cem (version 1.0.120)

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 chosen to calculate it, and as such the comparison of different matching solutions may differ depending on this somewhat arbitrary choice. This function computes L1 for a very wide range of possible coarsenings. The point of this function is that if one matching solution has a lower L1 than another, then it dominates without regard to the choice of coarsening. A graphic display conveys the results succinctly. (The logic is similar to that for ROC curves used for classification algorithms.) (This degree of coarsening should remain fixed for different CEM runs.)

This function first tries to move the cutpoints of 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. 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: Coarsened Exact Matching,'' 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"))