Small-N design – theoretical outline Jiří Navrátil jiri.navratil@fss.muni.cz GLCb1008 Introduction to Methodology of Social Sciences Lecture outline •Context of small-N designs •Case study •Comparative method •Process tracing Main types of research strategies •Experiment (small N) •Case study (small N) •Comparative design (small N) •Longitudinal design (small/large N) •Cross-sectional design (large N) • Main aspects of research strategies Main aspects of research strategies Main aspects of research strategies Main aspects of research strategies Case study •Research on a contemporary phenomenon in a real-world context; the phenomenon is often not clearly delineated •many variables are examined, and different data sources are used, often preceded by theoretical consideration of what and how to analyze •Case: a more/less closed system in time and (social) space (individual, organization, institution, event, community ...) Case study: sampling criteria -unique case study (detailed analysis of the case) – e.g. homelesness in Brno -instrumental case study (more general knowledge) – e.g. homelesness in the Czech Republic -collective case study (multiple cases representing a phenomenon, population or circumstance - sometimes an attempt to generate theory) – e.g. homelessness in big post-socialist cities Sampling strategies •Maximum variation •Homogeneous •Critical case •Theory based •Confirming and disconfirming cases •Snowball or chain •Extreme or deviant case •Typical case •Politically important case •Random purposeful •Stratified purposeful •Criterion •Opportunistic •Combination or mixed •Convenience • Miles and Huberman (1994: 28) Case sampling and generalization (Rohlfing 2012) •Generalizations must always take into account the relationship between the case and the population Relationship to theory (Blaikie) •Types of case studies: •- configurative-idiographic - understanding - disciplined-comparative – theory application - heuristic – theory seeking - plausibility probes – theory development - crucial-case – theory testing • Comparative method •Functional equivalent of the experiment •Study of contrasting cases using identical methods •Method of controlling for the effect of variables in research with a small number of cases (by selecting cases we transform variables into constants, thus controlling for the effect of alternative variables) •It is a cross-sectional design for small N •e.g. Durkheim analysis of suicide: official statistics (large N) across countries (small N) Mill's method of difference and agreement Effect Potential causes Case-oriented strategy in comparative settings (Ragin) •Combination of causal analysis, interpretative analysis and concept formation •Designed to uncover patterns of invariance and constant association, using cross-tabulation of cause(s) and effect and accounting for deviant cases; no probabilistic relationships! •If only one case deviates – explanation is doubted •Cases are considered as whole entities, not as collection as variables (e.g. Weber´s analysis of protestant ethics) •Stimulation of dialogue between ideas and evidence Process tracing •Beyond correlations between independent variables (Xs) and outcomes (Ys) •Aiming to unpack the causal relationship between them and trace causal mechanisms •A causal mechanism -“a complex system, which produces an outcome by the interaction of a number of parts“ •Single case research design •E.g. analysis of how particular social protest emerges How? •within- case inferences about the presence/absence of causal mechanisms vs. cross- case inferences about causal relationships •Vs. congruence method: based on the value of the independent variable (X), researchers test whether the prediction about the outcome that should follow from the theory is congruent with what is found in the case, investigated either temporally or other across aspects of the outcome(s) (e.g. higher crime rate in economically deprived localities) •Congruence investigates correlations between X and Y, whereas process-tracing investigates the workings of the mechanism(s) that contribute to producing an outcome (e.g. how exactly is economic deprivation linked to crime?) •Process- tracing case studies are usually presented as a stepwise test of each part of a causal mechanism, especially in the theory- testing variant (e.g. economic downturn, perception of this downturn, conflict between social norms and achievable goals, social ties, social norms reassessment, illegal activity) • Variants of proces tracing •theory- testing: deduces a theory from the existing literature and then tests whether evidence shows that each part of a hypothesized causal mechanism is present in a given case (theory-centric) •theory- building- inferring that a more general causal mechanism exists from the facts of a particular case (theory-centric) •explaining- outcome – come out with a minimally sufficient explanation of a puzzling outcome in a specific historical case (case-centric) Theory-testing •causal mechanism is hypothesized to be present in a population of cases of a phenomenon, the researcher selects a single case where both X and Y are present, and the context allows the mechanism to operate, the goal is to evaluate whether evidence shows that the hypothesized causal mechanism linking X and Y was present and that it functioned as theorized "democratic peace theory“ - democracies are hesitant to engage in armed conflict with other identified democracies: -democracies are in general more peaceful in their international relations); -democracies do not go to war with other democracies -more democratic states in the international system makes the international system more peaceful Theory-building •building a theory about a causal mechanism between X and Y that can be generalized to a population of a given phenomenon, starting from a situation where we are in the dark regarding the mechanism • Explaining outcome •the aim is to craft a sufficient explanation of the outcome, instead of studying mechanisms that cause war (Y), the analysis would focus on explaining a particular outcome such as war in Ukraine • Overview References