Suicide Rates Analysis(1985 to 2016)
Suicide Rates Overview 1985 to 2016
Data Source United Nations Development Program. (2018). Human development index (HDI). Retrieved from http://hdr.undp.org/en/indicators/137506
World Bank. (2018). World development indicators: GDP (current US$) by country:1985 to 2016. Retrieved from http://databank.worldbank.org/data/source/world-development-indicators#
[Szamil]. (2017). Suicide in the Twenty-First Century [dataset]. Retrieved from https://www.kaggle.com/szamil/suicide-in-the-twenty-first-century/notebook
World Health Organization. (2018). Suicide prevention. Retrieved from http://www.who.int/mental_health/suicide-prevention/en/
data <- read_csv("master.csv")## Parsed with column specification:
## cols(
## country = col_character(),
## year = col_double(),
## sex = col_character(),
## age = col_character(),
## suicides_no = col_double(),
## population = col_double(),
## `suicides/100k pop` = col_double(),
## `country-year` = col_character(),
## `HDI for year` = col_double(),
## `gdp_for_year ($)` = col_number(),
## `gdp_per_capita ($)` = col_double(),
## generation = col_character()
## )Global Trend
#global trend
a<-data %>%
group_by(year)%>%
mutate(sum_year=sum(`suicides/100k pop`))
ggplot(a,aes(year,sum_year))+geom_line()+geom_point()+
geom_line(col = "deepskyblue3", size = 1) +
geom_point(col = "deepskyblue3", size = 2) +
labs(title = "Global Suicides (per 100k)",
subtitle = "Trend over time, 1985 - 2015.",
x = "Year",
y = "Suicides per 100k") +
scale_x_continuous(breaks = seq(1985, 2015, 2)) +
scale_y_continuous(breaks = seq(10, 20))
Insights
Globally the Suicide rate has dropped compared to 1985
Suicide rate has gradually incereased from 1985 till 1995 where the global suicide rate was all time high.
The Highest Drop at suicide rate was observed within 2015 and 2016 but this is observation might be incorrenct due to lack of data points at that certain year.
Cleaning the Data
Dropped the suicides/100k pop & HDI for year variable due to in efficient labeling.Furthermore some variables labling was renamed to make it more concise.
tidy_data <- data %>%
select(-c(`HDI for year`, `suicides/100k pop`)) %>%
rename(gdp_for_year = `gdp_for_year ($)`,
gdp_per_capita = `gdp_per_capita ($)`,
country_year = `country-year`) %>%
as.data.frame()Adding Continent
Added continent for each country in our observations via using the countrycode package.
tidy_data$continent <- countrycode(sourcevar = tidy_data[, "country"],
origin = "country.name",
destination = "continent")Factoring the Colums
tidy_data$generation <- factor(tidy_data$generation,
ordered = T,
levels = c("G.I. Generation",
"Silent",
"Boomers",
"Generation X",
"Millenials",
"Generation Z"))
tidy_data <- as_tibble(tidy_data)Suicides Per 100k in Each continent
b<-tidy_data %>% group_by(continent) %>%
summarize(population = sum(population),
suicides = sum(suicides_no),
suicides_per_100k = (suicides / population) * 100000)
ggplot(b, aes(continent,suicides_per_100k,fill=continent))+
geom_bar(stat = "identity")
Insights 1. Europe has the highest rate of the Suicide.
- Africa has the lowest rate of suicide
Suicides per 100k in between each Generation
tidy_data %>% group_by(generation) %>%
summarize(
population = sum(population),
suicides = sum(suicides_no),
suicides_per_100k = (suicides / population) * 100000
) %>%
ggplot(aes(generation,suicides_per_100k,fill=generation))+geom_bar(stat = "identity")
Suicide rates in male-female
tidy_data %>% group_by(sex) %>%
summarize(
population = sum(population),
suicides = sum(suicides_no),
suicides_per_100k = (suicides / population) * 100000
) %>%
ggplot(aes(sex,suicides_per_100k,fill=sex))+geom_bar(stat = "identity")
Trend over time, By Sex
trend_sex<-tidy_data %>%
group_by(year,sex) %>%
summarise(
population = sum(population),
suicides = sum(suicides_no),
suicides_per_100k = (suicides / population) * 100000
)
ggplot(trend_sex,aes(year,suicides_per_100k,color=sex),)+
geom_line(size=1)+
geom_point(size=2)+
facet_wrap(~sex,nrow = 2,scales = 'free')+
labs(title = "Trends Over Time, by Sex",
x = "Year",
y = "Suicides per 100k",
color = "Sex") +
theme(legend.position = "none") +
scale_x_continuous(breaks = seq(1985, 2015, 5), minor_breaks = F)
Global Suicides per 100k, by Country
country <- tidy_data %>%
group_by(country, continent) %>%
summarize(n = n(),
suicide_per_100k = (sum(as.numeric(suicides_no)) / sum(as.numeric(population))) * 100000) %>%
arrange(desc(suicide_per_100k))
country$country <- factor(country$country,
ordered = T,
levels = rev(country$country))
ggplot(country, aes(x = country, y = suicide_per_100k, fill = continent)) +
geom_bar(stat = "identity") +
labs(title = "Global suicides per 100k, by Country",
x = "Country",
y = "Suicides per 100k",
fill = "Continent") +
coord_flip() +
scale_y_continuous(breaks = seq(0, 45, 2)) +
theme(legend.position = "bottom")
GDP & Suicide Rate
We see from our previous analysis that Suicide Rate in europian countries are High.So is there any corelation between a country’s GDP and suicide rate? Here each data point represents each country
gdp_suicide_rate <- tidy_data %>%
group_by(country,continent)%>%
summarise(
population = sum(population),
suicides = sum(suicides_no),
suicides_per_100k = (suicides / population) * 100000,
gdp_per_capita = mean(gdp_per_capita))
gdp_suicide_rate<- gdp_suicide_rate %>% ungroup() %>%
arrange(desc(suicides_per_100k))
ggplot(gdp_suicide_rate,aes(gdp_per_capita,suicides_per_100k,color=continent))+
geom_point(aes(alpha=0.01))+
geom_jitter()
It’s Hard to see any trend with this scatter plot so we add a smooth line with geom_smooth().
## `geom_smooth()` using formula 'y ~ x'
there’s a slight positive corelation between the gdp_per_capita & suicides_per_100k
Let’s look into Asia
gdp_suicide_rate_asia<-gdp_suicide_rate %>%
filter(continent=="Asia")
ggplot(gdp_suicide_rate_asia,aes(gdp_per_capita,suicides_per_100k,color="red"))+
geom_point(size=2)+
geom_jitter() +
geom_smooth(method = "lm")## `geom_smooth()` using formula 'y ~ x'
Asia seems to have a negetive corelation between gdp_per_capita & suicides_per_100k