SVMMatch (version 1.1)

balance: Assessing balance when using SVMMatch.

Description

balance returns a diagnostic plot of covariate balance as well as an object containing the posterior estimate of covariate imbalance.

Usage

balance(treat, X, obj, plot.it=TRUE, sd.plot=.2, color=TRUE)

Arguments

treat

A binary vector indicating treatment status.

X

A covariate matrix.

obj

A fitted SVMMatch object.

plot.it

Whether to return a figure illustrating balancing in the raw and balanced data. TRUE or FALSE.

sd.plot

Number of standard deviations at which to include dashed vertical lines in the figure.

color

Whether to plot in color or black and white. TRUE or FALSE.

Value

balance

Posterior density of imbalance, by covariate.

Details

Assess the covariate balance using weights from an SVMMatch object.

References

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

See Also

svmmatch

Examples

## 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 balance
# 	bal1<-balance(treat, X, m1.param)
# 
# 	## End(Not run)