Accounting for Complex Survey Designs: Strategies for Post-stratification and Weighting of Internet Surveys
Erin Hartman and Ines Levin
This chapter focuses on methods for analyzing data from Internet surveys with complex survey designs in order to draw inferences that can be generalized to a target population of interest. We first review the central design issues and approaches for dealing with representativeness challenges that researchers commonly face when using online polling for persuasion research. Then, using data from a survey experiment on support for immigration reform, we demonstrate the importance of the careful choice of auxiliary information used when constructing weights for ensuring the generalizability of findings from non-representative Internet surveys.
Ann N. Crigler and Parker R. Hevron
Whether political observers and participants applaud or decry the presence of emotions in political decision-making, scholars have begun to view the relationship between affect and reason as a key component of decision-making. This chapter provides an overview of the research on affect and political choice. The authors argue that emotions undergird acts of political choice, not simply as additional variables to explain preferences or actions but also as integral to the processing of information and decision-making. They briefly define affect, emotion and mood and outline some of the methodologies commonly used to measure each of the four emotion functions that are central to political communication and choice. These four functions of emotion – expressive, perceptual/attentional, appraisal, and behavioral – are discussed in relation to political decision-making.
Public opinion’s role in shaping governmental actions is a central concern of democracy, yet the absence of systematic state-level survey data has inhibited analyses of public opinion at the subnational level. This essay traces the evolution of studies of public opinion at that level, first reviewing studies using surrogates derived from demographic variables. It next considers methodologies that develop state-level opinion from aggregated national samples. Finally, it discusses recent efforts to develop state-level opinion measures using post-sample stratification integrating limited survey data with demographic variables. There is evidence of significant cross-sectional and temporal variation in public opinion and policy across and within the states. Research on subnational public opinion once hinged on assumptions about opinion surrogates, but is now based on abundant and progressively rigorous opinion data. These studies reveal that public opinion plays an enormous role in subnational politics, with effects varying across issues, contexts, and conditions.
This chapter reviews the state of the art in at-a-distance analysis. This methodology originated in attempts by psychologists and students of policy-making and international relations to understand and predict a national or government’s policy choices by studying the verbal behaviour of key government leaders. It has since widened into an array of methods that have also found use in areas such as candidate assessment. Several key methods are presented, as are some of the key critiques and rebuttals around the issue of inferring personality characteristics from speeches and then using those to explain government policies and state behaviours. The chapter ends by critically assessing the state of the art in the field and by presenting some possible and needed advances.
This chapter reviews the historical development of the genre of biography in relation to the social sciences, and discusses the debates about its utility in the study of leadership. Taking key examples, it explores the contrast between the ‘common-sense, humane tradition’ said to be the bedrock of biography, and more theoretically informed approaches (especially leadership typologies, psychobiographies, and the ‘interpretive turn’) in the ways that questions of leadership are addressed. Developments in biographical methodology are a core concern. Biography, it is argued, need not be driven by an ‘individual journey’ but can be oriented to questions germane to political enquiry, especially questions of leader efficacy, achievement, or dysfunction.
Matthew Cawvey, Matthew Hayes, Damarys Canache, and Jeffery J. Mondak
Levels of interpersonal and political trust undoubtedly ebb and flow in response to external stimuli. Despite the variability in one’s environment, there is good reason to believe that interpersonal and political trust also originate from individual characteristics. In this chapter, we focus on the impact of biology and personality on trust. Biological factors and personality traits constitute relatively stable individual differences that influence perceptions, evaluations, and orientations toward the social and political world. Research on trust has examined both of these influences, and we review this literature below. The first section considers the role of biology in shaping trust, and the second examines trust as a dimension of personality and as an individual orientation that can be shaped by personality. We then present a brief statistical analysis of the impact of personality traits on interpersonal and political trust. The last section summarizes the discussion and suggests avenues for future research.
Citizens, Elites, and Social Media: Methodological Challenges and Opportunities in the Study of Persuasion and Mobilization
Philip Habel and Yannis Theocharis
In the last decade, big data, and social media in particular, have seen increased popularity among citizens, organizations, politicians, and other elites—which in turn has created new and promising avenues for scholars studying long-standing questions of communication flows and influence. Studies of social media play a prominent role in our evolving understanding of the supply and demand sides of the political process, including the novel strategies adopted by elites to persuade and mobilize publics, as well as the ways in which citizens react, interact with elites and others, and utilize platforms to persuade audiences. While recognizing some challenges, this chapter speaks to the myriad of opportunities that social media data afford for evaluating questions of mobilization and persuasion, ultimately bringing us closer to a more complete understanding Lasswell’s (1948) famous maxim: “who, says what, in which channel, to whom, [and] with what effect.”
