Entropy-balancing weights (Hainmueller 2012)

Routes to the shared native entropy-balancing solver (smallstats_native.R): control units are reweighted so their covariate means match the treated means exactly (ATT).

Usage

morie_weight_entropy(data, treatment, covariates)

Arguments

data

Data frame.

treatment

Binary treatment column (0/1).

covariates

Covariate column names.

Value

A morie_weight object (ATT estimand).

References

Hainmueller (2012) Political Analysis 20(1).

Examples

d <- data.frame(t = rbinom(100, 1, 0.4), x = rnorm(100))
morie_weight_entropy(d, "t", "x")
#> morie_weight: entropy balancing (Hainmueller 2012) (estimand ATT)
#>   n = 100  ESS = 99.7  weight range [0.877, 1.138]