fit_balancer_formatted: Find Balancing weights by solving the dual optimization...

In ebenmichael/ents: Maximum Entropy Synthetic Controls

Description

Find Balancing weights by solving the dual optimization problem

Usage

fit_balancer_formatted(X, trt, link = c("logit", "linear", "pos-linear"),
  regularizer = c(NULL, "l1", "l2", "ridge", "linf"), hyperparam,
  normalized = TRUE, opts = list())

Arguments

X	n x d matrix of covariates
trt	Vector of treatment status indicators
link	Link function for weights
regularizer	Dual of balance criterion
hyperparam	Regularization hyperparameter
normalized	Whether to normalize the weights
opts	Optimization options MAX_ITERS Maximum number of iterations to run EPS Error rolerance

Value

• theta Estimated dual propensity score parameters

• weights Estimated primal weights

• imbalance Imbalance in covariates

ebenmichael/ents documentation built on May 31, 2019, 8:45 p.m.