When Should You Adjust Standard Errors for Clustering?
National Bureau of Economic Research · Ca' Foscari University of Venice · +5 more institutions
Abstract
In empirical work in economics it is common to report standard errors that account for clustering of units.Typically, the motivation given for the clustering adjustments is that unobserved components in outcomes for units within clusters are correlated.However, because correlation may occur across more than one dimension, this motivation makes it difficult to justify why researchers use clustering in some dimensions, such as geographic, but not others, such as age cohorts or gender.This motivation also makes it difficult to explain why one should not cluster with data from a randomized experiment.In this paper, we argue that clustering is in essence a design problem, either a sampling design or an experimental…
Citation impact
- FWCI
- —
- Percentile
- —
- References
- 39
Authors
4- AAAlberto AbadieCorresponding
National Bureau of Economic Research, Ca' Foscari University of Venice, Brown University, IIT@MIT, Cambridge Econometrics (United Kingdom), Michigan State University, Stanford University
- SASusan Athey
National Bureau of Economic Research, Ca' Foscari University of Venice, Brown University, IIT@MIT, Cambridge Econometrics (United Kingdom), Michigan State University, Stanford University
- GWGuido W. Imbens
National Bureau of Economic Research, Ca' Foscari University of Venice, Brown University, IIT@MIT, Cambridge Econometrics (United Kingdom), Michigan State University, Stanford University
- JMJeffrey M. Wooldridge
National Bureau of Economic Research, Ca' Foscari University of Venice, Brown University, IIT@MIT, Cambridge Econometrics (United Kingdom), Michigan State University, Stanford University
Topics & keywords
- Cluster analysis
- Computer science
- Artificial intelligence