Causal Discovery on Dependent Binary Data
This work addresses the challenge of accurate causal discovery for researchers and practitioners dealing with dependent binary data, representing an incremental improvement by adapting existing methods to handle dependence.
The paper tackles the problem of learning causal graphs from dependent binary data, which violates the common independence assumption, by proposing a decorrelation-based approach that uses a latent utility model and an EM-like algorithm to generate decorrelated data for any standard causal discovery method, resulting in significantly improved accuracy in causal graph learning as demonstrated on synthetic and real-world datasets.
The assumption of independence between observations (units) in a dataset is prevalent across various methodologies for learning causal graphical models. However, this assumption often finds itself in conflict with real-world data, posing challenges to accurate structure learning. We propose a decorrelation-based approach for causal graph learning on dependent binary data, where the local conditional distribution is defined by a latent utility model with dependent errors across units. We develop a pairwise maximum likelihood method to estimate the covariance matrix for the dependence among the units. Then, leveraging the estimated covariance matrix, we develop an EM-like iterative algorithm to generate and decorrelate samples of the latent utility variables, which serve as decorrelated data. Any standard causal discovery method can be applied on the decorrelated data to learn the underlying causal graph. We demonstrate that the proposed decorrelation approach significantly improves the accuracy in causal graph learning, through numerical experiments on both synthetic and real-world datasets.