Treatment Spillover Effects Across Survey Experiments

Posted: 18 Aug 2009

See all articles by John E. Transue

John E. Transue

University of Illinois at Springfield

Daniel J. Lee

Michigan State University

John Aldrich

Duke University - Department of Political Science

Date Written: Spring 2009

Abstract

Embedding experiments within surveys has reinvigorated survey research. Several survey experiments are generally embedded within a survey, and analysts treat each of these experiments as self-contained. We investigate whether experiments are self-contained or if earlier treatments affect later experiments, which we call “experimental spillover.” We consider two types of bias that might be introduced by spillover: mean and inference biases. Using a simple procedure, we test for experimental spillover in two data sets: the 1991 Race and Politics Survey and a survey containing several experiments pertaining to foreign policy attitudes. We find some evidence of spillover and suggest solutions to avoid bias.

Suggested Citation

Transue, John Ethan and Lee, Daniel J. and Aldrich, John, Treatment Spillover Effects Across Survey Experiments (Spring 2009). Political Analysis, Vol. 17, Issue 2, pp. 143-161, 2009, Available at SSRN: https://ssrn.com/abstract=1448444 or http://dx.doi.org/10.1093/pan/mpn012

John Ethan Transue (Contact Author)

University of Illinois at Springfield ( email )

Springfield, IL 62703
United States
217-206-8383 (Phone)

Daniel J. Lee

Michigan State University ( email )

Agriculture Hall
East Lansing, MI 48824-1122
United States

John Aldrich

Duke University - Department of Political Science ( email )

140 Science Drive (Gross Hall), 2nd floor
Duke University Mailcode: 90204
Durham, NC 27708-0204
United States
919-660-4346 (Phone)

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Abstract Views
304
PlumX Metrics