rrp.dist {rrp} | R Documentation |
Main piece of the RRP algorithm which generates the RRP dissimilarity matrix.
rrp.dist(X, treated = NULL, msplit = 10, Rep = 250, cut.in = 15, check.bal = FALSE, plot = FALSE, asdist = FALSE, verbose = 0)
X |
a data.frame object |
treated |
optional class indicator variable |
msplit |
minimum split parameter in the rpart algorithm |
Rep |
number of RRP replications |
cut.in |
number of breaks in which to cut continuous variables |
check.bal |
indicator function. If TRUE balance check using
hyper-rectangles will be used inside leaves |
plot |
wheter to plot the porximity matrix as image |
asdist |
if TRUE returns an object of class dist |
verbose |
if greater than 1 some information is printed |
This algorithm allows for missing data in X
. From version 1.6 of the
package the RRP matrix is stored as an external pointer to avoid duplications.
This allow to work on bigger datasets.
an object of class externalptr, XPtr
or dist
S.M. Iacus
Iacus, S.M., Porro, G. (2009) Random Recursive Partitioning: a matching method for the estimation of the average treatment effect, Journal of Applied Econometrics, 24, 163-185.
Iacus, S.M., Porro, G. (2007) Missing data imputation, matching and other applications of random recursive partitioning, Computational Statistics and Data Analysis, 52, 2, 773-789.