Cluster–Robust Variance Estimation for Dyadic Data

By P. M. Aronow, Cyrus Samii, Valentina A. Assenova. Political Analysis, 2013

126 citations recorded by the source corpus.

Dyadic data are common in the social sciences, although inference for such settings involves accounting for a complex clustering structure. Many analyses in the social sciences fail to account for the fact that multiple dyads share a member, and that errors are thus likely correlated across these dyads. We propose a non-parametric, sandwich-type robust variance estimator for linear regression to account for such clustering in dyadic data. We enumerate conditions for estimator consistency. We also extend our results to repeated and weighted observations, including directed dyads and longitudinal data, and provide an implementation for generalized linear models such as logistic regression. We examine empirical performance with simulations and an application to interstate disputes.

Subfields: Economics and Econometrics, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/a92fb4c3cb3798ccee77442b53a77d02a56741bd

How researchers see this paper

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

In Economics and Econometrics

In Statistics and Probability

Citations in the corpus

Estimating peer effects in networks with peer encouragement designs (2016, methodology): “These are Huber–White “sandwich” estimators of the form V̂ar[β̂] = (X′X)−1X′(ûû′ B)X(X′X)−1, (3) where û is the vector of residuals, is element-wise multiplication, and S is a n×n matrix that selects and/or weights pairs of observations.”
When Should We Use Unit Fixed Effects Regression Models for Causal Inference with Longitudinal Data? (2019, methodology): “…for the correlations across dyads when they share a common member, we verify our findings with the cluster-robust standard errors proposed by Aronow, Samii, and Assenova (2015) and find that the positive effects of participant membership remain statistically significant, although the…”