Inference from Biased Polls

64 Pages Posted: 17 Nov 2020 Last revised: 11 Mar 2022

See all articles by Andy Brownback

Andy Brownback

University of Arkansas

Nathaniel Burke

West Virginia University

Tristan Gagnon-Bartsch

Harvard University

Multiple version iconThere are 2 versions of this paper

Date Written: March 3, 2022


Poll respondents often attempt to present a positive image by overstating virtuous behaviors. We examine whether people account for this "socially desirable responding" (SDR) when drawing inferences from poll data. In an experiment, we incentivize "predictors" to guess others' choice behaviors across eight actions with varying social desirability. Predictors observe random subsamples of either (i) incentivized choices or (ii) hypothetical claims from polls. The hypothetical claims exhibit predictable SDR and predictors are reasonably skeptical of them. However, their skepticism is not tailored to the direction or magnitude of SDR. This under-correction occurs even though subjects' explicit responses can predict SDR.

Keywords: Polling, Social Desirability, Inference, Signaling, Selection Bias

JEL Classification: D91, D84, D72

Suggested Citation

Brownback, Andy and Burke, Nathaniel and Gagnon-Bartsch, Tristan, Inference from Biased Polls (March 3, 2022). Available at SSRN: or

Andy Brownback (Contact Author)

University of Arkansas ( email )

Fayetteville, AR 72701
United States

Nathaniel Burke

West Virginia University ( email )

Morgantown, WV 26506
United States

HOME PAGE: http://

Tristan Gagnon-Bartsch

Harvard University ( email )

Do you have negative results from your research you’d like to share?

Paper statistics

Abstract Views
PlumX Metrics