Qualitative and quantitative methods can help make sense of the range of meanings connected with concepts, mapping usage and clarifying alternatives so people can position their intended meanings with respect to the space of existing alternatives. Likewise, qualitative and quantitative methods can help clarify where measurement problems come from, and can be used together to turn abstract ideas about measurement error into far research conversations about how social dynamics work to produce social science measures in the first place. Qualitative and quantitative approaches to conceptualization and measurement involves familiar tensions between deep attention to texts versus breadth and representation across a broader collection; between human comprehensibility and optimal work with complex, multidimensional mathematical and linguistic representations; and between familiarity and precision. Good research designs, like those discussed in this chapter, mitigate these tensions and emphasize the strengths of both methods.

How can regression-type studies, which try to get causal inferences by controlling for variables until whatever is left is plausibly a causal relationship, benefit as much as possible from qualitative research? This chapter offers three qualitative research designs that can help test and improve quantitative causal inferences based on control variables. First, we consider process-tracing designs that seek to discover previously unknown confounding variables that can be added as new control variables, thereby refining and improving the statistical model. Second, we discuss process tracing that seeks to confirm that control variables have a direct connection to the outcome variable, and therefore are relevant controls. Third, we discuss process tracing to check whether control variables might be posttreatment and therefore at least partially harmful. Finally, we provide a demonstration of the kind of iterated interaction that we have in mind between statistical efforts at causal inference and qualitative research to learn more about the assumptions behind the model, involving the relationship between labor union strength and the prevalence of employment law across U.S. states.

How can mixed-method research add value to experiments? There is much to learn by adding qualitative components to experiments that can test for problems related to measurement; networks and spillover among experimental subjects; issues related to the meaning of treatments, outcomes, and other aspects of the experiment for participants; the exhaustiveness of the intended causal content of the treatment; and moderation effects related to subgroups of participants, or to differences across implementations of an experiment in divergent contexts. Some of these areas relate to the goal of theoretical generalization from the initial experiment, but most of them also have connections with the meaning and quality of the causal inference for the experiment at hand.

This chapter summarizes key themes from the book as a whole and offers general concluding thoughts.

Process tracing methods, which involve ways of using information within a single case to think carefully about questions of social-science theory, have become one of the leading qualitative methods in political science and related fields. Can mixed-method approach to process tracing work without destroying the qualitative logic of the method? This chapter argues that two distinct forms of process tracing, involving testing of existing causal theories and discovery of new theories, each have room for mixed-method strategies. We show that qualitative components can become steps within a testing-based process tracing argument, and offer guidelines for structuring such studies. We then offer a novel approach to combining machine-learning techniques like LASSO regression with discovery-based process tracing, illustrating the design with an application to the rise in visibility of U.S. far right broadcaster Alex Jones.

How can quantitative methods support case studies in general? One common task in case-study research is presenting audiences with a large collection of texts. Text-as-data methods may facilitate this task by summarizing the overall collection more quickly and understandably than we can usually do ourselves, and by locating individual documents within the collection. We offer an application, showing how text-as-data methods effectively summarize the large collection of legal documents available regarding defendants in cases related to the January 6th invasion and facilitate case-study exploration and understanding of specific individuals. We also discuss how mixed-method approaches may save time and resources as a way of moving across levels of analysis within a case-study design. We wind up the chapter by raising a note of caution regarding common attempts to use statistics as a test of generalizability for case studies and regarding the somewhat less common but still recurrent designs that mix game theory and qualitative research. Both of these approaches can work, and can offer insights, but both are harder than they may initially appear.

Research designs can combine qualitative, quantitative, experimental, and data-science methods through careful planning, attention to details and assumptions, and methodological execution. This chapter introduces the book's perspective, arguing that designs that combine methods carefully and with close attention to their details will outperform designs where two or more methods are carried out in parallel and then compared. The chapter also considers a range of practical and philosophical questions related to whether it makes sense to combine methods. Is one method always best, such that it isn't worth trying? Do methods speak fundamentally different languages, such that there is no point? Are methods and problems inextricably linked, such that the question is irrelevant? We argue against each of these views.

Chapter 5 examines Swift’s major foreign policy writings, particularly the Conduct of the Allies and the History of the Four Last Years of the Queen. It differentiates his neoclassical balance-of-power theory – which pointed toward the need to negotiate peace – from modern, nonnormative, militaristic, and pseudoscientific versions of the theory, which his contemporaries used to justify continuing the war. Swift condemned militarism even when exhibited by his own country. He opposed the attempted subjugation and domination of an enemy country as unwise policy that would lead to international power imbalances and unintended consequences, and thus threaten both domestic constitutionalism and international security. He adopted a mixed qualitative-quantitative method of argument and revealed the conceptual flaws of the quantitative or military-statistical approach adopted by the pro-war Whigs. While his arguments facilitated the Peace of Utrecht (1713), French delays in implementing the peace terms left Swift with little more than satire in his last Tory pamphlets.

With legendary regionalisms like ‘r-dropping’, fronted palm vowels, ‘broad-a BATH vowels, and other features, New England has played a key role in the historical development of English in North America. Historically, the six small states of New England (Massachusetts, Rhode Island, Connecticut, Maine, New Hampshire, Vermont) have had an outsized influence on American English. Their modern sociolinguistic and geographic boundaries still reflect colonial-era settlement patterns from centuries past. Many prior studies on New England English have focused on phonological patterns and changes, but scholars have also examined regional grammatical patterns, lexical variation and change, and also the continuing influence of local Native American words on English. In fact, modern linguists have access to ninety years of detailed fieldwork reports on regional New England dialect features, dating as far back as the 1930s and continuing to the present era. Using this wealth of intergenerational data, the present chapter takes a historical perspective that traces the roots and development of New England English into the present time.

This chapter examines the arguments Robert Adcock and David Collier developed in their 1999 and 2001 essays “Democracy and Dichotomies” and “Measurement Validity.” He encourages conversation across methodological communities and explores how “dubious dualisms” hinder such conversation. Specifically, the chapter critically explores both the qualitative/quantitative dualism Adcock and Collier engaged and the positivist/interpretive dualism emphasized in certain responses to their articles. The chapter argues that leaving both dualisms behind can help us to rethink shared standards, not as a denial of methodological differences but as the pursuit of a network of bridges across these differences.

This chapter provides details of the molecular techniques in use to detect viral RNA and DNA, including PCR, NAAT, nested PCR, multiplex PCR, real time PCR, quantitative PCR, LAMP, TMA, microarrays, sequencing and point-of-care tests and their utility.

This chapter focuses on quantitative EEG processing, also known as EEG trend analysis. These types of algorithms process raw EEG data in a quantitative way, and display the data in more compressed forms that may be easier for the amateur EEG reader to interpret. Specific QEEG algorithms described in this chapter include amplitude integrated EEG, FFT spectrogram, rhythmicity spectrogram, asymmetry indices, and seizure detectors. Specific roles for QEEG covered include seizure detection and detection of focal cerebral ischemia.