Most nonexperimental studies of voter turnout rely on survey data. However, surveys overestimate turnout because of (1) nonresponse bias and (2) overreporting. We investigate this possibility using a rich dataset of Danish voters, which includes validated turnout indicators from administrative data for both respondents and nonrespondents, as well as respondents’ self-reported voting from the Danish National Election Studies. We show that both nonresponse bias and overreporting contribute significantly to overestimations of turnout. Further, we use covariates from the administrative data available for both respondents and nonrespondents to demonstrate that both factors also significantly bias the predictors of turnout. In our case, we find that nonresponse bias and overreporting masks a gender gap of two and a half percentage points in women’s favor as well as a gap of 25 percentage points in ethnic Danes’ favor compared with Danes of immigrant heritage.

Expert evaluations about countries form the backbone of comparative political research. It is reasonable to assume that such respondents, no matter the region they specialize in, will have a comparable understanding of the phenomena tapped by expert surveys. This is necessary to get results that can be compared across countries, which is the fundamental goal of these measurement activities. We empirically test this assumption using measurement invariance techniques which have not been applied to expert surveys before. Used most often to test the cross-cultural validity and translation effects of public opinion scales, the measurement invariance tests evaluate the comparability of scale items across any groups. We apply them to the Perceptions of Electoral Integrity (PEI) dataset. Our findings suggest that cross-regional comparability fails for all eleven dimensions identified in PEI. Results indicate which items remain comparable, at least across most regions, and point to the need of more rigorous procedures to develop expert survey questions.

Difference-in-differences is a widely used evaluation strategy that draws causal inference from observational panel data. Its causal identification relies on the assumption of parallel trends, which is scale-dependent and may be questionable in some applications. A common alternative is a regression model that adjusts for the lagged dependent variable, which rests on the assumption of ignorability conditional on past outcomes. In the context of linear models, Angrist and Pischke (2009) show that the difference-in-differences and lagged-dependent-variable regression estimates have a bracketing relationship. Namely, for a true positive effect, if ignorability is correct, then mistakenly assuming parallel trends will overestimate the effect; in contrast, if the parallel trends assumption is correct, then mistakenly assuming ignorability will underestimate the effect. We show that the same bracketing relationship holds in general nonparametric (model-free) settings. We also extend the result to semiparametric estimation based on inverse probability weighting. We provide three examples to illustrate the theoretical results with replication files in Ding and Li (2019).