Terrorism is often understood to be a cultural phenomenon involving different and competing ideological perceptions of social and political realities. Hence the terrorists themselves, those who fight terrorism, and the mass media all tend to invoke cultural variables to make a sense of violent terrorist actions. In this context one often encounters references to “the clash of civilizations” or “religious wars.” Nevertheless social scientists have largely discredited such simplistic accounts and have made clear that culture plays a much more complex role in terrorism. In this chapter I critically review the three leading cultural and anthropological perspectives on terrorism: the neo-Durkhemian perspectives, interactionism, and the anti-foundationalist approaches. I argue that culturalist perspectives contribute substantially towards understanding of terrorism but they also show some explanatory weaknesses. To remedy these pitfalls I provide an outline for the alternative, longue durée, historical-sociological model of terrorism analysis.
Seth K. Goldman and Stephen M. Warren
To answer many of the most pressing questions in the social sciences, researchers need reliable and valid measures of media exposure that can be implemented in surveys. Despite considerable effort, however, substantial disagreement remains about how best to measure this key concept. This chapter critically reviews the debate surrounding traditional frequency measures of exposure to “news” and contemporary list-based measures of political media exposure. It also evaluates the related debate over how best to capture the effects of media exposure with different observational research designs. Overall, the chapter finds that although substantial progress has been made in measurement and research design, both issues require more attention if scholars are to understand the many and varied effects of media exposure.
David Brulé, Alex Mintz, and Karl DeRouen
This chapter focuses on the decision-making models and biases used to explain the decisions of political leaders with a particular emphasis on foreign-policy decisions. We summarize some of the key debates and criticisms of the various approaches. Various models and theories are considered: rational choice theory, bounded rationality/cybernetic, organizational process model, bureaucratic politics model, prospect theory, and poliheuristic theory. Several biases are discussed: personality and beliefs, groupthink, polythink, and summary approaches. We conclude with a detailed discussion of the rational–cognitive debate as well as some thoughts for future progress in decision-making analysis.
Douglas J. Wiebe and Christopher N. Morrison
Achieving accurate measurements of mobility and where people spend time is an essential step toward understanding how environments influence people’s impressions, actions, well-being, and health. But identifying where people are located in space and time and drawing from these data conclusions about what people actually experience is a challenge. Advances in communication technologies are creating possibilities for research today that even recently would not have been possible. This chapter reviews a classic study in the field of mobility pattern research, demonstrates the interest of mobility patterns to investigators of geography and health, and describes how geographic information systems and Global Positioning Systems are being used to better understand the complex relationships between people’s physical locations and health outcomes. The chapter concludes with predictions about how advances in communication technology will shape future research.
Andrew Flanagin and Miriam J. Metzger
The rich research heritage on source credibility is fundamentally linked to processes of political communication and the provision of political information. Networked digital technologies, however, have recently complicated the assessment of source credibility by modifying people’s ability to determine source expertise and trustworthiness, which are the foundations upon which credibility evaluations have traditionally rested. This chapter explores source credibility in online contexts by examining the credibility of digital versus traditional channels, the nature of political information conveyed by social media, and the dynamics of political information online. In addition, this chapter considers related research concerns, including the link between credibility and selective exposure, the potential for group polarization, and the role of social media in seeking and delivering credible political information. These concerns suggest challenges and opportunities as information consumers navigate the contemporary information environment in search of the knowledge to make them informed members of a politically engaged citizenry.
Michael S. Lewis-Beck and Charles Tien
This article offers a new way to evaluate the pros and cons of predicting US presidential elections: the long view versus the short view. Election forecasters who take the long view stress electoral theory and lead time, examining model performance over several contests. For this view, an overarching goal remains knowledge of how the electoral process works. In contrast, forecasters who take the short view stress accuracy exclusively. Forecasts are made repeatedly, especially near the election. The short view depends increasingly on polls until nothing else matters. The short view also risks setting back the study of elections, for example, fostering the idea of an unstable, even volatile electorate, even though American voters have shown great stability. Finally, the short view forgets the lesson that most variation in national election outcomes can be predicted, even explained, by established rules of political behavior.
