DML_partial_linear: Double Machine Learning estimation of partially linear model

In MCKnaus/causalDML: Causal Double Machine Learning

Double Machine Learning estimation of partially linear model

Description

This function estimates the parameter of interest in a partially linear model using the residual-on-residual representation of Robinson (1988) and flexibly estimated nuisance parameters following Chernozhukov et al. (2018).

Usage

DML_partial_linear(
  y,
  w,
  x,
  ml_w = list(create_method("forest_grf")),
  ml_y = list(create_method("forest_grf")),
  cf = 5,
  cv = 5,
  weights = FALSE,
  path = NULL,
  quiet = TRUE,
  e_hat = NULL,
  m_hat = NULL,
  cf_mat = NULL
)

Arguments

y	Numeric vector containing the outcome variable.
w	Treatment vector (binary or continuous).
x	Covariate matrix.
ml_w	List of methods to be used in ensemble estimation of treatment regression. Methods can be created by create_method. Default is an untuned honest regression_forest.
ml_y	List of methods to be used in ensemble estimation of outcome regression. Methods can be created by create_method. Default is an untuned honest regression_forest.
cf	Number of cross-fitting folds for DML (default 5).
cv	Number of cross-validation folds when estimating ensemble if more than one method is defined in ml_w and/or ml_y (default 5).
weights	If TRUE, prediction weights of the outcome nuisance extracted and saved (requires to provide a path).
path	Optional path to save the ensemble objects of each cross-fit for later inspection.
quiet	If FALSE, ensemble estimators print method that is currently running.
e_hat	Optional vector of predicted treatment outside of the function.
m_hat	Optional vector of predicted outcome outside of the function.
cf_mat	Optional prespecified logical matrix with k columns of indicators representing the different folds (for example created by prep_cf_mat).

Value

Returns a DML_partial_linear object:

results	Point estimate, standard error, t- and p-value of estimated effect.
e_hat	Predicted treatment
m_hat	Predicted outcomes
w	Treatment vector used in estimation.
y	Vector of outcomes used in estimation.
cf_mat	Matrix with k columns of indicators representing the different folds used in estimation.
path	Path where results are stored if specified, otherwise NULL.

References

• Robinson, P. M. (1988). Root-N-consistent semiparametric regression. Econometrica, 931-954.

• Chernozhukov, V., Chetverikov, D., Demirer, M., Duflo, E., Hansen, C., Newey, W., & Robins, J. (2018). Double/Debiased machine learning for treatment and structuralparameters.The Econometrics Journal,21(1), C1-C68

MCKnaus/causalDML documentation built on June 11, 2025, 12:30 a.m.