TL;DR —
The paper investigates the optimal design of clustering in experimental setups, particularly in the context of social networks. It discusses theoretical frameworks, objective functions, and practical algorithms for choosing the best clustering method. The authors analyze the impact of various factors, including bias, variance, and spillover effects, providing recommendations for real-world applications.
Authors:
(1) Davide Viviano, Department of Economics, Harvard University;
(2) Lihua Lei, Graduate School of Business, Stanford University;
(3) Guido Imbens, Graduate School of Business and Department of Economics, Stanford University;
(4) Brian Karrer, FAIR, Meta;
(5) Okke Schrijvers, Meta Central Applied Science;
(6) Liang Shi, Meta Central Applied Science.
Table of Links
Empirical illustration and numerical studies
B Endogenous peer effects
This paper is available on arxiv under CC 1.0 license.
[story continues]
Written by
@escholar
We publish the best academic work (that's too often lost to peer reviews & the TA's desk) to the global tech community
Topics and
tags
tags
experimental-design|cluster-design|causal-clustering|network-experiments|cluster-experiments|optimal-cluster-design|endogenous-peer-effects|network-data-analysis
This story on HackerNoon has a decentralized backup on Sia.
Transaction ID: KI1Xi87J4vfjoYj0bLrD9yI9w0rAM7A_XuTGOiBhxBE