weighted_test_bal: Get the weighted permutation distribution of SC estimate test...

In ebenmichael/ents: Maximum Entropy Synthetic Controls

Description

Get the weighted permutation distribution of SC estimate test statistics estimating p-scores with logit-link synth

Usage

weighted_test_bal(outcomes, metadata, trt_unit, hyperparam, link = c("logit",
  "linear", "pos-linear"), regularizer = c(NULL, "l1", "l2", "ridge", "linf"),
  normalized = TRUE, statfuncs = c(rmse_ratio, mean_abs, abs_tstat),
  cols = list(unit = "unit", time = "time", outcome = "outcome", treated =
  "treated"))

Arguments

outcomes	Tidy dataframe with the outcomes and meta data
metadata	Dataframe of metadata
trt_unit	Unit that is treated (target for regression), default: 0
statfuncs	Function to compute test stats
cols	Column names corresponding to the units, time variable, outcome, and treated indicator
n_sim	Number of montecarlo samples

Value

att estimates, test statistics, p-values

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