[R] Propensity score matching in R using Classification tree method

Frank Harrell f.harrell at vanderbilt.edu
Tue Jan 10 14:43:50 CET 2012


A single tree will undermatch subjects.
Frank

ardsiiitmg wrote
> 
> I can able to calculate the propensity score using classification tree
> method.
> And if i am trying to find the PS matching i am getting error.(Error in
> Match(Y = Y, Tr = Tr, X = ps0) : length(Y) != length(Tr))
> 
> Propensity score matching:
> library("rgenoud")
> library("Matching")
> data("Passport")
> attach("Passport")
> 
> Y<-Passport$A3
> Tr<-Passport$fserv_cd
> rr1<-Match(Y=Y, Tr = Tr, X= glm1$fitted)
> [in above command i am getting Error in Match(Y = Y, Tr = Tr, X = ps0) :
> length(Y) != length(Tr)]
> 
> Matchbalance(fserv_cd~ A4,match.out=rr1,nboots=1000,data=Passport)
> 
> Please suggest me right approach for Propensity score matching using
> classification trees(if possible code me) .
> ps0-propensity score values
> 


-----
Frank Harrell
Department of Biostatistics, Vanderbilt University
--
View this message in context: http://r.789695.n4.nabble.com/Propensity-score-matching-in-R-using-Classification-tree-method-tp4281605p4281981.html
Sent from the R help mailing list archive at Nabble.com.



More information about the R-help mailing list