Indexed on: 09 Sep '16Published on: 02 Sep '16Published in: Public opinion quarterly
Online surveys have seen a rapid growth in the past decade and are now frequently being used for electoral research. Although they have obvious advantages, it is unclear whether the data produce inferences similar to more traditional face-to-face surveys, particularly when response to the survey is correlated with the survey variables of interest. Drawing on data from the latest American National Election Study and British Election Study, we examine how age affects political engagement, comparing responses between face-to-face and online surveys. The results indicate that online surveys, particularly those where respondents have opted in, reduce variance and overestimate the proportion of those who are politically engaged, which produces different conclusions about what motivates citizens to vote. These findings suggest a need to acknowledge selection bias when examining questions about political engagement, particularly when it comes to election surveys that rely on opt-in panels that are more likely to attract those who are interested in the subject matter and thus more politically engaged.