Causal

Documentation for each of the causal inference methods implemented in zEpid

Causal Diagrams

DirectedAcyclicGraph(exposure, outcome)

Inverse Probability Weights

IPTW(df, treatment, outcome[, weights, …]) Calculates inverse probability of treatment weights.
StochasticIPTW(df, treatment, outcome[, weights]) Calculates the IPTW estimate for stochastic treatment plans.
IPMW(df, missing_variable[, stabilized, …]) Calculates inverse probability of missing weights.
IPCW(df, idvar, time, event[, flat_df, enter]) Calculates inverse probability of censoring weights.

Time-Fixed Treatment G-Formula

TimeFixedGFormula(df, exposure, outcome[, …]) G-formula for time-fixed exposure and single endpoint, also referred to as the g-computation algorithm formula.
SurvivalGFormula(df, idvar, exposure, …[, …]) G-formula for time-to-event data where the exposure is fixed at baseline.

Time-Varying Treatment G-Formula

MonteCarloGFormula(df, idvar, exposure, …) Time-varying implementation of the Monte Carlo g-formula.
IterativeCondGFormula(df, exposures, outcomes) Iterative conditional g-formula estimator.

Augmented Inverse Probability Weights

AIPTW(df, exposure, outcome[, weights, alpha]) Augmented inverse probability of treatment weight estimator.
SingleCrossfitAIPTW(df, exposure, outcome[, …]) Implementation of the Augmented Inverse Probability Weighting estimator with a cross-fit procedure.
DoubleCrossfitAIPTW(df, exposure, outcome[, …]) Implementation of the augmented inverse probability weighted estimator with a double cross-fit procedure.

Targeted Maximum Likelihood Estimator

TMLE(df, exposure, outcome[, alpha, …]) Implementation of target maximum likelihood estimator.
StochasticTMLE(df, exposure, outcome[, …]) Implementation of target maximum likelihood estimator for stochastic treatment plans.
SingleCrossfitTMLE(df, exposure, outcome[, …]) Implementation of the Targeted Maximum Likelihood Estimator with a single cross-fit procedure.
DoubleCrossfitTMLE(df, exposure, outcome[, …]) Implementation of the Targeted Maximum Likelihood Estimator with a double cross-fit procedure.

G-estimation of SNM

GEstimationSNM(df, exposure, outcome[, weights]) G-estimation for structural nested mean models.

Generalizability / Transportability

IPSW(df, exposure, outcome, selection[, …]) Calculate inverse probability of sampling weights through logistic regression.
GTransportFormula(df, exposure, outcome, …) Calculate the g-transport-formula using a observed study sample and a sample from the target population.
AIPSW(df, exposure, outcome, selection[, …]) Doubly robust estimator for generalizability.