-
Notifications
You must be signed in to change notification settings - Fork 2
/
README.Rmd
162 lines (126 loc) · 4.68 KB
/
README.Rmd
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
---
output: github_document
editor_options:
chunk_output_type: console
---
<!-- README.md is generated from README.Rmd. Please edit that file -->
```{r, echo = FALSE}
knitr::opts_chunk$set(
warning = FALSE,
message = FALSE,
collapse = TRUE,
comment = "#>",
fig.path = "man/figures/README-",
out.width = "100%"
)
```
# About `lalonde`
[![Travis-CI Build Status](https://travis-ci.org/jjchern/lalonde.svg?branch=master)](https://travis-ci.org/jjchern/lalonde)
[![AppVeyor Build Status](https://ci.appveyor.com/api/projects/status/github/jjchern/lalonde?branch=master&svg=true)](https://ci.appveyor.com/project/jjchern/lalonde)
[![CRAN_Status_Badge](http://www.r-pkg.org/badges/version/lalonde)](https://cran.r-project.org/package=lalonde)
The Lalonde datasets are widely used in the causal inference literature.
The current package makes loading such datasets in R easier. I found myself
calling the following command
```R
haven::read_dta("http://www.nber.org/~rdehejia/data/nsw_dw.dta")
```
in several R projects. It might be easier to just type `lalonde::nsw_dw`.
# Data and Source
- NSW Data Files (Lalonde Sample)
- `lalonde::nsw`
- These files contain the treated and control units from the male sub-sample from the National Supported Work Demonstration as used by Lalonde in his paper.
- NSW Data Files (Dehejia-Wahha Sample)
- `lalonde::nsw_dw`
- Based on pre-intervention variables, Dehejia-Wahha extract a further subset of Lalonde's NSW experimental data, a subset containing information on RE74 (earnings in 1974).
- Non-experimental Comparison Data Files:
- `lalonde::psid_controls`
- `lalonde::psid_controls2`
- `lalonde::psid_controls3`
- `lalonde::cps_controls`
- `lalonde::cps_controls2`
- `lalonde::cps_controls3`
- All the datasets are available in `txt` and `dta` format from Dehejia's [website](http://users.nber.org/~rdehejia/nswdata2.html)
# Installation
```R
# install.packages("devtools")
devtools::install_github("jjchern/lalonde")
```
# Usage
The datasets print nicely in the tidyverse:
```{r}
library(tidyverse)
lalonde::nsw
lalonde::nsw_dw
```
Combine the treatment group from `lalonde::nsw_dw` with a non-experimental
comparison group from the Panel Study of Income Dynamics (PSID):
```{r}
lalonde::nsw_dw %>%
filter(treat == 1) %>%
bind_rows(lalonde::psid_controls) %>%
select(-data_id) %>%
print() -> df
# install.packages("skimr")
skimr::skim(df)
```
The unadjusted difference in means is -$15,205:
```{r}
df %>%
group_by(treat) %>%
summarise(mean_re78 = mean(re78)) %>%
print() %>%
spread(treat, mean_re78, sep = "_") %>%
mutate(diff = treat_1 - treat_0)
```
The naive estimate is certainly biased, because the treated group looks very
different from the control group:
```{r}
# install.packages("cem")
cem::imbalance(group = df$treat,
data = as.data.frame(df),
drop = c("treat", "re78"))
```
The multivariate imbalanced meaure is close to 1, suggesting an almost complete
separation between the treated and control group. The differences in the
empirical quantiles of the two distributions also indicate a large amount of
imbalance for many covariates. For example, the treated group tends to be
younger, has fewer years of education, are less likely to be married, and earns
a lot less in 1974 and 1975.
Matching on the covariates can help to create a matching sample in which the
matched control group is more comparable to the treated group. Below we call
the `cem()` function to implement an automatic coarsened exact matching (CEM):
```{r}
cem::cem(treatment = "treat",
data = as.data.frame(df),
verbose = TRUE,
keep.all = TRUE,
drop = "re78") -> cem
cem
```
The `cem()` function includes the automatic cut points:
```{r}
cem$breaks
```
Alternatively, we can supply some infomation to aid the CEM process. For
example, we can choose to discretize the variable `age`, `educ`, `re74`, `re75`
in the following way:
```{r}
cut_age = seq(min(df$age), max(df$age), by = 15)
cut_educ = c(0, 6.5, 8.5, 12.5, 17)
cut_re74 = seq(0, max(df$re74), by = 5000)
cut_re75 = seq(0, max(df$re75), by = 5000)
cem::cem(treatment = "treat",
data = as.data.frame(df),
verbose = TRUE,
keep.all = TRUE,
drop = "re78",
cutpoints = list(age = cut_age,
educcation = cut_educ,
re74 = cut_re74,
re75 = cut_re75)) -> mat2
mat2
```
Is there a way to improve the number of subjects who can be matched?
```{r cem-relax, message=FALSE, results='hide'}
cem::relax.cem(obj = mat2, data = as.data.frame(df), verbose = FALSE)
```