boxplot_diffs {triplesmatch}

Boxplots of pairwise differences in triples match

Description

Make boxplots of treated - control pair differences before matching, for the two types of triples, and weighted across triples

Usage

boxplot_diffs(m, y, z, yname = NULL)

Arguments

m

'm' element of the list returned from 'triples()' function containing information about matched individuals

y

Named vector containing variable to plot on the y axis. Names must correspond to the units specified in 'm'

z

Vector of treatment indicators. Must be in same order as 'y'

yname

y axis label

Value

Boxplots with treated minus control pair differences for the specified covariate. Boxplots are show for before matching, for the matches with 1 treated individual, for the matches with 2 treated individuals, and for the weighted combination that duplicates the differences for the matches with two treated individuals

Examples

# Generate some data
set.seed(8)
n <- 200
nt <- floor(n * 0.5)
nc <- n - nt
x <- c(rnorm(nt, 0, 1), rnorm(nc, 0.6, 1))
z <- c(rep(1, nt), rep(0, nc))
# Create some strata
ps <- glm(z ~ x, family = binomial)$fitted.values
ps_st <- cut(ps, c(0, quantile(ps, 1/3 * 1:2), 1), labels = 1:3)
# Create a distance matrix
dist <- dist_mahal(data.frame(x = x), z, ps_st)
# Construct the triples match
triplesm <- triples(cost = dist, z = z, st = ps_st, solver = "rlemon")
boxplot_diffs(m = triplesm$m, y = ps, z = z, yname = "Propensity score")