bootstrap_bal: Bootstrap standard errors for estimated counterfactual with...

In ebenmichael/ents: Maximum Entropy Synthetic Controls

Description

Bootstrap standard errors for estimated counterfactual with synth

Usage

bootstrap_bal(outcomes, metadata, n_boot, hyperparam, trt_unit = 1,
  link = c("logit", "linear", "pos-linear"), regularizer = c(NULL, "l1",
  "l2", "ridge", "linf"), normalized = TRUE, cols = list(unit = "unit", time
  = "time", outcome = "outcome", treated = "treated"), opts = list())

Arguments

outcomes	Tidy dataframe with the outcomes and meta data
metadata	Dataframe of metadata
n_boot	Number of bootstrap samples
hyperparam	Regularization hyperparameter
trt_unit	Treated unit
link	Link function for weights
regularizer	Dual of balance criterion
normalized	Whether to normalize the weights
cols	Column names corresponding to the units, time variable, outcome, and treated indicator
opts	Optimization options MAX_ITERS Maximum number of iterations to run EPS Error tolerance
outcome_col	Column name which identifies outcomes, if NULL then assume only one outcome

Value

outcomes with additional synthetic control added and weights

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