Author ORCID Identifier

Date of Award


Document Type

Thesis (Ph.D.)

Department or Program

Engineering Sciences

First Advisor

Eugene Santos, Jr.


Correlation does not imply causation" is one of the fundamental principles taught in science, emphasizing that associations between variables do not necessarily indicate causality. Yet, over the past three decades, extensive research has begun to challenge this perspective by developing sophisticated methods to differentiate causal from correlative relationships. This research suggests that correlations often involve a blend of confounded and causal interactions, which, given certain assumptions, can be disentangled to uncover actionable insights and deepen our understanding of physical, biological, and societal systems.

Accurately discovering causal relationships from data amidst cyclic dynamics remains a challenging open problem in causality research. This complexity emerges when two variables influence each other in a feedback loop, complicating the determination of causal directionality. Most existing research sidesteps this issue by initially assuming acyclicity in the system, an assumption that does not hold in complex domains such as biology and economics. This thesis introduces a novel approach that effectively addresses both cyclic and acyclic scenarios. It capitalizes on structure learning results within a probabilistic graphical modeling framework, specifically Bayesian Knowledge Bases, and establishes a Kolmogorov identifiability result that supports an instance-based method for causal discovery capable of managing and detecting cycles from data. The validity of this approach is demonstrated through its state-of-the-art cycle identifiability in 18 simulated fMRI experiments and its comparative performance with established acyclic algorithms across 22 real-world causal benchmark datasets. This thesis not only bridges a crucial gap in causal analysis with cycles but also sets a new standard for real-world empirical validation in the field.