Diff-in-diff estimation with resampling from large dataset - r

Question

I have a large dataset on which to perform a diff-in-diff estimation. Given the nature of the dataset my t-statistics denominators are inflated and coefficient are (surreptitiously) statistically significant.
I want to step-by-step reducing the number of element in the database, and for each step resample a large number of times and re-estimating each time interaction coefficient and standard errors.
Then I want to take all the averages estimates and standard error, and plot them on a graph, to show at what point (if any) they are not statistically different from zero.
My code follows with a toy example.
I am not sure this is the most efficient way to tackle the problem
I cannot retrieve and thus plot the confidence interval
I am not sure the sampling is representative given the existence of different groups.
Toy example (Creds Torres-Reyna - ‎2015)
library(foreign)
library(dplyr)
library(ggplot2)
df_0 <- NULL
for (i in 1:length(seq(5,nrow(mydata)-1,5))){
index <- seq(5,nrow(mydata),5)[i]
df_1 <- NULL
for (j in 1:10){
mydata_temp <- mydata[sample(nrow(mydata), index), ]
didreg = lm(y ~ treated + time + did, data = mydata_temp)
out <- summary(didreg)
new_line <- c(out$coefficients[,1][4], out$coefficients[,2][4], index)
new_line <- data.frame(t(new_line))
names(new_line) <- c("c","s","i")
df_1 <- rbind(df_1,new_line)
}
df_0 <- rbind(df_0,df_1)
}
df_0 <- df_0 %>% group_by(i) %>% summarise(coefficient <- mean(c, na.rm = T),
standard_error <- mean(s, na.rm = T))
names(df_0) <- c("i","c","s")
View(df_0)

Answer 1

Consider the following refactored code using base R functions: within, %in%, nested lapply, setNames, aggregate, and do.call. This approach avoids calling rbind in a loop and compactly re-writes code without constantly using $ column referencing.
library(foreign)
mydata = read.dta("http://dss.princeton.edu/training/Panel101.dta")
mydata <- within(mydata, {
time <- ifelse(year >= 1994, 1, 0)
treated <- ifelse(country %in% c("E", "F", "G"), 1, 0)
did <- time * treated
})
# OUTER LIST OF DATA FRAMES
df_0_list <- lapply(1:length(seq(5,nrow(mydata)-1,5)), function(i) {
index <- seq(5,nrow(mydata),5)[i]
# INNER LIST OF DATA FRAMES
df_1_list <- lapply(1:100, function(j) {
mydata_temp <- mydata[sample(nrow(mydata), index), ]
didreg <- lm(y ~ treated + time + did, data = mydata_temp)
out <- summary(didreg)
new_line <- c(out$coefficients[,1][4], out$coefficients[,2][4], index)
new_line <- setNames(data.frame(t(new_line)), c("c","s","i"))
})
# APPEND ALL INNER DFS
df <- do.call(rbind, df_1_list)
return(df)
})
# APPEND ALL OUTER DFS
df_0 <- do.call(rbind, df_0_list)
# AGGREGATE WITH NEW COLUMNS
df_0 <- within(aggregate(cbind(c, s) ~ i, df_0, function(x) mean(x, na.rm=TRUE)), {
upper = c + s
lower = c - s
})
# RUN PLOT
within(df_0, {
plot(i, c, ylim=c(min(c)-5000000000, max(c)[phone]), type = "l",
cex.lab=0.75, cex.axis=0.75, cex.main=0.75, cex.sub=0.75)
polygon(c(i, rev(i)), c(lower, rev(upper)),
col = "grey75", border = FALSE)
lines(i, c, lwd = 2)
})

Answer 2

In the end I solved it like this:
Is this the most efficient way?
library(foreign)
library(dplyr)
mydata = read.dta("http://dss.princeton.edu/training/Panel101.dta")
mydata$time = ifelse(mydata$year >= 1994, 1, 0)
mydata$treated = ifelse(mydata$country == "E" |
mydata$country == "F" |
mydata$country == "G", 1, 0)
mydata$did = mydata$time * mydata$treated
df_0 <- NULL
for (i in 1:length(seq(5,nrow(mydata)-1,5))){
index <- seq(5,nrow(mydata),5)[i]
df_1 <- NULL
for (j in 1:100){
mydata_temp <- mydata[sample(nrow(mydata), index), ]
didreg = lm(y ~ treated + time + did, data = mydata_temp)
out <- summary(didreg)
new_line <- c(out$coefficients[,1][4], out$coefficients[,2][4], index)
new_line <- data.frame(t(new_line))
names(new_line) <- c("c","s","i")
df_1 <- rbind(df_1,new_line)
}
df_0 <- rbind(df_0,df_1)
}
df_0 <- df_0 %>% group_by(i) %>% summarise(c = mean(c, na.rm = T), s =
mean(s, na.rm = T))
df_0 <- df_0 %>% group_by(i) %>% mutate(upper = c+s, lower = c-s)
df <- df_0
plot(df$i, df$c, ylim=c(min(df_0$c)-5000000000, max(df_0$c)[phone]), type = "l")
polygon(c(df$i,rev(df$i)),c(df$lower,rev(df$upper)),col = "grey75", border = FALSE)
lines(df$i, df$c, lwd = 2)