|
Activity Number:
|
155
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Monday, August 1, 2016 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Section on Statistics in Marketing
|
|
Abstract #319075
|
View Presentation
|
|
Title:
|
Potential Outcome Regression with Interference
|
|
Author(s):
|
Joseph Rigdon* and Michael Hudgens
|
|
Companies:
|
Stanford University and The University of North Carolina at Chapel Hill
|
|
Keywords:
|
Interference ;
Observational Study ;
Bayesian ;
Regression ;
Malaria
|
|
Abstract:
|
Interference is present when the treatment or exposure of one individual affects the outcome of another individual. In this presentation, outcome regression models are employed to construct frequentist and Bayesian estimators for causal effects in the presence of interference in an observational study assuming that the treatment assignment mechanism is ignorable. The proposed estimators are compared via a simulation study to previously proposed IPW estimators. The outcome regression approaches outperform the IPW estimators in bias and precision. The methods are applied to data from the 2007 Demographic and Health Survey in the Democratic Republic of the Congo, examining the impact of individual and community bed net use on malaria.
|
Authors who are presenting talks have a * after their name.
