Doubly-Robust Nonparametric Estimation and Inference


[Up] [Top]

Documentation for package ‘drtmle’ version 1.0.5

Help Pages

adaptive_iptw Compute asymptotically linear IPTW estimators with super learning for the propensity score
ci Compute confidence intervals for drtmle and adaptive_iptw@
ci.adaptive_iptw Confidence intervals for adaptive_iptw objects
ci.drtmle Confidence intervals for drtmle objects
drtmle TMLE estimate of the average treatment effect with doubly-robust inference
estimateG estimateG
estimategrn estimategrn
estimateQ estimateQ
estimateQrn estimateQrn
eval_Diptw Evaluate usual influence function of IPTW
eval_Diptw_g Evaluate extra piece of the influence function for the IPTW
eval_Dstar Evaluate usual efficient influence function
eval_Dstar_g Evaluate extra piece of efficient influence function resulting from misspecification of outcome regression
eval_Dstar_Q Evaluate extra piece of efficient influence function resulting from misspecification of propensity score
extract_models Help function to extract models from fitted object
fluctuateG fluctuateG
fluctuateQ fluctuateQ
fluctuateQ1 fluctuateQ1
fluctuateQ2 fluctuateQ2
make_validRows Make list of rows in each validation fold.
plot.drtmle Plot reduced dimension regression fits
predict.SL.npreg Predict method for SL.npreg
print.adaptive_iptw Print the output of a '"adaptive_iptw"' object.
print.ci.adaptive_iptw Print the output of ci.adaptive_iptw
print.ci.drtmle Print the output of ci.drtmle
print.drtmle Print the output of a '"drtmle"' object.
print.wald_test.adaptive_iptw Print the output of wald_test.adaptive_iptw
print.wald_test.drtmle Print the output of wald_test.drtmle
reorder_list Helper function to reorder lists according to cvFolds
SL.npreg Super learner wrapper for kernel regression
tmp_method.CC_LS Temporary fix for convex combination method mean squared error Relative to existing implementation, we reduce the tolerance at which we declare predictions from a given algorithm the same as another
tmp_method.CC_nloglik Temporary fix for convex combination method negative log-likelihood loss Relative to existing implementation, we reduce the tolerance at which we declare predictions from a given algorithm the same as another. Note that because of the way 'SuperLearner' is structure, one needs to install the optimization software separately.
wald_test Wald tests for drtmle and adaptive_iptw objects
wald_test.adaptive_iptw Wald tests for adaptive_iptw objects
wald_test.drtmle Wald tests for drtmle objects