Learn R Programming

⚠️There's a newer version (0.10.8) of this package.Take me there.

optmatch (version 0.9-17)

Functions for Optimal Matching

Description

Distance based bipartite matching using the RELAX-IV minimum cost flow solver, oriented to matching of treatment and control groups in observational studies. Routines are provided to generate distances from generalised linear models (propensity score matching), formulas giving variables on which to limit matched distances, stratified or exact matching directives, or calipers, alone or in combination.

Copy Link

Version

Install

install.packages('optmatch')

Monthly Downloads

6,120

Version

0.9-17

License

file LICENSE

Issues

Pull Requests

Stars

Forks

Repository

https://github.com/markmfredrickson/optmatch

Maintainer

Mark Fredrickson

Last Published

February 22nd, 2022

Functions in optmatch (0.9-17)

as.InfinitySparseMatrix

Convert an object to InfinitySparseMatrix

cbind.InfinitySparseMatrix

Combine InfinitySparseMatrices or BlockedInfinitySparseMatrices by row or column

InfinitySparseMatrix-class

Objects for sparse matching problems.

compare_optmatch

Compares the equality of optmatch objects, ignoring attributes and group names.

Specify a matching problem where units in a common factor cannot be matched.

BlockedInfinitySparseMatrix-class

Blocked Infinity Sparse Matrix

Combine Optmatch objects

Prepare matching distances suitable for matching within calipers.

(Internal) Determines how many other units fall within a caliper distance

caliperUpperBound

(Internal) Returns a reasonable upper bound on the arcs remaining after placing a caliper.

dimnames,InfinitySparseMatrix-method

Get and set dimnames for InfinitySparseMatrix objects

effectiveSampleSize

Compute the effective sample size of a match.

(Internal) Remove the call before digesting a distance so things like omitting caliper and calling caliper=NULL give the same digest #

num_eligible_matches

Returns the number of eligible matches for the distance.

optmatch-defunct

Functions deprecated or removed from optmatch

+,InfinitySparseMatrix,InfinitySparseMatrix-method

Element-wise addition

Nuclear Power Station Construction Data

subset.InfinitySparseMatrix

Subsetting for InfinitySparseMatrices

Combine multiple distance specifications into a single distance specification.

Printing optmatch objects.

model.frame.svyglm

This method quells a warning when optmatch::scores() is applied to a svyglm object.

Returns the dimension of each valid subproblem

Display license information about embedded code

findSubproblems

List subproblems of a distance

fmla2treatedblocking

(Internal) A helper function to turn formulas into treatment and blocking variables

Optimal full matching

show,BlockedInfinitySparseMatrix-method

Displays a BlockedInfinitySparseMatrix

(Internal) Sets up option to try recovery in fullmatch.

getMaxProblemSize

What is the maximum allowed problem size?

(Internal) Create optmatch objects, the result of matching.

matched.distances

Determine distances between matched units

Create treated to control distances for matching problems

subproblemSuccess

(Internal) Report successful subproblems.

Find the minimal exact match factors that will be feasible for a given maximum problem size.

(Deprecated, in favor of match_on) Create matching distances

stratumStructure

Return structure of matched sets

standardization_scale

pooled dispersion for a numeric variable

Find the maximum caliper width that will create a feasible problem.

(Internal) Predict for CBPS objects

Set thinning and thickening caps for full matching

Dissimilarities of Some U.S. Nuclear Plants

(Internal) If the x argument does not exist for match_on, fullmatch, or pairmatch, use this function to print a helpful message.

optmatch_same_distance

Checks if two distances are equivalent. x and y can be distances (InfinitySparseMatrix, BlockedInfinitySparseMatrix, or DenseMatrix), or they can be optmatch objects.

Generate an exact matching set of subproblems.

Create missingness indicator variables and non-informatively fill in missing values

optmatch_restrictions

optmatch_restrictions

(Internal) Helper function to create an InfinitySparseMatrix from a set of scores, a treatment indicator, and a caliper width.

match_on_szn_scale

pooled dispersion for a numeric variable Dispersion as pooled across a treatment and a control group. By default, the measure of dispersion calculated within each group is not the ordinary standard deviation but rather the robust alternative provided by stats::mad.

Identification of units placed into matched sets

Optimal 1:1 and 1:k matching

setMaxProblemSize

Set the maximum problem size

setFeasibilityConstants

(Internal) Sets up the default values for maximum feasible problems

show,InfinitySparseMatrix-method

Displays an InfinitySparseMatrix

sort.InfinitySparseMatrix

Sort the internal structure of an InfinitySparseMatrix.

Extract scores (propensity, prognostic,...) from a fitted model

validDistanceSpecification

(Internal) Validate that objects are valid distance specifications.

Summarize a distance matrix

update.optmatch

Performs an update on an optmatch object.