PAPE: Estimation of the Population Average Prescription Effect in...

In experiment: R Package for Designing and Analyzing Randomized Experiments

Estimation of the Population Average Prescription Effect in Completely Randomized Experiments

Description

This function estimates the Population Average Prescription Effect with and without a budget constraint. The details of the methods for this design are given in Imai and Li (2019).

Usage

PAPE(T, That, Y, plim = NA)

Arguments

T	The unit-level binary treatment receipt variable.
That	The unit-level binary treatment that would have been assigned by the individualized treatment rule.
Y	The outcome variable of interest.
plim	The maximum percentage of population that can be treated under the budget constraint. Should be a decimal between 0 and 1. Default is NA which assumes no budget constraint.

Value

A list that contains the following items:

pape	The estimated Population Average Prescription Effect.
sd	The estimated standard deviation of PAPE.

Author(s)

Michael Lingzhi Li, Operations Research Center, Massachusetts Institute of Technology [e-mail], http://mlli.mit.edu;

References

Imai and Li (2019). “Experimental Evaluation of Individualized Treatment Rules”,

experiment documentation built on April 13, 2022, 1:06 a.m.