Working Paper: CEPR ID: DP13402
Authors: Michael C. Knaus; Michael Lechner; Anthony Strittmatter
Abstract: We investigate the finite sample performance of causal machine learning estimators for heterogeneous causal effects at different aggregation levels. We employ an Empirical Monte Carlo Study that relies on arguably realistic data Generation processes (DGPs) based on actual data. We consider 24 different DGPs, Eleven different causal machine learning estimators, and three aggregation levels of the estimated effects. In the main DGPs, we allow for selection into treatment based on a rich set of observable covariates. We provide evidence that the estimators can be categorized into three groups. The first group performs consistently well across all DGPs and aggregation levels. These estimators have multiple steps to account for the selection into the treatment and the outcome process. The second group shows competitive performance only for particular DGPs. The third group is clearly outperformed by the other estimators.
Keywords: causal machine learning; conditional average treatment effects; selection on observables; random forest; causal forest; lasso
JEL Codes: C21
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| Causal machine learning estimators (C51) | identification of heterogeneous causal effects (C21) |
| Observable covariates (C29) | identification of average treatment effects (ATE) (C22) |
| Observable covariates (C29) | identification of individual treatment effects (ITE) (C22) |
| Selection into treatment (C24) | treatment effects (C22) |
| Causal machine learning estimators (C51) | performance across various data generation processes (DGPs) (C52) |
| Causal machine learning estimators (C51) | mean squared errors (MSE) (C20) |