ATTMatchPath: Matching estimator for the ATT

In kolesarm/ATEHonest: Honest Inference for Treatment Effects under Unconfoundedness

Description

Computes the matching estimator and the matching weights for a range of matches M. The output of this function is used as an input for ATTMatchEstimate for inference on the conditional average treatment effect for the treated (CATT) and population average treatment effect for the treated (PATT).

Usage

ATTMatchPath(y, d, D0, M = 1:25, tol = 1e-12)

Arguments

y	outcome vector with length n.
d	vector of treatment indicators with length n.
D0	matrix of distances with dimension n1 by n0 between untreated and treated units, where n0 is the number of untreated units and n1 is the number of treated units.
M	a vector of integers determining the number of matches. If Inf, then use the simple difference in means estimator.
tol	numerical tolerance for determining nearest neighbors in constructing matches

Value

List with the following components:

ep

A data frame with columns M, maxbias, att, and lindw corresponding to the number of matches, the scaled worst-case bias, the ATT estimate, and the largest Lindeberg weight.

K

A matrix where each row j corresponds to the linear weights k used to form the matching estimator with M[j] matches.

d

Vector of treatment indicators, as supplied by d

y

Vector of outcomes, as supplied by y

tol

The tolerance parameter tol, as supplied by tol

D0

The distance matrix, as supplied by D0

Examples

## Construct distance matrix
Ahalf <- diag(c(0.15, 0.6, 2.5, 2.5, 2.5, 0.5, 0.5, 0.1, 0.1))
D0 <- distMat(NSWexper[, 2:10], Ahalf, method="manhattan", NSWexper$treated)
ATTMatchPath(NSWexper$re78, NSWexper$treated, D0, M=1:2, tol=1e-12)

kolesarm/ATEHonest documentation built on Nov. 14, 2020, 4:50 a.m.