Optimal Design of Experiments in the Presence of Interference

Optimal Design of Experiments in the Presence of Interference

We formalize the optimal design of experiments when there is interference between units, i.e. an individual's outcome depends on the outcomes of others in her group. We focus on randomized saturation designs, two-stage experiments that first randomize treatment saturation of a group, then indiv...

Full description

Bibliographic Details
Main Authors: Baird, Sarah, Bohren, J. Aislinn, McIntosh, Craig, Ozler, Berk
Format: Journal Article
Published: The MIT Press 2018
Subjects:
EXPERIMENTAL DESIGN
CAUSAL INTERFERENCE
SPILLOVER EFFECT
Online Access:http://hdl.handle.net/10986/29656
id okr-10986-29656
recordtype oai_dc
spelling okr-10986-296562021-05-25T10:54:36Z Optimal Design of Experiments in the Presence of Interference Baird, Sarah Bohren, J. Aislinn McIntosh, Craig Ozler, Berk EXPERIMENTAL DESIGN CAUSAL INTERFERENCE SPILLOVER EFFECT We formalize the optimal design of experiments when there is interference between units, i.e. an individual's outcome depends on the outcomes of others in her group. We focus on randomized saturation designs, two-stage experiments that first randomize treatment saturation of a group, then individual treatment assignment. We map the potential outcomes framework with partial interference to a regression model with clustered errors, calculate standard errors of randomized saturation designs, and derive analytical insights about the optimal design. We show that the power to detect average treatment effects declines precisely with the ability to identify novel treatment and spillover effects. 2018-04-11T16:52:20Z 2018-04-11T16:52:20Z 2018-01-12 Journal Article Review of Economics and Statistics http://hdl.handle.net/10986/29656 CC BY-NC-ND 3.0 IGO http://creativecommons.org/licenses/by-nc-nd/3.0/igo World Bank The MIT Press Publications & Research :: Journal Article Publications & Research
repository_type Digital Repository
institution_category Foreign Institution
institution Digital Repositories
building World Bank Open Knowledge Repository
collection World Bank
topic EXPERIMENTAL DESIGN
CAUSAL INTERFERENCE
SPILLOVER EFFECT
spellingShingle EXPERIMENTAL DESIGN
CAUSAL INTERFERENCE
SPILLOVER EFFECT
Baird, Sarah
Bohren, J. Aislinn
McIntosh, Craig
Ozler, Berk
Optimal Design of Experiments in the Presence of Interference
description We formalize the optimal design of experiments when there is interference between units, i.e. an individual's outcome depends on the outcomes of others in her group. We focus on randomized saturation designs, two-stage experiments that first randomize treatment saturation of a group, then individual treatment assignment. We map the potential outcomes framework with partial interference to a regression model with clustered errors, calculate standard errors of randomized saturation designs, and derive analytical insights about the optimal design. We show that the power to detect average treatment effects declines precisely with the ability to identify novel treatment and spillover effects.
format Journal Article
author Baird, Sarah
Bohren, J. Aislinn
McIntosh, Craig
Ozler, Berk
author_facet Baird, Sarah
Bohren, J. Aislinn
McIntosh, Craig
Ozler, Berk
author_sort Baird, Sarah
title Optimal Design of Experiments in the Presence of Interference
title_short Optimal Design of Experiments in the Presence of Interference
title_full Optimal Design of Experiments in the Presence of Interference
title_fullStr Optimal Design of Experiments in the Presence of Interference
title_full_unstemmed Optimal Design of Experiments in the Presence of Interference
title_sort optimal design of experiments in the presence of interference
publisher The MIT Press
publishDate 2018
url http://hdl.handle.net/10986/29656
_version_ 1764469903555821568

Similar Items