Learn R Programming

kbal (version 0.1.2)

Kernel Balancing

Description

Provides a weighting approach that employs kernels to make one group have a similar distribution to another group on covariates. This method matches not only means or marginal distributions but also higher-order transformations implied by the choice of kernel. 'kbal' is applicable to both treatment effect estimation and survey reweighting problems. Based on Hazlett, C. (2020) "Kernel Balancing: A flexible non-parametric weighting procedure for estimating causal effects." Statistica Sinica. .

Copy Link

Version

Install

install.packages('kbal')

Monthly Downloads

192

Version

0.1.2

License

GPL (>= 2)

Issues

Pull Requests

Stars

Forks

Maintainer

Borna Bateni

Last Published

March 14th, 2025

Functions in kbal (0.1.2)

one_hot

One-Hot Encoding for Categorical Data
biasbound

Worst-Case Bias Bound due to Incomplete Balance
makeK

Build the Gaussian Kernel Matrix
dimw

Difference in Means and Difference in Weighted Means
lalonde

Data from National Supported Work program and Panel Study in Income Dynamics
b_maxvarK

Maximum Variance of Gaussian Kernel Matrix
getdist

L1 Distance
drop_multicollin

Drop Multicollinear Columns
ebalance_custom

Modified version of ebalance (originally from Jens Hainmueller)
getw

Find Weights using Entropy Balancing.
kbal

Kernel Balancing