Learn R Programming

SVMMatch (version 1.1)

control.overlap: Assessing the number of control observations used in estimating the treatment effect.

Description

control.overlap returns a diagnostic plot showing the posterior mass over the number of control observations estimated in the common support region between the treatment and control groups.

Usage

control.overlap(obj, color=TRUE, label.main="Assessing Control Overlap", label.x="Size of Control Set", label.y="Mass")

Arguments

obj
A fitted SVMMatch object.
color
Whether to plot in color or black and white. TRUE or FALSE.
label.main
Main title for figure
label.x
X-axis label.
label.y
Y-axis label.

Value

counts
Table containing posterior mass of number untreated observations.

Details

Gives the posterior mass of control observations that fall in the common support region between treated and untreated obsevations. These are the only observations used in constructing the treatment effect.

References

Ratkovic, Marc. 2014. "Balancing within the Margin: Causal Effect Estimation with Support Vector Machines." Working paper.

See Also

svmmatch

Examples

Run this code
## Not run: 
# ##See svmmatch() for a full implementation
# ##Load data
# 	data("LaLonde")
# 	Data1<-LaLonde
# 	Data1<-Data1[Data1$exper==0|Data1$treat==1,]
# 	attach(Data1)	
# 
# ##Format X matrix
# 	varnames<-c("age","educ","black","married","nodegr","hisp",
# 		"re75","re74")
# 	X<-cbind(Data1[,varnames],Data1$re75==0,Data1$re74==0)
# 	X<-as.matrix(X)
# 
# ##Fit model
# 	set.seed(1)
# 	m1.param<-svmmatch(treat, X, dv=re78, burnin=100, gibbs=100, thin=5)
# 
# ##Assess ignorability:	
# 	#Assess control overlap--are there enough
# 	#controls to balance the treated?
# 		cont1<-control.overlap(m1.param)	
# 
# 	## End(Not run)

Run the code above in your browser using DataLab