Racial and other demographic imputation is necessary for many applications, especially in auditing disparities and outreach targeting in political campaigns. The canonical approach is to construct continuous predictions -- e.g., based on name and geography -- and then to $\textit{discretize}$ the predictions by selecting the most likely class (argmax). We study how this practice produces $\textit{discretization bias}$. In particular, we show that argmax labeling, as used by a prominent commercial voter file vendor to impute race/ethnicity, results in a substantial under-count of African-American voters, e.g., by 28.2% points in North Carolina. This bias can have substantial implications in downstream tasks that use such labels. We then introduce a $\textit{joint optimization}$ approach -- and a tractable $\textit{data-driven thresholding}$ heuristic -- that can eliminate this bias, with negligible individual-level accuracy loss. Finally, we theoretically analyze discretization bias, show that calibrated continuous models are insufficient to eliminate it, and that an approach such as ours is necessary. Broadly, we warn researchers and practitioners against discretizing continuous demographic predictions without considering downstream consequences.

Prediction of individual's race and ethnicity plays an important role in social science and public health research. Examples include studies of racial disparity in health and voting. Recently, Bayesian Improved Surname Geocoding (BISG), which uses Bayes' rule to combine information from Census surname files with the geocoding of an individual's residence, has emerged as a leading methodology for this prediction task. Unfortunately, BISG suffers from two Census data problems that contribute to unsatisfactory predictive performance for minorities. First, the decennial Census often contains zero counts for minority racial groups in the Census blocks where some members of those groups reside. Second, because the Census surname files only include frequent names, many surnames -- especially those of minorities -- are missing from the list. To address the zero counts problem, we introduce a fully Bayesian Improved Surname Geocoding (fBISG) methodology that accounts for potential measurement error in Census counts by extending the naive Bayesian inference of the BISG methodology to full posterior inference. To address the missing surname problem, we supplement the Census surname data with additional data on last, first, and middle names taken from the voter files of six Southern states where self-reported race is available. Our empirical validation shows that the fBISG methodology and name supplements significantly improve the accuracy of race imputation across all racial groups, and especially for Asians. The proposed methodology, together with additional name data, is available via the open-source software WRU.

We provide the largest compiled publicly available dictionaries of first, middle, and last names for the purpose of imputing race and ethnicity using, for example, Bayesian Improved Surname Geocoding (BISG). The dictionaries are based on the voter files of six Southern states that collect self-reported racial data upon voter registration. Our data cover a much larger scope of names than any comparable dataset, containing roughly one million first names, 1.1 million middle names, and 1.4 million surnames. Individuals are categorized into five mutually exclusive racial and ethnic groups -- White, Black, Hispanic, Asian, and Other -- and racial/ethnic counts by name are provided for every name in each dictionary. Counts can then be normalized row-wise or column-wise to obtain conditional probabilities of race given name or name given race. These conditional probabilities can then be deployed for imputation in a data analytic task for which ground truth racial and ethnic data is not available.

The Fox News Voter Analysis (FNVA), conducted in partnership with the Associated Press, provides a comprehensive look at voting behavior, opinions and preferences as America votes. It is based on surveys conducted in all 50 states by NORC at the University of Chicago, as well as actual voting results by county collected by The AP. The FNVA survey encompasses interviews with an estimated 140,000 registered voters and is conducted Oct. 26 to Nov. 3, and continues through the end of voting on Election Day. Both voters and nonvoters are interviewed to provide a full picture of the election, including why some Americans voted while others stayed at home. FNVA combines respondent interviews from three data sources: (1) a random sample of registered voters drawn from state voter files; (2) a sample of self-identified registered voters conducted using NORC's probability-based panel, which is designed to be representative of the U.S. population; and (3) a sample of self-identified registered voters selected from nonprobability online panels.

After that election, Laura Quinn moved mountains to raise the funds, assemble the team, and lead the overhaul of the Democratic Party's web, data, and analytics infrastructure. The Republicans were able to conduct national targeting in 2000 because they had built a consolidated voter file covering all 50 states. As a key part of the overhaul, and with just a few years of effort, Lina Brunton miraculously consolidated the Democratic Party's voter files, which had previously been controlled individually by the state parties. Between 2003 and 2008, the Democratic Party developed significant infrastructure on top of this standardized data substrate.

Imagine the difference between a buffalo stampede and a cheeseburger. Both are tasty sources of protein. The difference lies in their requisite culinary tools. Predictive Analytics (PA) is the buffalo stampede of quantitative research: data is big, fast, and shaggy. Interactive Analytics (IA) is a cheeseburger: structured, convenient, and easy to grill.