Search Results

This chapter considers the main types of data used in Politics and International Relations, as well as the main criteria by which to judge whether the data collected is good or not. It first describes the steps involved in the process of thinking about what data or evidence is relevant to answering a research question before discussing the importance of addressing issues of validity and reliability in research. Some of these issues are illustrated by referring to recent attempts to measure corruption, a major topic of interest in Politics and International Relations. The chapter also examines the issue of case selection as well as the collection of qualitative and quantitative data using methods such as interviewing and observation. Finally, it analyses the so-called ‘big data’ revolution in data collection and analysis, and provides a data quality checklist.

This chapter focuses on multiple correspondence analysis (MCA), which is a factor analysis statistical method used to analyse relations between a large set of categorical variables. Developed by Jean-Paul Benzécri in the early 1970s, MCA is one of the principal methods of geometric data analysis (GDA). Three different statistical methods can be identified as GDA: correspondence analysis (CA), which enables the cross-tabulation of two categorical variables; MCA for the analysis of a matrix of individuals and categorical variables; and principal component analysis (PCA), which uses numerical variables. In GDA, data is represented as a cloud of points to allow statistical interpretations. Although MCA is a relational method, it differs from social network analysis (SNA) as it focuses on the objective relations that characterize actors or groups, rather than the effective relations.

This chapter examines factor analysis, which is used to test whether a set of observable or manifest variables can measure one or more unobservable or latent constructs that they have in common. Such constructs are called factors. Factor analysis is therefore a data reduction method. In its foundation period, factor analysis was often applied to the study of general intelligence and mental abilities. Nowadays factor analysis is a workhorse for quantitative research in the social sciences, humanities, and natural sciences. There are two types of factor analysis: exploratory factor analysis and confirmatory factor analysis. Exploratory factor analysis is used for examining the underlying structures in a set of variables. Confirmatory factor analysis is used to test theoretical hypotheses; the researcher assumes that variables are interrelated in a specific way and uses factor analysis to find out whether the assumption is supported by the data — i.e. to what extent the data fits the predefined structure.

This chapter discusses two approaches to analyse quantitative data: descriptive statistics and inferential statistics. Descriptive statistics allows the student to summarize and describe data, whereas inferential statistics enables him or her to infer answers from the data using hypotheses. Both approaches can be extremely useful. The chapter details some of the techniques associated with these approaches, and helps the student to choose which techniques are appropriate for the data collected. In showing how to present data appropriately, it also explores ways to discuss findings in an evidence-informed manner. By introducing some of the basic ideas involved in quantitative analysis, the chapter provides students with skills that can be employed in a quantitative dissertation.

This chapter reflects on contextual analysis, which examines the environment in which a given phenomenon operates. Contextual analysis is used widely in social sciences, such as history, managerial and leadership studies, organizational theory, business studies, and political sciences. It is useful for identifying trends and topics within unstructured data (contexts). In a sense, contextual analysis helps create order out of chaos. The main aim of contextual analysis is to assess when and how contexts shape a social phenomenon and vice versa. Contexts can be, inter alia, historical, institutional, cultural, demographic, technological, psychological, ideological, ontological, and epistemological. A wide body of scholarship has developed on the topic of contextual analysis. The chapter reviews the literature briefly and identify clues and themes relevant to the social sciences.

This chapter evaluates thematic analysis (TA), which is one of the oldest and most widely used qualitative analytic method across the social sciences. TA is a flexible method for identifying and analysing patterns of meaning — ‘themes’ — in qualitative data, with wide-ranging applications. The method has a long, if indeterminate, history in the social sciences, but seems likely to have evolved from early forms of (qualitative) content analysis. TA is now more likely to be demarcated and acknowledged as a distinct method; however, confusion remains about what TA is. The popularity of TA as a distinct method received a considerable boost from the publication of Using Thematic Analysis in Psychology by social psychologists Virginia Braun and Victoria Clarke in 2006, which has become one of the most cited academic papers of recent decades.

This text provides readers with the analytic skills and resources they need to evaluate research findings in political research, as well as the practical skills for conducting their own independent inquiry. It shows that empirical research and normative research are not independent of each other and explains the distinction between positivism and interpretivism, and between quantitative and qualitative research. Part 1 of this edition discusses key issues in the philosophy of social science, while Part 2 presents a ‘nuts and bolts’ or ‘how to’ guide to research design, such as how to find and formulate a research question. Part 3 evaluates different methods of data collection and analysis that can be used to answer research questions, along with the variety of considerations and decisions that researchers must confront when using different methods.

This chapter focuses on the basic principles of research design. It first considers different types of research design, including experimental designs, cross-sectional and longitudinal designs, comparative designs, and historical research designs. It also discusses two types of research validity: internal validity and external validity. The chapter proceeds by describing various methods of data collection and the sort of data or evidence each provides, including questionnaires and surveys, interviewing and focus groups, ethnographic research, and discourse/content analysis. Finally, it examines six issues that must be taken into account to ensure ethical research: voluntary participation, informed consent, privacy, harm, exploitation, and consequences for future research.

