Double Cross-fit Doubly Robust Estimators: Beyond Series Regression

arXiv:2403.15175v1 Announce Type: cross
Abstract: Doubly robust estimators with cross-fitting have gained popularity in causal inference due to their favorable structure-agnostic error guarantees. However, when additional structure, such as H\"{o}lder smoothness, is available then more accurate "double cross-fit doubly robust" (DCDR) estimators can be constructed by splitting the training data and undersmoothing nuisance function estimators on independent samples. We study a DCDR estimator of the Expected Conditional Covariance, a functional of interest in causal inference and conditional independence testing, and …

abstract arxiv beyond causal causal inference data error however inference math.st regression robust series stat.me stat.ml stat.th training training data type