Vote Overreporting Research Articles

A reassessment of the association between political interest and electoral participation: adding vote overreporting to the equation

Electoral participation research points to political interest as a strong and consistent predictor of voting, but overlooks the propensity of interested people to overreport in surveys. Vote validation studies demonstrate that vote overreporting exaggerates the association between political interest and turnout, but fails to highlight the pathways through which this bias occurs. To fill this gap and link these two strands of literature, we take a closer look at the relationships between political interest, likelihood of voting (as defined by one's actual voting record), and participation in given vote, while taking care of overreporting. Applying causal mediation models to a unique set of validated vote data, we show that the modus operandi of overreporting is both direct and indirect: A portion of politically interested people overreport their vote regardless of whether they usually vote or not. Yet, the indirect path also matters: Another portion of interested people do vote frequently, which prompts them to overreport if they for once abstain. This is consequential for the commonly found association between political interest and turnout.

Vote Overreporting While Black: Identifying the Mechanism Behind Black Survey Respondents’ Vote Overreporting

It is now a well-documented fact of survey research that Black survey respondents overreport turning out to vote at higher rates than many of their peers of other racial and ethnic backgrounds. We bring renewed attention to this phenomenon by investigating how the ways in which the race of the interviewer might influence a Back respondent’s propensity to overreport turning out to vote. In this paper, we test two competing mechanisms for African American overreporting and race of interviewer effects: (1) racial group linked fate, and (2) conformity with norms of Black political behavior. We find support that social pressure to conform to group norms of political behavior is behind Black respondent’s overreporting in the presence of a same-race interviewer. These results have significant implications for how we view, analyze, and consider results from such studies.

Vote overreporting in national election surveys: a 55-nation exploratory study

Vote overreporting in national election surveys: a 55-nation exploratory study

Who Gets Lost, and What Difference Does It Make? Mixed Modes, Nonresponse Follow-up Surveys and the Estimation of Turnout

Abstract This article assesses whether—and to what extent—turnout bias in postelection surveys is reduced by adding a short nonresponse follow-up (NRFU) survey to a mixed-mode survey. Specifically, we examine how the NRFU survey influences response propensities across demographic groups and political factors and whether this affects data quality. We use a rich dataset on validated voter turnout data, collected across two different ballots. In addition to the main survey that comprises computer-assisted telephone interviews (CATI) and web respondents, both studies include a short follow-up mail survey for nonrespondents. The results demonstrate that collecting extra information from additional respondents on so-called “central” questions is worth the effort. In both studies, the NRFU survey substantially increases representativeness with respect to sociodemographic and participation variables. In particular, voters and politically active citizens are more accurately represented in the NRFU survey. This tends to result in better estimates of turnout determinants in the final (combined) sample than is seen from CATI/web respondents only. Moreover, the increase in response rate and the decrease in nonresponse bias comes at almost no price in terms of measurement errors. Vote overreporting is only slightly higher in the mail follow-up survey than in the main CATI/web survey.

Using self-prophecy to combat vote overreporting on public opinion surveys

Survey researchers have long struggled with respondents who, due to the pressure to adhere to socially desirable norms, erroneously claim to have voted in a previous election. In this paper, we develop a new approach to reducing the overreporting of voting in surveys by leveraging psychological theories that show people have a tendency to follow through on an action once they have predicted their behavior (e.g. Sherman, 1980). Using a survey experiment through the 2014 Cooperative Congressional Election Study, we find that an overwhelming majority of respondents will agree to take an honesty pledge regarding their future vote report. Having pledged their honesty, they then overreport their vote at far lower rates than other survey participants. The observed effects are additive, since previously developed methods of reducing overreporting were present across all conditions. These findings have important implications for studies endeavoring to understand voting behavior and social desirability pressures.

