CLAS Research Methodology

Incomplete datasets are common across scientific and historical disciplines. Conventional approaches often rely on interpolation, statistical fitting, or assumptiondriven reconstruction, which may unintentionally introduce structural bias. This paper introduces the CLAS (Coherence-Logic Axiomatic System) research methodology as a structured framework for modeling incomplete datasets without forcing missing values. CLAS separates observed data, unknown variables, and system-level coherence constraints, allowing scenario-space exploration while preserving empirical integrity. A case study in energy-transition policy modeling demonstrates the method’s practical applicability