library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.5.0     ✔ tibble    3.2.1
## ✔ lubridate 1.9.3     ✔ tidyr     1.3.1
## ✔ purrr     1.0.2     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
getwd()
## [1] "C:/Users/홍지민/Desktop/24-1/데이터/PS2"
"C:/Users/홍지민/Desktop/24-1/데이터/PS2"
## [1] "C:/Users/홍지민/Desktop/24-1/데이터/PS2"
setwd("C:/Users/홍지민/Desktop/24-1/데이터/PS2")
leaders <- read.csv("leaders.csv")

#1

library(ggplot2)
ggplot(data = leaders, aes(x = year, y = polityafter, label = country)) + 
  geom_point() +
  geom_smooth() +
  geom_text(size = 2)
## `geom_smooth()` using method = 'loess' and formula = 'y ~ x'
## Warning: The following aesthetics were dropped during statistical transformation: label.
## ℹ This can happen when ggplot fails to infer the correct grouping structure in
##   the data.
## ℹ Did you forget to specify a `group` aesthetic or to convert a numerical
##   variable into a factor?

#2

library(forcats)
library(dplyr)
leaders <- leaders %>% 
  mutate(result = fct_recode(result,
    "dies" = "dies between a day and a week",
    "dies" = "dies within a day after the attack",
    "dies" = "dies between a week and a month",
    "dies" = "dies, timing unknown",
    "survives" = "hospitalization but no permanent disability",
    "survives" = "not wounded", 
    "survives" = "plot stopped", 
    "survives" = "survives but wounded severely",
    "survives" = "survives, whether wounded unknown",
    "survives" = "wounded lightly")) %>%
  mutate(success = ifelse(result == "dies", 1, 0))
success_rate <- mean(leaders$success)

Overall success rate is 21.6%.

#3

library(ggplot2) 
library(dplyr)

successful_attempts <- filter(leaders, success == 1)
failed_attempts <- filter(leaders, success == 0)

ggplot(data = leaders) +
  geom_point(mapping = aes(x = 0, y = politybefore, color = factor(success))) +
  labs(title = "Polity Scores Over 3 Years Prior to Assassination Attempt",
       x = "Success of Assassination Attempt",
       y = "Polity Score 3 Years Before",
       color = "Success")

One that has failed, thus survives tend to have higher polity scores.

summary(successful_attempts$politybefore)
##     Min.  1st Qu.   Median     Mean  3rd Qu.     Max. 
## -10.0000  -6.0000  -3.0000  -0.7037   5.5000  10.0000
summary(failed_attempts$politybefore)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
## -10.000  -7.000  -3.000  -1.743   3.000  10.000
sd(successful_attempts$politybefore)
## [1] 6.541808
sd(failed_attempts$politybefore)
## [1] 6.417421

However, although they have same minimum value of -10 and maximum value of 10, mean for successful attempts is -0.7037 and mean for failed attempts is -1.743. However, since the standard deviation for successful attempt is 6.54 and failed attempt is 6.42, it doesn’t have major difference.

#4

successful_change <- mean(successful_attempts$polityafter - successful_attempts$politybefore)
failed_change <- mean(failed_attempts$polityafter - failed_attempts$politybefore)

No. There is only 0.059 difference between after and before the assassination. Also, even though the assassination fails, there is 0.15 difference for the average polity scores.