Chapter Summary

Chapter Objectives

7.1: Explain the importance of case study designs to the study of political phenomena.
7.2: Identify the purposes of case study designs. 
7.3: Describe the logic underlying the selection of cases and case comparison.
7.4: Explain the difference between a counterfactual and a mechanistic understanding of causation. 
7.5: Describe how process tracing is used to establish causation. 
7.6: Understand the limits to generalizing from case studies.

  • Case study designs are a comprehensive and in-depth qualitative study of a single case or several cases. They are a nonexperimental design in which the investigator has little control over events and are usually referred to as small N research.
  • Case study research is the only research that can be used to answer question about important, but rare or singular, events.
  • The comparative method is traced back to John Stuart Mill’s A System of Logic (1983).
  • Case studies were the dominant approach due to the lack of powerful computing and the ability to study rare events where experimental manipulation is difficult or unethical.
  • Advocates today claim that case studies do in fact have much to contribute. They are now used to test theories and to elucidate causal mechanisms in ways that quantitative studies could not.
  • Idiographic case studies aim to describe, explain, or interpret a singular historical episode with no intention of generalizing beyond the case.
    • They can be either inductive or theory-guided.
  • Hypothesis-generation case studies examine one or more cases for the purpose of developing more general theoretical propositions” which can be tested in future research.
  • Hypothesis-testing case studies entail testing hypothesized empirical relationships.
  • Plausibility probes serve several purposes: to sharpen a hypothesis or theory, to refine the operationalization or measurement of key variables, and to explore the suitability of a particular case as a vehicle for testing a theory before engaging in a costly and time-consuming research effort.
  • Mill describe two comparative strategies:
    • The method of difference is a comparative strategy wherein the researcher selects cases in which the outcomes differ, compares the cases looking for the single factor that the cases do not have in common, and concludes that this factor is causal.
    • The method of agreement is a comparative strategy wherein the researcher selects cases which share the same outcome and identifies those conditions or causal factors which the cases also have in common.
  • Researchers also rely on logic to improve the strength of their conclusions. They do this by selecting a most likely case or least likely case.
  • In a deviant case, researcher may choose a case that does not conform to a theory or fit a normal pattern.
  • Comparative case analysis can rely on two types of causation:
    • Counterfactual understanding of causation, which is the logical argument that support for the claim that A causes B is demonstrated by a case in which A is absent and B does not occur.
    • Mechanistic understanding of causation, which is an approach to demonstrating or understanding causation by focusing on the mechanism by which a cause leads to an outcome.
  • Process tracing refers to case studies that explicitly unpack mechanisms and engage in detailed empirical tracing of them.
    • Process tracing depends on logic.
      • There are four tests:
        • Hoop tests involve evidence that is certain but not unique.
        • Smoking-gun tests provide unique evidence but not certain evidence.
        • Doubly decisive tests provide both certain and unique evidence.
        • Straw-in-the-wind tests provide evidence which is neither unique nor certain.
  • Researchers also talk about causal conditions in terms of whether they are necessary or sufficient.
    • A necessary cause is a condition that must be present in order for the outcome to occur.
    • A sufficient cause is condition that when found, the outcome is always found.
  • In order to generalize to other cases, the other cases must be causally homogenous, not heterogeneous.
    • A causally heterogeneous population is a population in which a given cause might have many different effects across different cases or the same cause is linked to the same outcome through different causal mechanisms.
    • A causally homogeneous population is a population in which a given cause can be expected to have the same causal relationship with the outcome across cases in the population.
  • There are various drawbacks when utilizing case studies, but they can also be an informative and appropriate choice for researchers.