dr_quant_est: The Doubly Robust Quantile Estimator for a Given Treatment...

In quantoptr: Algorithms for Quantile- And Mean-Optimal Treatment Regimes

Description

Given a fixed treatment regime, this doubly robust estimator estimates the marginal quantile of responses when it is followed by every unit in the target population. It took advantages of conditional quantile functions for different treatment levels when they are available.

Usage

dr_quant_est(beta, x, y, a, prob, tau, y.a.0, y.a.1, num_min = FALSE)

Arguments

beta	a vector indexing the treatment regime. It indexes a linear treatment regime: d(x)= I{β_0 + β_1*x_1 + ... + β_k*x_k > 0}.
x	a matrix of observed covariates from the sample. Notice that we assumed the class of treatment regimes is linear. This is important that columns in x matches with beta.
y	a vector, the observed responses from a sample
a	a vector of 0s and 1s, the observed treatments from a sample
prob	a vector, the propensity scores of getting treatment 1 in the samples
tau	The quantile of interest
y.a.0	Estimated conditional potential outcome given that treatment = 0, which can be calculated by the function augX.
y.a.1	Estimated conditional potential outcome given that treatment = 1, which can be calculated by the function augX.
num_min	logical. If TRUE, the number of global minimizers for the objective function is returned.

Details

The double robustness property means that it can consistently estimate the marginal quantile when either the propensity score model is correctly specified, or the conditional quantile function is correctly specified.

See Also

augX

quantoptr documentation built on May 2, 2019, 4:03 p.m.