Identity and Vote Overreporting by Bureaucrats: Implications for Public Service Motivation

Studies have argued that the higher levels of public service motivation (PSM) found in bureaucrats as compared with others lead to the positive civic and political behaviors seen in government employees. This study extends those findings to see if high PSM could have any negative effects on these same behaviors. Drawing from research on identity theory, it is hypothesized that a salient “public service identity” could contribute to bureaucrats being more apt than others to report that they have voted in elections when they actually had not. Logit models using data covering a span of almost 30 years in the United States find support for the hypothesis. This work suggests that viewing PSM through the lens of identity theory may have broad implications for the field of public administration.

Vote Overreporting and a Survey Experiment: The Case of the Taiwan National Elections

The misreporting of voter turnout, prevalent in survey data across the world, has received comparatively little attention anywhere apart from in some western countries. This study evaluates the use of questions specifically designed to mitigate the level of vote overreporting for the 2012 national elections in Taiwan. After a theoretical examination of social desirability and memory failure, the two primary causes of misreporting, we present the results of a split-question experiment featuring two questions designed to mitigate overreporting. While the findings reveal that the experiment with changes to the questionnaire context was far from successful because of a low reported turnout for the control question, it is the case that, as hypothesized, reported voter turnout differs vastly among the different questions, with the question mitigating for social desirability resulting in higher figures than that for memory failure.

Turnout Bias in Postelection Surveys: Political Involvement, Survey Participation, and Vote Overreporting

Turnout bias is a classic flaw of postelection surveys. It has a double cause: overrepresentation of actual voters among survey respondents and vote overreporting by actual nonvoters. Previous studies have focused on the latter, measurement bias, and have failed to address the former, nonresponse bias. However, turnout is typically a topic where there may be a link between response propensity and measurement error, as factors related to political involvement are likely to influence both survey participation and misreport. To take this link into account, we resort to a Heckman selection model in which the outcome equation estimates the probability of overreporting conditional on the probability of participation in the survey. We apply such a model to a unique data set of validated votes from the canton of Geneva, Switzerland, informing about the actual turnout of both individuals who were interviewed and individuals who were sampled but could not be interviewed. Based on the same data, we put forward a solution that may correct for the nonresponse bias in cases where information regarding nonresponse is not available. Applying this correction to U.S. data shows that not correcting for response propensity may indeed lead to inaccurate estimates of the determinants of overreporting and, ultimately, of turnout.

Lost on the Way: Nonresponse and its Influence on Turnout Bias in Postelection Surveys

Earlier studies on turnout bias in postelection surveys have focused on vote overreporting (measurement bias) and have disregarded nonresponse bias associated with voter overrepresentation. Based on a unique data set of validated votes collected for two different ballots, we offer an in-depth analysis of the size and sources of nonresponse bias. On the aggregate level, we find that voter overrepresentation accounts for a larger share of total turnout bias than misreporting. On the individual level, past voting record, ballot vote, and age appear as strong predictors of survey participation. Breaking down further the analysis, we show that these factors contribute to nonresponse bias through both contact and cooperation. By contrast, the effects of some other factors work at cross-purpose in the contact and cooperation stages.

Achieving Validation: Barack Obama and Black Turnout in 2008

AbstractIn this study we examine black voting in the 2008 presidential election. Recognizing the significance of having an African American win the presidency, we evaluate black political attitudes in 2008 vis-à-vis 2004, place black turnout in historical context, and discuss the problem of vote overreporting. The issue of vote overreporting plagues surveys, and this is particularly notable among African American respondents. The momentousness of Barack Obama's candidacy and subsequent election may further complicate black turnout responses. On the one hand, an African American Democratic presidential nominee is expected to mobilize blacks, but on the other hand this situation is also expected to increase the social desirability to misreport voting. To get around this intractable problem with surveys, we evaluate validated black turnout in the state of Georgia, which provides individual-level data on the population of registered voters. The validated black turnout numbers are much lower than those reported in national studies like the Current Population Survey, but our analysis indicates that compared to 2004, African American registration and voting in Georgia were markedly higher in 2008.

