kmatching-package: A package to generate weights according to matching vectors

In davidkane9/kmatching: Creates random vectors fulfilling constraints

Description

Package	kmatching
Type:	Package
Version:	0.3-2
Date:	2015-08-28
License:	GPL-3

Details

Given a data frame and the specified matching vectors and weight vector, the package can extract the matching vectors and weight vector from the data set, and form them to a system of linear equations, whose matrix expression is Aw=b, where A is the matching vectors and b is the weight vector. The package then randomly sample w subject to the non-negativity constraint w_i >= 0 and sum(w)=0. These two constrains bound the simplex and make the sampling space bounded so uniform sampling over the whole sampling space is achievable. Then the w the package generates is the weights.

davidkane9/kmatching documentation built on May 15, 2019, 1:14 a.m.