Eeva Luhtakallio and Nina Eliasoph
The ethnographic approach has particular potential for studying political communication through enlarging understandings of political institutions and expanding definitions of “politics.” First, widening institutional understanding takes advantage of ethnography’s capacity to open windows that traditional analysis of political institutions leaves shut. Second, ethnography is uniquely able to examine new forms of engagement that people have not yet defined as “politics.” Third, studying political communication ethnographically means expanding the modes of communication and activity examined to include nonverbal and virtual communication. Politics is one of the principal arenas in which “culture” unfolds and becomes observable, yet in ways that are not limited to political institutions or decision-making practices. Common to political ethnographies is the capability to show how “how” and “why” are linked: how a political process or practice takes place enables finding out why it does.
Anthony M. Salvanto
This chapter considers exit polls from a researcher’s perspective, pointing out how it compares in terms of operation and sampling to more conventional pre-election polling and speculating about what future exit polling in the United States might look like. The chapter discusses the practical steps taken today to conduct post-election exit polling in the United States. Taken as a research study in itself, it discusses how exit polling might adapt over time in the context of the explosion in new data sources, lists, and new technologies, and—importantly—accounting for changes in the way Americans go to the polls, which is increasingly not on Election Day at all, but in the days or weeks to it or by mail or absentee ballot.
This chapter provides an overview of the experimental study of leadership historically, describing a few seminal studies that outline the central concepts and debates in the field. Very little work has been done in this area involving real political leaders because of ethical and logistical constraints. However, some experimental work on the nature of followership appears relevant, because public perception often determines who becomes elevated to positions of leadership. The chapter then describes some critical challenges and opportunities confronting the use of experiments to investigate political leadership, including the many different kinds of leadership that exist, and how leadership may change across domains of decision-making. A discussion of some possible future directions in this area concludes the chapter, including further exploration of the biological basis of leadership.
Jacob N. Shapiro
A large game-theoretic literature has developed to study terrorism. This literature has made significant contributions to the understanding of terrorism by providing a useful guide to parsing the empirical record, by helping to illuminate how seemingly puzzling behavior by terrorist organizations can be understood as the outcome of strategic interactions, and by providing some guidance to policy. Specifically, the formal literature helps provide plausible logically coherent explanations for seemingly anomalous patterns in the real world including: (1) there is more terrorism when the economy is bad, but terrorists themselves tend not to be poor; (2) terrorist groups often keep lots of paperwork, but sometimes they operate with little formal organization; (3) many states appear to tolerate low levels of terrorism they could stamp out and counterterrorism spending seems to over-emphasize publicly observable actions; (4) opposition groups often choose terrorism despite the fact that it seldom succeeds; and (5) bargaining with terrorists rarely succeeds in ending conflict. This brief piece focuses on explaining how the formal literature provides useful guidance for understanding these patterns.
How Can Computational Social Science Motivate the Development of Theories, Data, and Methods to Advance Our Understanding of Communication and Organizational Dynamics?
It is almost a decade since the article “Computational Social Science” was published in Science (Lazer et al., 2009). That article advocated for computational social science as a promising new arrow in the quiver for understanding and enabling social systems. The chapters in this section, and indeed in this book, are a testament to the decade-long trajectory of this movement. The chapters in this section also provide an opportunity to reflect on how computational social science can motivate the development of theories, data, and methods to advance understanding of current and emerging forms of communication and organizational dynamics. This chapter reviews some of the progress made on these dimensions and points to chapters in the section that serve as exemplars.
Dan Cassino, Milton Lodge, and Charles S. Taber
This chapter reviews recent work on implicit political attitudes, detailing how, when, and why unconscious processes impact the explicit expression of political beliefs, attitudes, and preferences. The authors begin by discussing thresholds of awareness, defining implicit attitudes and how the circumstances under which they reach conscious awareness. The ubiquity of unconscious effects in everyday life is considered, and two research paradigms for measuring implicit attitudes are discussed. The resulting dual-process model, in which influences can be either conscious or subconscious, allows us to understand how sensory input works its way through the mind to influence attitudes and behaviors in ways that are rarely evident to the individual. These influences often include factors that the individual would never consider as being important, but nevertheless hold enormous power over effortful decision-making.
This article discusses left–right orientations; the left–right dimension has been described as a ‘shorthand’ device that helps facilitate comparisons through space and time. It first examines the acceptability of left and right and the referents of left and right. The last two sections of the article focus on the blurring and the resilience of left and right. It is noted that the left–right schema was able to offer something in structure and substance that helped facilitate efficient communication and orientation.