Electoral Salience and Vote Overreporting: Another Look at the Problem of Validity in Voter Turnout Studies

Electoral Salience and Vote Overreporting: Another Look at the Problem of Validity in Voter Turnout Studies

Vote Overreporting: The Statistical and Policy Implications

Voting is a critical way for citizens to gain representation for their interests, as well as the most direct way that most citizens participate in the political process. Yet, many citizens fail to cast their vote on election day. America's comparatively low turnout rate has motivated reams of research on voting behaviors, but researchers are limited by data quality problems. In particular, vote overreporting, when systematic, can bias analysis of who votes and why, which hampers efforts to understand and increase turnout. Previous research using individual-level National Election Survey (NES) validated data found demographic and regional patterns of overreporting. Since the NES no longer validates voting, individual-level data is no longer available and region is the only remaining determinant of systematic vote overreporting that can be studied. This paper uses census data to examine regional variations in vote overreporting in the 2000 and 2004 Presidential elections. After reviewing the actual turnout rate and how it increased from 2000 to 2004, I use both conventional ways to measure overreporting and examine variation by region. My results using both methods fit with past research indicating that overreporting is slightly higher in the South, but only in 2000.

Bringing Registration into Models of Vote Overreporting

Voting is a socially desirable act and a basic form of political participation in the United States. This social desirability sometimes leads respondents in surveys, such as the National Election Study (NES), to claim to have voted when they did not. The methodology of previous studies assumes that people only overreport voting and that the sample of potential overreporters (i.e., nonvalidated voters) is not systematically different from the sample of potential voters. In this research note, we explore several different ways of examining the determinants of overreporting at two different stages (registering and voting) and with a consideration for selection bias. Comparing the traditional probit model used in previous research with sequential and heckit probit models, we find that the determinants of overreporting registering and voting differ substantially. In addition, there is a significant selection effect at the registration stage of overreporting. We conclude with a discussion of contemporary implications for pre-election polling and the postelection analysis of survey data.

Response Privacy and Elapsed Time Since Election Day as Determinants for Vote Overreporting

Survey respondents have consistently been found to overreport their participation in political elections. Lots of research has been done about the sociodemographic correlates of vote overreporting, but only a few studies analyzed determinants which survey researchers have under their control in order to reduce the problem. Theoretical explanations have assumed memory failure and social desirability bias to explain overreporting. Taking these explanations as a starting point, we tested firstly whether asking retrospective questions about the participation in elections which date back longer in time leads to more overreporting. The second hypothesis is that ensured response privacy eliminates the need for positive self-presentation and thus reduces overreporting. Using data from a field experiment, we found that even when already a substantial time has elapsed between the election under consideration and the survey interview, increasing this time lag still increases the probability of vote reports. This was as well the case when the data was collected interviewer- rather than self-administered. Thus, conducting the survey interview as soon as possible after the political election and using an administration mode which ensures response privacy successfully reduces vote overreporting.

Political involvement and memory failure as interdependent determinants of vote overreporting

AbstractSurvey respondents have been found to systematically overreport their participation in political elections. Although the sociodemographic correlates of this response bias are well known, only a few studies have analysed the determinants predicted by two prominent theoretical explanations for vote overreporting: memory failure and social desirability (SD) bias. Both explanations have received empirical support in studies in which the probability of vote overreporting was found to increase (a) with the time between the election and the survey interview and (b) when respondents were politically involved to a larger extent. In the present paper, we argue that the effect of each of these determinants is not simply additive but depends on the value of the respective other factor. This interaction effect has been found with data from the American National Election Studies: The probability of vote overreporting increases significantly more strongly with the respondents' political involvement when more time has elapsed since the election day. Copyright © 2007 John Wiley & Sons, Ltd.

