximum likelihood. Although it is designed to perform the wild cluster bootstrap, boottest can also perform the ordinary (nonclustered) version. Wrappers offer classical Wald, score/Lagrange multiplier, and Anderson–Rubin tests, optionally with (multiway) clustering. We review the main ideas of the wild cluster bootstrap, offer tips for use, explain why it is particularly amenable to computational optimization, state the syntax of boottest, artest, scoretest, and waldtest, and present several empirical examples.

Subfields: Artificial Intelligence, Economics and Econometrics, Marketing

View Paper: https://www.semanticscholar.org/paper/42453b0a55ff0754e7f108a10d86ce9b5bda9a24

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Economics and Econometrics

In Marketing

Citations in the corpus

Asymptotic theory and wild bootstrap inference with clustered errors (2019, methodology): “• Because the wild cluster bootstrap is remarkably inexpensive to implement when G is not too large, even when N is very large (Roodman et al. 2019), we recommend using WCR-R whenever there is any reason to believe that asymptotic inference may not be reliable.”
Wild Bootstrap and Asymptotic Inference With Multiway Clustering (2019, methodology): “All these procedures are implemented in the (computationally very eﬃcient) Stata package boottest ; see Roodman, MacKinnon, Nielsen, and Webb (2019).”
The Effects of Social Movements: Evidence from #MeToo (2020, methodology): “Row (2) shows the p-value calculated with wild bootstrap (Roodman et al., 2019).”