Introduction \label | Definition and estimators of the average treatment effect | Parameters of interest \label | G-computation estimators \label | Inverse probability of treatment estimators \label | Doubly-robust estimators \label | Doubly-robust inference \label | Outcome-adaptive propensity score estimation \label | Implementation of doubly-robust inference \label | Estimating regressions \label | Using glm to estimate regressions | Using SuperLearner to estimate regressions | Reducing dependence on random seed | Outcome-adaptive propensity score | Arbitrary user-specified regressions | Standard error estimation \label | Standard errors for TMLE | Cross-validated standard errors | Partially cross-validated standard errors | Confidence intervals \label | Hypothesis tests \label | Missing data \label | Multi-level treatments | Cross-validated regression estimates | Inference for IPTW using adaptive PS estimators \label | Implementation of inference for adaptive IPTW | Discussion | Session Info

Introduction \label | Estimators | Nuisance parameters | Parameters of interest | Using the drord function | COVID-19 data | Basic calls and plots | Working model controls | Bootstrap confidence intervals | Stratified estimators | Missing outcome values | Risk difference for binary outcomes | Session Info