On the pitfalls of Gaussian likelihood scoring for causal discovery

Abstract

We consider likelihood score-based methods for causal discovery in structural causal models. In particular, we focus on Gaussian scoring and analyze the effect of model misspecification in terms of non-Gaussian error distribution. We present a surprising negative result for Gaussian likelihood scoring in combination with nonparametric regression methods.

Keywords

• graphical models
• model misspecification
• non-parametric regression
• structural causal models
• 62d20