• Choose a category
• All
• Classic-Fiction

By Root 912 0

Social Inquiry has been provided by a team of specialists in a book edited by Henry Brady and David Collier, 34 in which the editors integrate their respective specializations in quantitative survey research and qualitative comparative studies. Their book provides a major scholarly statement on the relationship between quantitative and qualitative methods. While generous and specific in its praise for contributions made in DSI, Brady, Collier, and the contributors to their volume express major misgivings: First, DSI, “does not adequately address the basic weaknesses within the mainstream quantitative approach it advocates.” Second, DSI’s “treatment of concepts, operationalizations, and measurement” is regarded as “seriously incomplete.” Third, Brady and Collier “disagree with DSI’s claims that it provides a general framework for ‘specific inference in qualitative research.’” They emphasize, as others have, DSI’s “failure to recognize the distinctive strengths of qualitative methods,” which leads its authors to “inappropriately view qualitative analysis almost exclusively through the optic of mainstream quantitative methods.”

The present book has much in common with Brady and Collier’s book. They emphasize, as we do, the need to “rethink the contributions” of quantitative and qualitative approaches and to indicate how scholars can most effectively draw on the respective strengths of each. Considerable attention is given to our emphasis on the importance of within-case analysis and process-tracing. Brady and Collier, and other distinguished scholars contributing to their book, share our criticism of DSI’s almost exclusive focus on increasing the number of observations in order to increase “leverage.” In their conclusion, Brady, Collier, and Jason Seawright develop a “multi-faceted approach to evaluating sources of leverage for addressing rival explanations.”

Despite these important reservations and criticisms, Brady and Collier, as do we, regard DSI as a major contribution that has usefully stimulated important new work on the relation between quantitative and qualitative methods.

Advantages and Limitations of Case Studies: Casting Off the Prism of Statistical Methods

In the 1960s and 1970s, definitions of case studies relied on distinctions between the study of a small versus a large number of instances of a phenomenon. Case studies were characterized as “small-n” studies, in contrast to “large-N” statistical studies. This distinction suggests that the difference in the number of cases studied is the most salient difference between statistical and case study methods; in our “bigger is better” culture, this language implies that large-N methods are always preferable when sufficient data is available for study, as Arend Lijphart implied in a 1971 article.35 In fact, case studies and other methods each have particular advantages in answering certain kinds of questions.

One early definition, still widely used, states that a case is a “phenomenon for which we report and interpret only a single measure on any pertinent variable.”36 This definition, which case study researchers have increasingly rejected, has sometimes led scholars trained in statistical methods to misapply the “degrees of freedom problem” (which we discuss below) and to conclude that case studies provide no basis for evaluating competing explanations of a case.

We define a case as an instance of a class of events.37 The term “class of events” refers here to a phenomenon of scientific interest, such as revolutions, types of governmental regimes, kinds of economic systems, or personality types that the investigator chooses to study with the aim of developing theory (or “generic knowledge”) regarding the causes of similarities or differences among instances (cases) of that class of events. A case study is thus a well-defined aspect of a historical episode that the investigator selects for analysis, rather than a historical event itself. The Cuban Missile Crisis, for example, is a historical instance of many different classes of events: deterrence, coercive