StratifiedMedicine (version 0.2.3)

param_dr: Parameter Estimation: Double-robust estimator

Description

For each identified subgroup and in the overall population, use the double robust estimator (Funk et al 2011). For continuous and binary outcomes, this outputs estimates for E(Y|A=1), E(Y|A=0), and E(Y|A=1)-E(Y|A=0).

Usage

param_dr(Y, A, X, mu_hat, Subgrps, alpha_ovrl, alpha_s, ...)

Arguments

Y

The outcome variable. Must be numeric (binary, continuous)

A

Treatment variable. (a=1,...A)

X

Covariate space.

mu_hat

Patient-level estimates (See PLE_models)

Subgrps

Identified subgroups (can be the overall population)

alpha_ovrl

Two-sided alpha level for overall population

alpha_s

Two-sided alpha level at subgroup

...

Any additional parameters, not currently passed through.

Value

Data-set with parameter estimates and corresponding variability metrics, for overall and subgroups. Subgrps=0 corresponds to the overall population by default.

• param.dat - Parameter estimates and variability metrics (est, SE, LCL/UCL = lower/upper confidence limits, pval = p-value).

References

Funk et al. Doubly Robust Estimation of Causal Effects. Am J Epidemiol 2011. 173(7): 761-767.

Examples

# NOT RUN {
library(StratifiedMedicine)

## Continuous ##
dat_ctns = generate_subgrp_data(family="gaussian")
Y = dat_ctns$Y
X = dat_ctns$X
A = dat_ctns$A

## Estimate PLEs (ranger) ##
res_ranger = ple_train(Y, A, X, Xtest=X, ple="ple_ranger")

## Identify Subgroups: MOB (lmtree) ##
res_lmtree = submod_train(Y, A, X, Xtest=X, submod="submod_lmtree")

## Parameter-estimation ##
params = param_dr(Y, A, X, mu_hat = res_ranger$mu_train,
                  Subgrps = res_lmtree$Subgrps.train, alpha_ovrl=0.05,
                  alpha_s=0.05)
params

# }