Causality on Longitudinal Data: Stable Specification Search in Constrained Structural Equation Modeling

Developing causal models from observational longitudinal studies is an important, ubiquitous problem in many disciplines. A disadvantage of current causal discover algorithms, however, is the inherent instability in structure estimation. With finite data samples small changes in the data can lead to completely different optimal structures. The present work presents a new causal discovery algorithm for longitudinal data that is robust for finite data samples. We validate our approach on simulated data set and real-world data for Chronic Fatigue Syndrome.

• Type: Journal
• Year: 2015
• Where: PKDD
• Authors: Ridho Rahmadi, Perry Groot, Marianne Heins, Hans Knoop, Tom Heskes
• Keywords: Data Mining, PKDD 2015