An experimental comparison of question forms used to reduce vote overreporting

Via telephone, a national probability sample of 1464 respondents randomly received one of three question versions of a voter turnout question in the months of December, January, and February, following the November 1998 Congressional elections in the United States. The long version form contained memory cueing techniques and face-saving response options, the short form, modeled after the 2000 American National Election Studies (ANES) question, included only the face-saving response options, and the standard form, modeled after ANES questions used before 2000, included neither. The long form led to significantly lower reported turnout in comparison to both the short and standard forms, indicating that the long form successfully reduced vote overreporting in comparison to the other question versions.

Reducing Vote Overreporting in Surveys: Social Desirability, Memory Failure, and Source Monitoring

Journal Article Reducing Vote Overreporting in Surveys: Social Desirablity, Memory Failure, and Source Monitoring Get access ROBERT F. BELLI, ROBERT F. BELLI Search for other works by this author on: Oxford Academic Google Scholar MICHAEL W. TRAUGOTT, MICHAEL W. TRAUGOTT Search for other works by this author on: Oxford Academic Google Scholar MARGARET YOUNG, MARGARET YOUNG Search for other works by this author on: Oxford Academic Google Scholar KATHERINE A. MCGONAGLE KATHERINE A. MCGONAGLE Search for other works by this author on: Oxford Academic Google Scholar Public Opinion Quarterly, Volume 63, Issue 1, May 1999, Pages 90–108, https://doi.org/10.1086/297704 Published: 01 May 1999

Can Changes in Context Reduce Vote Overreporting in Surveys?

This paper reports the results of two split-sample experiments designed to examine whether question context can reduce vote overreporting in surveys. The first experiment tests the effects of preceding the turnout item with a question about the location of the polling place. If respondents who overreport do not know where their polling place is, they should be less apt to report incorrectly about turnout after being asked the location of the poll. The second experiment tests the effects of preceding the vote item with a question about lifetime electoral behavior. If inaccuracy is due to respondents' wanting to present themselves in a favorable light, the opportunity to report past or usual good citizenship should reduce the pressure to claim participation in the last election. Much of the scholarly work on both electoral turnout and vote choice relies on self-reported behavior. In the typical election study, people are asked whether, and for whom, they voted. Yet many individuals do not report accurately about their political participation. In fact, one of the surest predictions in survey research is that more respondents will claim to have voted in postelection interviews than actually cast a ballot. Vote overreporting has been found in every major validation study. Record checks indicated that 13% of a sample of Denver residents falsely claimed to have voted in the 1948 presidential election (Parry and Crossley, 1950); 16% of a sample of New York City mothers receiving public assistance overreported their vote in the 1964 election (Weiss, 1968); and 12% of a nationwide sample of Americans inaccuSTANLEY PRESSER iS Professor of Sociology and Director of the Survey Research Center at the University of Maryland. The author thanks Dana Ostrow and Tim Triplett for research assistance and Johnny Blair for helpful comments. This paper was presented at the 1990 annual meeting of the American Association for Public Opinion Research,

Who Overreports Voting?

The effects of respondent characteristics with regard to the propensity of nonvoters to report that they voted are examined by analyzing the vote validation studies conducted by the University of Michigan Survey Research Center in 1964, 1976, and 1980. Previous research has suggested that vote overreporting derives from the respondent's wish to appear to engage in socially desirable behavior. This earlier research suggests that the only respondent characteristic that is strongly related to overreporting is race; measures of socioeconomic status and of general political attitudes are said to be at most weakly related to the tendency to exaggerate voting. These earlier conclusions are incorrect. We measure the extent of overreporting for the population “at risk” of overreporting voting: those who did not actually vote. Respondents most inclined to overreport their voting are those who are highly educated, those most supportive of the regime norm of voting, and those to whom the norm of voting is most salient—the same characteristics that are related to the probability that a person actually votes. Blacks are only slightly more likely to overreport voting than whites. The pattern of relations between education and vote overreporting is opposite what would be found if those who falsely reported voting fit the typical image of the uneducated, uninvolved, “acquiescent” respondent who is concerned primarily with pleasing the interviewer.