Choosing Imputation Models

Imputing missing values is an important preprocessing step in data analysis, but the literature offers little guidance on how to choose between imputation models. This letter suggests adopting the imputation model that generates a density of imputed values most similar to those of the observed values for an incomplete variable after balancing all other covariates. We recommend stable balancing weights as a practical approach to balance covariates whose distribution is expected to differ if the values are not missing completely at random. After balancing, discrepancy statistics can be used to compare the density of imputed and observed values. We illustrate the application of the suggested approach using simulated and real-world survey data from the American National Election Study, comparing popular imputation approaches including random forests, hot-deck, predictive mean matching, and multivariate normal imputation. An R package implementing the suggested approach accompanies this letter.

The Effect of Partisan Representation at Different Levels of Government on Satisfaction with Democracy in the United States

In this paper, we analyze how variations in partisan representation across different levels of government influence Americans’ satisfaction with the democracy in the United States. We conduct two survey experiments and analyze data from the 2016 American National Election Study postelection survey. We find that Americans are the most satisfied with democracy when their most preferred party controls both the federal and their respective state governments. However, we also find that even if an individual’s least preferred party only controls one level of government, they are still more satisfied with democracy than if their most preferred party controls no levels of government. These findings suggest that competition in elections across both the national and state government, where winning and losing alternates between the two parties, may have positive outcomes for attitudes toward democracy.

Experimental Measurement of Misperception in Political Beliefs

Recent research suggests widespread misperception about the political views of others. Measuring perceptions often relies on instruments that do not separate uncertainty from inaccuracy. We present new experimental measures of second-order political beliefs. To carefully measure political (mis)perceptions, we have subjects report beliefs as probabilities. To encourage accuracy, we provide micro-incentives for each response. To measure learning, we provide information sequentially about the perception of interest. We illustrate our method by applying it to perceptions of vote choice in the 2016 presidential election. Subjects made inferences about randomly selected American National Election Study (ANES) respondents. Before and after receiving information about the other, subjects reported a probabilistic belief about the other’s vote. We find that perceptions are less biased than in previous work on second-order beliefs. Accuracy increased most with the delivery of party identification and report of a most important problem. We also find evidence of modest egocentric and different-trait bias.

Institutional Context and Accountability for Political Distrust

This project investigates how voters hold government electorally accountable for perceived untrustworthiness, and particularly how this accountability is conditioned by institutional context. Studies show that political distrust is associated at least as much with attitudes toward the legislative branch as with attitudes toward the executive. With this in mind, I consider two contextual factors. First, whether a party that controls both branches of government may affect the degree to which its candidates face electoral accountability for distrust in government. Second, whether voters who are being asked to elect a representative to the legislative branch as opposed to the executive may affect which institution’s ruling party is more likely to be held accountable. I analyze these relationships using survey data from the American National Election Study covering over half a century. The results demonstrate that institutional context conditions both when and whom voters hold accountable for their distrust in government.

That Woman from Michigan: How Gender Resentment Shapes the Efficacy of Stay-at-Home Policies

The United States has the highest number of COVID-19 cases, yet many Americans have responded indifferently toward policies designed to combat the spread of the virus. While nearly all 50 states have implemented some type of stay-at-home policy to encourage social distancing, there has been high variation in the degree of compliance. We argue that this variance is partly driven by gender resentment. Gender resentment reduces trust in female political leaders and thus decreases compliance with government policy and recommendations. Using data from SafeGraph and the 2016 American National Election Study, we demonstrate that the effect of stay-at-home policies on social distancing is reduced when gender resentment increases in states with female leaders. However, when gender resentment is low, there is no difference in the effect of policies on behavior. This research has important implications for understanding unseen barriers that can mediate the efficacy of female political leaders.

Citizens as Consumers: White Imagined Futures

This study examines how racial ideologies directly influence perceptions of the economy–specifically, how racial colorblindness ideology, a component of white supremacy ideology, is mediated through market fundamentalism. These findings challenge widely held beliefs that perceptions of the economy are solely driven by economic factors such as family income and employment status. My theoretical approach examines how whiteness and colorblindness shape and distort white consumers’ perception of the economy. I develop the framework of white imagined futures. White imagined futures assume a white-owned and white-dominated destiny of wealth and economic success based on an economy that is built to serve white people above all other racial groups. I utilize the American National Election Study due to its measures of racial colorblindness and perception of the economy. I pooled a subsample of the American National Election Study from 2000 to 2016 and conducted an OLS regression and regression-based causal mediation analysis to test how racial and economic ideologies influence perceptions of the economy. The study finds that racial colorblindness serves to stratify present perceptions of the economy and notes how racial colorblindness ideology is also being conveyed through market fundamentalism ideologies. The study also demonstrates that whites’ racial ideology has a role in shaping their perceptions of the economy. This evidence supports claims that white supremacy ideology, as defined here, is embedded within markets. Moreover, this study provides evidence that challenges the notions that economic perceptions are solely tied to a person’s economic reality (e.g. income, employment status). As a consequence, we can begin to interrogate ‘pocketbook’ or economic policy talk as a racialized discourse.