Causal discovery evaluations should report negative control baselines, because common metrics can look good under random guessing.
Learning high-dimensional directed acyclic graphs with mixed data-types
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ME 1years
2024 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Are you doing better than random guessing? A call for using negative controls when evaluating causal discovery algorithms
Causal discovery evaluations should report negative control baselines, because common metrics can look good under random guessing.