This chapter addresses diagnostic studies, which evaluate the performance of clinical tests and tools used to detect disease. The concepts of sensitivity, specificity, positive predictive value, and negative predictive value are explained in detail, highlighting how these metrics guide clinicians in interpreting test results. The role of prevalence in influencing predictive values is emphasised, underlining the need to consider population context when applying diagnostic tools. Receiver operating characteristic (ROC) curves are introduced as a method to assess test performance across varying thresholds, enabling identification of optimal cut-off points. The chapter also explores likelihood ratios, which integrate sensitivity and specificity into a single measure to support diagnostic decision-making. Strengths of diagnostic studies include their direct clinical relevance and utility in evaluating new technologies or biomarkers. Limitations include potential spectrum bias, verification bias, and challenges in defining an appropriate gold standard. Examples from infectious disease testing and mental health screening illustrate the practical implications of study design and interpretation. The chapter concludes by positioning diagnostic research as critical for improving clinical decision-making, resource allocation, and patient outcomes. This chapter maps to syllabus sections 3.2.5–3.2.8, which cover diagnostic accuracy measures including sensitivity, specificity, predictive values, likelihood ratios, and ROC curves.

This chapter provides a critical overview of how L2 researchers have used measures of lexical and phraseological complexity, with a special focus on their definition and operationalization. Lexical and phraseological complexity are often measured in terms of diversity (the number of different words or multi-word units respectively) and sophistication (the number of ‘sophisticated’ words or multi-word units, with ‘sophisticated’ variously understood as less frequent, more specialized, or in the case of phraseological sophistication, as more strongly associated word combinations). With the development of natural language processing (NLP) tools such as the Lexical Complexity Analyzer (Lu, 2012) or the Tool for the Automatic Analysis of Lexical Sophistication (Kyle et al., 2018), L2 researchers can now analyze lexical complexity in L2 English texts using dozens or even hundreds of measures with a click of a button. However, unresolved questions remain: How accurate, reliable, and valid are these measures across learner samples and research contexts? Can they assess L2 proficiency across registers? How should measures be selected from the many available? By contrast, do the current, limited set of measures of phraseological complexity represent the full construct, or is there a need to develop for further development?

Capability is the informational focus of the theory of justice developed by Sen. This means that, according to this theory, people’s relative advantages and disadvantages should be assessed in terms of their capability. I present and discuss some of the investigational requirements that this entails. A key challenge here is that a capability relates not only to what people actually end up being and doing that is of value to them (achieved functionings) but also to what they are in fact able to do, irrespective of whether they choose to realise such an opportunity. This seems to produce a paradox in Sen’s writings – capability assessment being quite complex on the one hand but surprisingly simple on the other. Drawing on what Sen has to say on the relationship between capability and human rights, I offer a possible explanation for the apparent paradox. Two case studies are given, showing some methods that may be used to assess capability and how the validity and relevance of the resulting evidence can be assessed. I conclude by suggesting that Sen’s capability approach can be considered a realist and non-ideal theory of justice and that specific approaches to capability assessment should be in line with this.

This chapter builds on two papers published in 2016 that were the first to define and operationalise sustainable employability (SE) in a questionnaire (the CSWQ) in terms of the Capability Approach (CA), published by a consortium of the authors of this chapter. In this chapter, we first briefly summarise the research reported in these papers and then present research that has been conducted since then. We update and further develop the relationship between SE and the CA. In reporting follow-up research since 2016, we first present the results of a Delphi survey among experts and discuss some constructive critical remarks that have been published in the scientific literature. We discuss the conceptual and empirical steps taken since 2016. We distinguish between studies with a focus on 1) methodological aspects, both conceptual and measurement properties of the capability instrument, 2) specific target groups and 3) specific contexts and situations. The chapter concludes with a discussion and suggestions for future research in this area. In addition, two appendices have been added with the CSWQ (Appendix 2.1) and a conversation guide for the practical application of the CSWQ in the consultation room (Appendix 2.2).

This chapter offers readers a transparent view into the research methodology used to investigate mathematics anxiety and assess the impact of a targeted pedagogical intervention on students’ reported anxiety and attitudes towards statistics and quantitative research methods. It provides a detailed account of the research participants, ethical considerations, and the multi-mixed methods approach employed. The chapter also critiques the validity, reliability, and trustworthiness of the research design and findings, ensuring methodological rigour. A candid discussion of the study’s limitations further strengthens its credibility. It is an essential reading for educators, researchers, and anyone committed to evidence-based improvements in mathematics education.

