balance: Covariate Balancing Weights via Generalized Projections of...

In kevjosey/cbal: Covariate Balancing Weights using Generalized Projections of Bregman Distances

Covariate Balancing Weights via Generalized Projections of Bregman Distances

Description

The balance_ATE(), balance_ATT(), and balance_OWATE() functions solve a convex program with linear equality constraints determined by the data, the estimand (ATE, ATT, or OWATE), and the sampling weights (base_weights).

Usage

balance_ATE(
  X,
  Y,
  Z,
  base_weights = NULL,
  coefs_init = NULL,
  optim_ctrl = list(maxit = 500, reltol = 1e-10),
  ...
)

balance_ATT(
  X,
  Y,
  Z,
  base_weights = NULL,
  coefs_init = NULL,
  optim_ctrl = list(maxit = 500, reltol = 1e-10),
  ...
)

balance_OWATE(
  X,
  Y,
  Z,
  base_weights = NULL,
  coefs_init = NULL,
  optim_ctrl = list(maxit = 500, reltol = 1e-10),
  ...
)

Arguments

X	the balance functions to be contrained.
Y	the observed responses.
Z	the binary treatment assignment.
base_weights	a vector of optional base weights with length equal to the number of rows in X.
coefs_init	the optional initial values for the dual variables. Default is a vector of zeros with length equal to number of columns in X.
optim_ctrl	a list of arguments that will be passed to optim().
...	additional arguments.

References

Josey KP, Juarez-Colunga E, Yang F, Ghosh D (2019). "A Framework for Covariate Balance using Bregman Distances." arXiv:1903.00390 [stat].

kevjosey/cbal documentation built on July 22, 2023, 11:04 a.m.