ATEnocov {experiment}

Estimation of the Average Treatment Effect in Randomized Experiments

Description

This function computes the standard “difference-in-means” estimate of the average treatment effect in randomized experiments without using pre-treatment covariates. The treatment variable is assumed to be binary. Currently, the two designs are allowed: complete randomized design and matched-pair design.

Usage

ATEnocov(Y, Z, data = parent.frame(), match = NULL)

Arguments

Y

The outcome variable of interest.

Z

The (randomized) treatment variable. This variable should be binary.

data

A data frame containing the relevant variables.

match

A variable indicating matched-pairs. The two units in the same matched-pair should have the same value.

Value

A list of class ATEnocov which contains the following items:

call

The matched call.

Y

The outcome variable.

Z

The treatment variable.

match

The matched-pair indicator variable.

ATEest

The estimated average treatment effect.

ATE.var

The estimated variance of the average treatment effect estimator.

diff

Within-pair differences if the matched-pair design is analyzed.

Author(s)

Kosuke Imai, Department of Government and Department of Statistics, Harvard University [e-mail], https://imai.fas.harvard.edu;

References

Imai, Kosuke, (2008). “Randomization-based Inference and Efficiency Analysis in Experiments under the Matched-Pair Design”, Statistics in Medicine.