match.d_r_odd: Donor-Recipient Matching via Optimal Donor Distribution Method

Description

A function that performs the optimal donor distribution method. GLPK is used to find the optimal solution to the integer program.

Usage

match.d_r_odd(distance = NULL, recipients=NULL, donors=NULL, donor_limit=NULL)

Arguments

distance

A distance matrix of dimensions length(donors) * length(recipients)

recipients

A vector of object (row) numbers from the original data matrix, indicating which objects require imputation.

donors

A vector of object (row) numbers from the original data matrix, indicating which objects may be used for imputation.

donor_limit

A vector of length(donors) detailing how often any one donor may be used.

Value

recipients. The second column, named donors, contains the donor that is matched to any of the recipients.

References

Domschke, W. (1995) Logistik: Transport. Munich: Oldenbourg. [in German]

Joenssen, D.W. (2015) Donor Limited Hot Deck Imputation: A Constrained Optimization Problem. In: B. Lausen, S. Krolak-Schwerdt, and M. B\"ohmer (Eds.): Data Science, Learning by Latent Structures, and Knowledge Discovery. Studies in Classification, Data Analysis and Knowledge Organization, pages 319--328. Berlin/Heidelberg: Springer.

Joenssen, D.W. (2015) Hot-Deck-Verfahren zur Imputation fehlender Daten -- Auswirkungen des Donor-Limits. Ilmenau: Ilmedia. [in German, Dissertation]

Examples

Run this code

#Set the random seed to an arbitrary number
set.seed(421)

#Set up a random distance matrix
   ndonor=20
   nrecip=20
   distance<-matrix(sample(1:100,replace=TRUE,size=ndonor*nrecip),nrow=ndonor,ncol=nrecip)
#Name donors and recipients
   donors<-1:nrow(distance)
   recipients<-(nrow(distance)+1):(nrow(distance)+ncol(distance))
   colnames(distance)<-recipients
   rownames(distance)<-donors
#Set up the donor limit variable
   donor_limit<-rep(1,length(donors))

#perform the matching
match.d_r_odd(distance=distance,recipients=recipients,donors=donors,
   donor_limit=donor_limit)