Thesis (M.P.A.)--Kutztown University of Pennsylvania, 1993. / Source: Masters Abstracts International, Volume: 45-06, page: 2940. Typescript. Includes bibliographical references (leaf 69).

Thesis (Ph.D.)--University of Pennsylvania, 1901. / Reproduction of original from Harvard Law School Library. "Bibliography": p. [62]-63.

Thesis (M.A.)--University of Missouri-Columbia, 2004. / Typescript. Includes bibliographical references (leaves 91-97). Also available on the Internet.

Thesis (M.A.)--University of Missouri-Columbia, 2004. / Typescript. Includes bibliographical references (leaves 91-97). Also available on the Internet.

This dissertation presents the results of a series of large-N, demographically representative survey experiments conducted at different stages of the 2020 presidential election cycle, designed to test the effects of highlighting intraparty policy conflict on subjects’ political beliefs. I find politicians of both major political parties are able to persuade followers to take on counter-party policy positions with limited electoral risk, and that these persuasive effects are enduring, still detectable nine months after treatment. While subjects updated their own policy positions in response to treatment, they did not update the policy positions they prefer when selecting among hypothetical candidates, in contrast to issue voting theorists predictions. While politicians appear to be far more effective opinion leaders than parties, therefore, their persuasive abilities may not significantly alter the shape of the partisan electorate as faced by other candidates. These findings refine our scholarly understanding of individual politicians as opinion leaders in the contemporary United States, and demonstrates the challenges political parties face in checking their popular politicians.

In this dissertation project, I make three separate contributions on how we can improve aggregate election forecasting models with respect to modeling choices, interpretability, and performance. Two of the three papers are applications to particular cases, the U.S. and France specifically, while the third points to a cross-national pattern in polling errors. The first paper addresses how we can make more reasonable prior choices for key parameters – such as the variability of non-sampling error – by using past pre-election polls. I showcase this approach on U.S. presidential elections. The second paper shows how to create and aggregate predictions in a multi-party contest while keeping the individual forecasts intact. This is useful to see convergences or divergences in the forecasts which might affect our confidence in the aggregate prediction. I develop a new aggregate forecasting model for French presidential elections to demonstrate this idea. The last paper shows and investigates a pattern in polling errors. We see that across multiple countries and electoral systems, polling errors favor the lesser party in two-party contests, i.e. polling errors favor Democratic candidates in Republican states and vice versa. We demonstrate a simple adjustment procedure based on this pattern to reduce the mean absolute polling error. We achieve a 16% reduction in the 2016 U.S. presidential election.

Indiana University-Purdue University Indianapolis (IUPUI) / The impact of new technology on the current presidential campaign has prevailed. A small but fundamental change quietly took place in the candidate’s website—Barack Obama’s official campaign blog. The campaign is now operating two sub-blogs at the same time, the Obamablog (also known as the Obama HQ blog) and the Community Blog. The former becomes a must-have tool in a political campaigner’s strategy, whereas the latter, which allows visitors to actually write, publish, and manage posts, is novel. This new function seems an audacious step up from the rest of the blogs of this kind since the 2004 presidential election because it gives citizen users freedom to express their own ideas that could put the campaign on an impromptu situation to respond.

This is a study of Korean presidential elections. Its purpose is to determine how Koreans voted in the 1992 and 1997 presidential elections and to examine the factors that contributed to winners. In addition, the study compares the two elections by developing three models: candidate choice, voter turnout and political interest models. Using post election data from the Korean Social Science Data Center a multinomial logit regression was used in the candidate choice model. It shows that Korean voters selected their candidates mainly in terms of interest in the elections, age, orientation toward the governing or opposition parties, the regional effects of the Southwest (Honam) and the Southeast (Youngnam), and the evaluation of merged parties in 1992 or a united candidacy of parties in 1997. A Monte Carlo simulation was also employed to test the traditional assumption of candidate strength. It indicates that Kim Young-Sam had a more cohesive support from his older supporters in the 1992 election while Kim Dae-Jung had a greater cohesive support from his older supporters in the 1997 election. Both Kim Young-Sam's and Kim Dae-Jung's loyalists were crucial to the winning candidates in the 1992 and 1997 elections respectively. How did people vote? To address this question a logit analysis of voter turnout was employed. Comparing the 1997 election to that of 1992 the findings suggest that low-probability voters in 1997 had: low efficacy, a negative evaluation of the Central Election Management Commission, claimed to be independent, young, and lived in areas other than Youngnam and Honam. Their lower turnout was a significant factor in the opposition candidate, Kim Dae-Jung's election. Finally, since political interest is closely related to political participation, an ordered logit model of political interest was developed. The results showed that the media and popularity of major candidates significantly contributed to Korean voters' interest in the elections.

This dissertation examines the use of statistical models for prediction. Examples are drawn from public policy and chosen because they represent pressing problems facing U.S. governments at the local, state, and federal level. The first five chapters provide examples where the perfunctory use of linear models, the prediction tool of choice in government, failed to produce reasonable predictions. Methodological flaws are identified, and more accurate models are proposed that draw on advances in statistics, data science, and machine learning. Chapter 1 examines skyscraper construction, where the normality assumption is violated and extreme value analysis is more appropriate. Chapters 2 and 3 examine presidential approval and voting (a leading measure of civic participation), where the non-collinearity assumption is violated and an index model is more appropriate. Chapter 4 examines changes in temperature sensitivity due to global warming, where the linearity assumption is violated and a first-hitting-time model is more appropriate. Chapter 5 examines the crime rate, where the independence assumption is violated and a block model is more appropriate. The last chapter provides an example where simple linear regression was overlooked as providing a sensible solution. Chapter 6 examines traffic fatalities, where the linear assumption provides a better predictor than the more popular non-linear probability model, logistic regression. A theoretical connection is established between the linear probability model, the influence score, and the predictivity.

"The present investigation was concerned with college students' perceptions of candidates in the 1972 Presidential Election."--[1].