In this chapter, we explore the idea of the social world as a collection of patterned phenomena, and how the social sciences attempt to make sense of those patterns. We value the characteristics of parsimony, predictiveness, falsifiability, fertility, and replicability in research. Research questions are one of four types – normative, hypothetical, factual/procedural, or empirical – depending on the goal or purpose of the investigation. Empirical research questions deal with the world ‘as it is,’ seeking general explanations for patterns of outcomes or classes of phenomena. A good research question is one whose answer takes as much space as your paper has length.

This chapter introduces unsupervised learning, where algorithms analyze data without predefined labels or target outcomes. It covers three main clustering approaches: agglomerative clustering (bottom-up approach merging similar data points) and divisive clustering (top-down approach, exemplified by k-means algorithm that partitions data into k groups by minimizing distances to centroids).

The chapter explains Expectation Maximization (EM) algorithm for handling incomplete data and finding maximum likelihood parameters in statistical models. It includes a section on reinforcement learning, where agents learn optimal actions through trial-and-error interactions with environments to maximize rewards.

Key topics include distance matrices, dendrograms, cluster evaluation metrics (AIC, BIC), and practical applications. The chapter emphasizes the artistic nature of unsupervised learning, requiring careful design decisions about thresholds, cluster numbers, and technique selection. Hands-on R examples demonstrate each method using real datasets.

Analyzing data requires more than simply running one model and reporting the results. Getting trustworthy results requires careful checking of the data, including checking for and addressing missing values, nonlinearities, and collinearity, and generating any necessary composite or recoded variables such as interaction terms, scales or indices, or even lagged variables. Finally, problems occur when messy real-world data meet assumption-laden models. Endogeneity, simultaneity, omitted variable bias, fixed effects, and dichotomous DVs all violate key assumptions of the OLS model and require appropriate statistical and/or theoretical adjustments to produce trustworthy results.

A framing case study describes Russia’s 2022 invasion of Ukraine. Then the chapter provides an overview of law on the use of force. The chapter begins by describing the historical movement to prohibit the use of force. It then discusses the use of force with UN Security Council authorization. Next, it examines the complex topic of self-defense, including how states can respond to armed attacks, whether they can prevent armed attacks, and how they can protect themselves against non-state actors. Finally, the chapter probes whether the use of force is ever legally justified for other reasons, including: protecting nationals abroad; humanitarian intervention and the responsibility to protect; and when states consent to intervention.

A framing case study describes the trial of Hissène Habré, the deposed leader of Chad who was prosecuted for multiple international crimes in Senegal. The chapter then discusses international criminal law. The chapter first discusses major principles of international criminal law and its evolution. It next discusses the key elements for establishing criminal guilt, including: the definition of core crimes; modes of responsibility and liability; and possible defences. Finally, the chapter surveys the major institutions that enforce international criminal law by discussing the operations of the International Criminal Court and the assertion of universal jurisdiction by domestic courts.

Write regularly and pay attention to your personal writing processes. When it’s writing time, it’s writing time. Save the self-editing for later. Choose a self-editing strategy that targets the kinds of writing problems you know you usually have: surface, sentence, paragraph, or global level. Don’t be afraid to change strategies or try multiple strategies; taking more looks at your paper is always better. Peer review as it’s practiced in political science is about reviewing research design and execution, not line editing. For all papers, look for theory grounded in concepts, hypotheses that are directly observable implications of the theory, and measurement that is valid in the context of the research. For qualitative research, consider case selection, measurement, and whether the conclusions are commensurate with the scope of the theory and tests. For quantitative research, consider issues of measurement and case selection, and be alert for specification errors and analytical pitfalls the author might have missed. Helpful peer reviews provide concrete guidance about weaknesses in the paper and often include specific suggestions or requests for additional development of the paper.

This chapter explores the fundamentals of data in data science, covering data types (structured vs. unstructured), collection sources (open data, social media APIs, multimodal data, synthetic data), and storage formats (CSV, TSV, XML, RSS, JSON). It emphasizes the critical importance of data pre-processing, including data cleaning (handling missing values, smoothing noisy data, data munging), integration, transformation, reduction, and discretization. Through hands-on examples, the chapter demonstrates how to systematically prepare "dirty" real-world data for analysis by addressing inconsistencies, outliers, and missing information. The chapter highlights that data preparation is often half the battle in data science, requiring both technical skills and careful attention to data quality and bias.