Explanatory research
Causation by regularity theory
Comparative Configurational Methods and CNA
Área
Ensino e Pesquisa em Administração
Tema
Métodos e Técnicas de Pesquisa
Autores
Nome
1 - Esdras Antunes do Nascimento UNIVERSIDADE FEDERAL DE MINAS GERAIS (UFMG) - CEPEAD
2 - Jonathan Simões Freitas UNIVERSIDADE FEDERAL DE MINAS GERAIS (UFMG) - Faculdade de Ciências Econômicas
Reumo
Scientific research drives societal advancement through new ideas, theories, and problem-solving. However, social sciences and management face challenges in identifying causes and establishing reliable causal relationships. Explanatory studies go beyond event description, predicting future occurrences. The theory of causation by regularity suggests events can cause each other under specific conditions. Comparative configurational methods, like Coincidence Analysis (CNA), analyze causal complexity and patterns in events, considering configurational relationships.
The proposed research problem is "how can the use of comparative configurational methods, specifically Coincidence Analysis (CNA), contribute to a deeper analysis of causal relationships in social science and management studies?"
The overall objective of this study is to discuss the relevance of the concept of causality and the theory of causality by regularity in explanatory studies, using comparative configurational methods, specifically CNA, as a methodological tool for a deeper analysis of causal relations associated with social research and phenomena observed in management studies.
Explanatory research aims to understand the causes behind phenomena, especially in complex management events. Causality explores necessary conditions, multiple causes, and cause-and-effect relationships. Although Qualitative Comparative Analysis (QCA) is commonly used, it has limitations in analyzing complex causality. Coincidence Analysis (CNA), a new approach to Comparative Configurational Methods, overcomes these limitations with a bottom-up approach and a unique optimization algorithm. CNA ensures rigorous search through consistency, coverage, and robustness analyses.
Studies applying Coincidence Analysis (CNA) have examined causal relationships in various research areas, such as supply chain, sports marketing, organizational change, and lean management, among others. CNA has enabled a comprehensive factor analysis, identifying patterns of configuration and interactions between variables. The practical implications of CNA include the development of targeted recommendations and effective interventions, and the promotion of multidisciplinary and integrated research. Overall, CNA promotes theoretical knowledge and helps solve complex problems.
Comparative Configurational Methods, specifically Coincidence Analysis (CNA), enhance the understanding of causal relationships in social and managerial studies. CNA surpasses Qualitative Comparative Analysis (QCA) by addressing multiple causes, causal sequentiality, and complex relationships. It explores common cause structures, causal chains, cycles, and feedback to gain comprehensive insights. Although QCA is predominant in management research, CNA gains traction in prestigious disciplines such as public health, social sciences, and management.
BAUMGARTNER, Michael. Inferring causal complexity. Sociological methods & research, v. 38, n. 1, p. 71-101, 2009a. https://doi.org/10.1177/0049124109339369
BAUMGARTNER, Michael; AMBÜHL, Mathias. Causal modeling with multi-value and fuzzy-set Coincidence Analysis. Political Science Research and Methods, v. 8, n. 3, p. 526-542, 2020. https://doi.org/10.1017/psrm.2018.45
BAUMGARTNER, Michael; FALK, Christoph. Boolean Difference-Making: A Modern Regularity Theory of Causation. The British Journal for the Philosophy of Science, 2019. https://doi.org/10.1093/bjps/axz047