Skip to content

[MatchIt] Naive Estimator for ATT after Full Matching

2 messages · thebudget72 m@iii@g oii gm@ii@com, Bert Gunter

Original
thebudget72 m@iii@g oii gm@ii@com
# 
Dear R-help ML,

I would like to compute a Naive Estimator for the Average Treatment 
Effect (ATT) after a Propensity Score Matching with full matching.

Since it is full matching, the resulting post-matching database contains 
all the observations of the original dataset.

I came up with this code, which does a weighted average of the outcomes, 
using the weights provided by the matching process, but I'm not sure 
this is the correct way to achieve it.

How can I compute the ATT using a Naive Estimator after PSM?

I know I am supposed to do a regression, but I am interested in 
computing a Naive Estimator as a difference between the means across the 
two groups.


```r
library("MatchIt")
data("lalonde")

m.out2 <- matchit(treat ~ age + educ + race + married +
 ????????????????? nodegree + re74 + re75,
 ????????????????? data = lalonde,
 ????????????????? method = "full",
 ????????????????? distance = "glm",
 ????????????????? link = "probit")

m.data2 <- match.data(m.out2)

te <- weighted.mean(m.data2$re78[m.data2$treat],
 ??????????????????? m.data2$weights[m.data2$treat])
nte <- weighted.mean(m.data2$re78[!m.data2$treat],
 ???????????????????? m.data2$weights[!m.data2$treat])
ne2w <- round(te-nte, 2)

print(paste0("The ATT estimated with a NE is: ", ne2w))
```


Thanks in advance and best regards.
Bert Gunter
# 
Do note, per the posting guide linked below (please read it if you haven't
done so already):

1. *"Questions about statistics:* The R mailing lists are primarily
intended for questions and discussion about the R software. However,
questions about statistical methodology are sometimes posted. If the
question is well-asked and of interest to someone on the list, it *may*
elicit an informative up-to-date answer. "

So do not be surprised if you do not get a response here.
stats.stackexchange.com *may* be a better alternative if you do not.

2. "For questions about functions in standard packages distributed with R
(see the FAQ Add-on packages in R
<https://cran.r-project.org/doc/FAQ/R-FAQ.html#Add-on-packages-in-R>), ask
questions on R-help.
If the question relates to a *contributed package* , e.g., one downloaded
from CRAN, try contacting the package maintainer first."

The matchit package maintainer can be found by: maintainer("matchit") if
you think the above applies.

Cheers,
Bert

Bert Gunter

"The trouble with having an open mind is that people keep coming along and
sticking things into it."
-- Opus (aka Berkeley Breathed in his "Bloom County" comic strip )
On Wed, May 5, 2021 at 11:55 AM <thebudget72 at gmail.com> wrote: