rm(list=ls())
library(tidyverse)
library(data.table)
library(ggplot2)
library(readxl)
library(RColorBrewer)
library(wooldridge)
library(foreign)
df = read.dta("http://dss.princeton.edu/training/Panel101.dta")

# 1) Create a dummy variable to indicate the time when the treatment started. Lets
#assume that treatment started in 1994. In this case, years before 1994 will have a
#value of 0 and 1994+ a 1.

## 2) Create a dummy variable to identify the group exposed to the treatment. In this
#example lets assumed that countries with code 5,6, and 7 were treated (=1).
#Countries 1-4 were not treated (=0). 

# 3) Create an interaction between time and the treated. The coefficient on the interaction corresponds to the DiD estimate.

df <- df %>% 
  mutate (after = ifelse(year >= 1994, 1, 0)) %>%
  mutate(treated = ifelse(country == "E"|country == "F"|country == "G",1,0)) %>%
  mutate(treated_after = after*treated)



DiD_mod = lm(y ~ treated + after + treated_after, data = df)
summary(DiD_mod)
# The coefficient for treated_after is the differences-in-differences estimator.
# The effect is significant at 10% with the treatment having a negative effect.