This chapter focuses on cross-sectional and longitudinal studies. cross-sectional studies involve the analysis of usually quantitative data collected at a single snapshot in time. The unit of observation might be people or countries, and those are measured only once, all at approximately the same time. In contrast, longitudinal studies (also referred to as repeated measures studies) involve analysis on multiple occasions over time, where the same individuals (or countries) — the panel — are measured on each occasion. As such, the unit of observation is occasions, and there are multiple occasions/measures of each individual. A subcategory of longitudinal studies is event-history/survival/duration analysis, where the dependent variable is binary and the focus is on causes of changes between the two states of the outcome. Note that in comparison, time series analysis typically involves fewer individuals (often only one) and a larger number of time points. A third type of study, situated in between longitudinal and cross-sectional studies, is repeated cross-sectional analysis, which involves the analysis of multiple cross-sectional data sets over time, and different individuals are measured in each wave of the survey. Here, the unit of observation is individuals, and there are multiple individuals measured in each survey wave.

This chapter examines automated text analysis (ATA), which describes the different methodologies that can be applied in order to perform text analysis with the use of computer software. ATA is a computer-assisted method for analysing text, whenever the analysis would be prohibitively labour-intensive due to the volume of texts to be analysed. ATA methods have become more popular due to current interest in big data, taking into account the volume of textual content that is made easily accessible by the digitization of human activity. Key to ATA is the notion of corpus, which is a collection of texts. A necessary step before starting any analysis is to collect together the necessary documents and construct the corpora that will be used. Which texts need to be included in this step is dictated by the research question. After text collection, some processing steps need to be taken before the analysis starts, for example tokenization and part-of-speech tagging. Tokenization is the process of splitting a text into its constituent words, also called tokens, whereas part-of-speech tagging assigns each word a label that indicates the respective part-of-speech.

This chapter discusses prosopography, which is defined as the investigation of the common background characteristics of a group of actors in history by means of a collective study of their lives. The etymology of the word suggests that prosopography is about describing or recording a person’s appearance or life, but prosopography differs from biography in that it analyses structured biographical data of groups of individuals that have something in common. Prosopography emerged primarily as a method for historical research. Outside of historical research, it is more commonly known as ‘group biography’ or ‘career-path analysis’. Prosopography has also been a key element of ‘field-based’ research on social groups and the sociology of professions, and is more of an approach than a method sui generis: it implies the systematic organization of data in such a way that connections and patterns that influence historical processes are revealed. The chapter then details the five stages of prosopography.

This chapter addresses the unit of analysis and observation. Each empirical social or behavioural science study typically includes the identification of one or more units of analysis. The unit is the entity, element, or grouping that constitutes the focus of the study’s analyses, and multiple cases of this unit are analysed. The unit of analysis is of primary importance, as this is the unit that is referred to in hypotheses or research questions and therefore the unit that is the focus of data analyses that address these hypotheses or research questions. However, there are two other types of units that need to be considered. In sum, the three types of units in any empirical study are the unit of sampling, the unit of observation or measurement (sometimes called the unit of inquiry or unit of data collection), and the unit of analysis.

This chapter illustrates process-tracing (PT), which is a qualitative within-case data analysis technique used to identify causal relations. Although there are several distinct definitions of the PT method, scholars largely agree that the process-tracing method attempts to identify the intervening causal process (or the causal chain or causal mechanism) between an independent variable and the dependent variable. The PT method can be used for theory testing and theory-building. When it is applied to theory testing, a hypothetical causal mechanism is tested against empirical evidence. The research goal is to test whether a theorized mechanism is present in a given case, or whether the mechanism functions as expected in the selected case. When tracing is applied to theory-building, the goal is to identify causal processes for which there is no available prior theoretical hypothesis in the literature. Here, the aim of the research is to develop theory.

This chapter addresses Boolean algebra, which is based on Boolean logic. In the social sciences, Boolean algebra comes under different labels. It is often used in set-theoretic and qualitative comparative analysis to assess complex causation that leads to particular outcomes involving different combinations of conditions. The basic features of Boolean algebra are the use of binary data, combinatorial logic, and Boolean minimization to reduce the expressions of causal complexity. By calculating the intersection between the final Boolean equation and the hypotheses formulated in Boolean terms, three subsets of causal combinations emerge: hypothesized and empirically confirmed; hypothesized, but not detected within the empirical evidence; and causal configurations found empirically, but not hypothesized. This approach is both holistic and analytic because it examines cases as a whole and in parts.

This chapter explores the principles of comparative research design as well as the issues and problems associated with different aspects of the approach. In particular, it considers the issue of case selection, the common sources of error that are associated with comparative research, and what can be done to try and avoid or minimize them. The comparative method is one of the most commonly used methods in political research and is often employed to investigate various political phenomena, including democratization, civil war, and public policy. The chapter discusses the three main forms of comparison, namely case study, small-N comparison, and large-N comparison. It also describes two main approaches used to select cases for small-N studies: Most Similar Systems Design and Most Different Systems Design. It also evaluates qualitative comparative analysis and concludes with an analysis of issues arising from case selection and data collection in large-N comparative research.