'How to obtain Pair Distance column in summary (MatchIt)
I'm trying to compare different CEM matchings, unfortunately the MatchIt package does not have the L statistic therefore I wanted to compare the Pair Distance conlumn that can be obained with the summary function
How can I print only that column? (Since I apply several trials in the original dataset and the variables are a lot I would like to avoid copy and paste)
library(tidyverse)
library(MatchIt)
data(lalonde)
cem1 <- matchit(treat ~ age + re74 + re75, data = lalonde,
method = "cem")
cem2 <- matchit(treat ~ age + re74 + re75, data = lalonde,
method = "cem",
cutpoints= list(age = c(20.5, 25.5, 30.5,35.5,40.5))
)
summary(cem1, un=TRUE)
summary(cem2, un=TRUE)
resutls I get
Call:
matchit(formula = treat ~ age + re74 + re75, data = lalonde,
method = "cem", cutpoints = list(age = c(20.5, 25.5, 30.5,
35.5, 40.5)))
Summary of Balance for All Data:
Means Treated Means Control Std. Mean Diff. Var. Ratio eCDF Mean eCDF Max
age 25.8162 28.0303 -0.3094 0.4400 0.0813 0.1577
re74 2095.5737 5619.2365 -0.7211 0.5181 0.2248 0.4470
re75 1532.0553 2466.4844 -0.2903 0.9563 0.1342 0.2876
Summary of Balance for Matched Data:
Means Treated Means Control Std. Mean Diff. Var. Ratio eCDF Mean eCDF Max Std. Pair
Dist.
age 25.6286 25.8312 -0.0283 0.6863 0.0222 0.0619 0.2364
re74 1299.0813 1755.5500 -0.0934 1.1026 0.0672 0.3764 0.1321
re75 1016.9323 1228.5970 -0.0657 1.0062 0.0471 0.1852 0.1617
Percent Balance Improvement:
Std. Mean Diff. Var. Ratio eCDF Mean eCDF Max
age 90.8 54.1 72.7 60.8
re74 87.0 85.1 70.1 15.8
re75 77.3 86.2 64.9 35.6
Sample Sizes:
Control Treated
All 429. 185
Matched (ESS) 169.79 175
Matched 288. 175
Unmatched 141. 10
Discarded 0. 0
what I would like to get a table like this one more or less
cem1 cem2
Pair. Dist. Pair. Dist.
age 0.1616 0.2364
re74 0.1289 0.1321
re75 0.1671 0.1617
Sources
This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.
Source: Stack Overflow
| Solution | Source |
|---|