The chapter discusses the creation and maintenance of databases offering accurate, research-ready data for multidisciplinary use. It draws on the experience with the IUROPA CJEU Database Project (IUROPA), which has collected data about the decision-makers and the decisions of the Court of Justice of the European Union (CJEU). IUROPA and similar multi-user databases must live up to four criteria for databases, as proposed by Weinshall and Epstein. First, they must address real-world problems. Second, they must be open and accessible. Third, they must deliver reliable and reproducible data. Fourth, they must be ageless and easily calibrated to research purposes unknown at the time of data collection and cleaning. These criteria involve trade-offs: the quest for reliability may, first, precipitate difficult choices such as whether to discard or improve upon ‘imperfect’ data or tempt creators to endlessly postpone publication of ‘incomplete’ data; second, sustainability and human intervention are inversely proportionate when it comes to database maintenance; finally, a fledgling discipline like empirical legal studies in EU law imposes a disproportionate time commitment and financial responsibility on a small group of researchers.

Empirical legal studies in EU law routinely, if not inevitably, engage with text. From the decisions of national courts applying EU law, applicants’ case filings, to the Court’s own jurisprudence, these texts are an invaluable source of information for researchers seeking to understand the dynamics involved in the shaping of EU law and its broader societal impact. Distilling relevant information from legal texts, however, is anything but trivial. Intended to serve as a reference manual, the chapter offers detailed guidelines to researchers of both law and political science interested in employing a text-as-data approach to the study of EU law. To this end, we elaborate on how to conceptualise real-life phenomena in a way that renders them conducive to measurement, providing practical guidance on hand-coding and the use of deep learning classifiers. Further, we address potential challenges arising in the specific context of EU law. This includes limitations to access to relevant documents, as well as ensuring inter-coder reliability in data collection efforts that require specialised legal expertise.

Scholars engaged in comparative research on democratic regimes are in sharp disagreement over the choice between a dichotomous or graded approach to the distinction between democracy and nondemocracy. This choice is substantively important because it affects the findings of empirical research. It is methodologically important because it raises basic issues, faced by both qualitative and quantitative analysts, concerning appropriate standards for justifying choices about concepts. Generic claims that the concept of democracy should inherently be treated as dichotomous or graded are incomplete. The burden of demonstration should instead rest on more specific arguments linked to the goals of research. This chapter thus takes the pragmatic position that how scholars understand and operationalize a concept can and should depend in part on what they are going to do with it. The chapter considers justifications focused on the conceptualization of democratization as an event, the conceptual requirements for analyzing subtypes of democracy, the empirical distribution of cases, normative evaluation, the idea of regimes as bounded wholes, and the goal of achieving sharper analytic differentiation.

The challenge of finding appropriate tools for measurement validation is an abiding concern in political science. This chapter considers four traditions of validation, using examples from cross-national research on democracy: the levels-of-measurement approach, structural-equation modeling with latent variables, the pragmatic tradition, and the case-based method. Methodologists have sharply disputed the merits of alternative traditions. The chapter encourages scholars – and certainly analysts of democracy – to pay more attention to these disputes and to consider strengths and weaknesses in the validation tools they adopt. An appendix summarizes the evaluation of six democracy data sets from the perspective of alternative approaches to validation.

Beginning with the eerie history of Edinburgh’s South Bridge vaults, Chapter 3 investigates how supernatural encounters are often reported in places associated with death, decay, and sensory uncertainty. Here, we explore the connection between electromagnetic fluctuations, ambiguous sensory experiences, and supernatural perceptions. The chapter explores the human tendency to assign meaning to ambiguous stimuli and introduces key concepts in measurement science, such as reliability and validity. It also addresses the limited evidence for human sensitivity to EMF changes. Disruptions in spatial and body awareness in the brain can lead to experiences like feeling a presence or seeing a shadow figure. Together, these ideas offer plausible brain-based explanations for some ghostly encounters and demonstrate how the brain strives to make sense of the unknown when sensory information is unclear.

This chapter explores how to get and prepare quantitative data prior to analysis. Use theory to identify the unit of analysis for your study, then determine the population and sample for your study. Be sure to capture appropriate variation in the DV and be alert for selection bias in how cases enter the sample. Issues of validity and reliability can potentially cause major problems with your analysis. Again, use your theory to carefully match indicators to concepts to minimize the risk of these problems. Think through the data collection process and plan ahead to maximize efficiency; gather all data for control variables and robustness checks in a single sweep, if possible. Much data, particularly for standard indicators of common concepts, is freely available online through a variety of sources, and your library probably also subscribes to other quantitative databases. Collecting new data is substantially more time-consuming than using previously-gathered data, but it is often necessary to test novel theories. Whether you use existing data or novel data, be sure to define your data needs list before beginning data collection, allow sufficient time, and document and back up everything.