Survey Nonresponse After Elections: Investigating the Role of Winner-Loser Effects in Panel Attrition

Abstract When and for whom do election outcomes drive survey nonresponse? This paper investigates whether belonging to the winners or losers of an election affects the likelihood of participating in post-election surveys. Systematic winner-loser effects on survey participation and resulting sample disproportionalities could yield decisive consequences for the accuracy of public opinion measurements. Through a series of logistic regressions and survival analyses on individual-level panel data from the German Longitudinal Election Study (GLES) after 4 German federal elections between 2009 and 2021, I find that winners and losers are equally prone to post-election survey nonresponse. Attitudes towards the democratic system and past survey loyalty outweigh winner-loser effects: For both winners and losers, more negative democratic views seem to make people more likely to exhibit (durable) post-election nonresponse. Moreover, past survey participation reduces post-election nonresponse and its durability. Crucially, my results show that election outcomes alone rarely change survey participation. However, post-election surveys tend to display underrepresentation (of, e.g., less educated or politically uninvolved people), if people who disapprove of the election outcome are already likely to have more cynical attitudes towards politics and the democratic system.