cem (version 1.0.117)

L1.profile: Calculates L1 distance for different coarsenings

Description

Calculates L1 distance for different coarsenings

Usage

L1.profile(group, data, drop = NULL, min.cut=2, max.cut=6, ref.cut=3, 
 weights, plot=TRUE, add=FALSE, col="red", lty=1)

Arguments

group

the group variable

data

the data

drop

a vector of variable names in the data frame to ignore

min.cut

minimum number of cut points per variable

max.cut

maximum number of cut points per variable

ref.cut

reference number of cut points per variable

weights

weights

plot

plot a graph?

add

add graph to an existing plot? Makes sense only if plot is TRUE

col

draw in specified color

lty

draw using specified lty

Value

• An invisible object of class L1profile which contains a named list of coarsening.

Details

The L1 measure depends on the coarsening. A very fine coarsening on the variables (many cut points) produces values of L1 close to 1. A very mild coarsening (very fex cutpoints), is not able to discriminate, i.e. L1 close to 0. This is particularly true when the number of observations is small with respect to the number of continuous variables.

This function calculates the L1 distance for different levels of coarsening. First tries to move the cut the support of all variables together from min.cut to max.cut. Then, fixing a coarsening into ref.cut number of cut points on all variables, it changes the coarsening one variable at time, again from min.cut to max.cut. Given two matching solutions, if, say, the first method provides values of L1 sistematically smaller then the same values for the second method, uniformly on the cut points choices, then then imbalance has been better reduced by the first method. Non numeric variables are not grouped, i.e. no coarsening occurs.

A plot method exists for the returned object.

References

Stefano Iacus, Gary King, Giuseppe Porro, ``Matching for Casual Inference Without Balance Checking,'' http://gking.harvard.edu/files/abs/cem-abs.shtml

Examples

data(LL)
for(i in c(4:6,10:12))
 LL[[i]] <- factor(LL[[i]])

L1.profile(LL$treated,LL, drop=c("treated","re78"), max.cut=10)

if(require(MatchIt)){
 m2 <- matchit(treated ~ black + hispanic + married + nodegree + u74 + u75 + education +
  age + re74 + re75, data=LL, distance="logit")
 
 L1.profile(LL$treated,LL, drop=c("treated","re78"), max.cut=10, 
  weights=m2$w, add=TRUE, col="green", lty=2)
}

m1 <- cem("treated", LL, drop="re78")

L1.profile(LL$treated,LL, drop=c("treated","re78"), max.cut=10, 
 weights=m1$w, add=TRUE, col="blue", lty=3)

legend(5, 0.9, legend=c("raw data", "pscore", "cem"), lty=1:3, col=c("red", "green", "blue"))