Mortality Rates
Nurdan Bekbolsunov
2024-06-07
For this project I will be using data from Kaggle on “Adult Mortality Rate (2019-2021)”
adult_mort <- read.csv("Adult mortality rate (2019-2021).csv")
adult_mort%>% head(10)## Countries Continent Average_Pop.thousands.people.
## 1 Afghanistan Asia 38947.06
## 2 Albania Europe 2834.57
## 3 Algeria Africa 43445.00
## 4 Angola Africa 33428.62
## 5 Antigua and Barbuda North America 92.67
## 6 Argentina South America 45374.74
## 7 Armenia Europe 2805.73
## 8 Australia Australia 25556.50
## 9 Austria Europe 8917.53
## 10 Azerbaijan Europe 10085.05
## Average_GDP.M.. Average_GDP_per_capita... Average_HEXP... Development_level
## 1 17995.64 462.05 80.53 Short
## 2 16263.16 5737.44 420.17 Short
## 3 160325.54 3690.31 215.53 Short
## 4 72148.29 2158.28 61.29 Short
## 5 1509.63 16290.97 868.60 Average
## 6 443212.28 9767.82 985.36 Short
## 7 13374.14 4766.73 573.12 Short
## 8 1514105.79 59245.44 6186.68 High
## 9 453405.07 50844.26 5778.39 High
## 10 48496.47 4808.75 232.16 Short
## AMR_female.per_1000_female_adults. AMR_male.per_1000_male_adults.
## 1 204.85 322.17
## 2 53.54 103.55
## 3 70.85 102.21
## 4 218.03 316.81
## 5 58.76 103.77
## 6 82.87 143.85
## 7 76.26 228.57
## 8 42.02 74.11
## 9 40.95 75.49
## 10 120.13 250.51
## Average_CDR
## 1 7.08
## 2 10.20
## 3 4.78
## 4 7.88
## 5 6.06
## 6 8.35
## 7 11.82
## 8 6.57
## 9 10.00
## 10 6.90Now, I want to look at the breakdown of the development levels within these countries.
adult_pie <- adult_mort %>%
count(Development_level) %>%
rename(Categorie = Development_level, Count = n)
fig <- plot_ly(adult_pie, labels = ~Categorie, values = ~Count, type = 'pie')
fig <- fig %>% layout(
title = "The breakdown of Countries' development levels (2019-2021)",
xaxis = list(showgrid = FALSE, zeroline = FALSE, showticklabels = FALSE),
yaxis = list(showgrid = FALSE, zeroline = FALSE, showticklabels = FALSE))
figThe pie chart shows that more than half of the countries are still not fully developed. While the countries who are developed or have “high” development level are the smallest. These countries are mainly from Europe and North America. This raises an assumption that the country with lowest CDR will be from High developed country, while the highest from “short” or under developed.
Lets look at the countries with High and Short development levels
#high
adult_mort %>% filter(Development_level == "High") %>% head(10)## Countries Continent Average_Pop.thousands.people. Average_GDP.M..
## 1 Australia Australia 25556.50 1514105.79
## 2 Austria Europe 8917.53 453405.07
## 3 Belgium Europe 11537.93 551810.42
## 4 Canada North America 37944.96 1797603.40
## 5 Denmark Europe 5834.19 366674.81
## 6 Finland Europe 5530.72 278929.63
## 7 France Europe 67574.47 2775253.80
## 8 Germany Europe 83149.97 4012611.25
## 9 Iceland Europe 366.52 23923.12
## 10 Ireland Europe 4984.30 443119.01
## Average_GDP_per_capita... Average_HEXP... Development_level
## 1 59245.44 6186.68 High
## 2 50844.26 5778.39 High
## 3 47825.79 5277.94 High
## 4 47373.96 5963.91 High
## 5 62849.35 6627.81 High
## 6 50432.77 4894.77 High
## 7 41069.56 4880.27 High
## 8 48257.52 6016.41 High
## 9 65271.81 6077.78 High
## 10 88903.04 6108.42 High
## AMR_female.per_1000_female_adults. AMR_male.per_1000_male_adults.
## 1 42.02 74.11
## 2 40.95 75.49
## 3 47.33 80.24
## 4 51.68 88.18
## 5 43.94 71.35
## 6 42.81 88.87
## 7 46.95 92.35
## 8 46.39 84.31
## 9 43.93 65.15
## 10 42.45 69.46
## Average_CDR
## 1 6.57
## 2 10.00
## 3 10.07
## 4 7.83
## 5 9.50
## 6 10.07
## 7 9.57
## 8 11.83
## 9 6.30
## 10 6.47#short
adult_mort %>% filter(Development_level == "Short") %>% head(10)## Countries Continent Average_Pop.thousands.people. Average_GDP.M..
## 1 Afghanistan Asia 38947.06 17995.64
## 2 Albania Europe 2834.57 16263.16
## 3 Algeria Africa 43445.00 160325.54
## 4 Angola Africa 33428.62 72148.29
## 5 Argentina South America 45374.74 443212.28
## 6 Armenia Europe 2805.73 13374.14
## 7 Azerbaijan Europe 10085.05 48496.47
## 8 Bangladesh Asia 167431.14 379314.11
## 9 Belize North America 394.68 2329.33
## 10 Benin Africa 12643.49 15921.69
## Average_GDP_per_capita... Average_HEXP... Development_level
## 1 462.05 80.53 Short
## 2 5737.44 420.17 Short
## 3 3690.31 215.53 Short
## 4 2158.28 61.29 Short
## 5 9767.82 985.36 Short
## 6 4766.73 573.12 Short
## 7 4808.75 232.16 Short
## 8 2265.49 52.09 Short
## 9 5901.78 297.75 Short
## 10 1259.28 31.72 Short
## AMR_female.per_1000_female_adults. AMR_male.per_1000_male_adults.
## 1 204.85 322.17
## 2 53.54 103.55
## 3 70.85 102.21
## 4 218.03 316.81
## 5 82.87 143.85
## 6 76.26 228.57
## 7 120.13 250.51
## 8 110.96 157.49
## 9 129.34 237.22
## 10 245.11 291.39
## Average_CDR
## 1 7.08
## 2 10.20
## 3 4.78
## 4 7.88
## 5 8.35
## 6 11.82
## 7 6.90
## 8 5.59
## 9 5.44
## 10 9.35I want to look at countries with lowest and highest Crude Death Rate
#high
high <- adult_mort%>%
arrange(desc(Average_CDR))
high %>% head(7)## Countries Continent Average_Pop.thousands.people. Average_GDP.M..
## 1 Bulgaria Europe 6929.17 74410.97
## 2 Serbia Europe 6892.90 55984.25
## 3 Latvia Europe 1899.59 36224.07
## 4 Romania Europe 19252.99 262556.24
## 5 Lithuania Europe 2796.62 59322.36
## 6 Hungary Europe 9743.73 167840.99
## 7 Croatia Europe 3997.31 62942.80
## Average_GDP_per_capita... Average_HEXP... Development_level
## 1 10738.80 864.87 Average
## 2 8122.02 743.51 Short
## 3 19069.45 1464.81 Average
## 4 13637.17 837.06 Average
## 5 21212.16 1582.99 Average
## 6 17225.54 1202.91 Average
## 7 15746.29 1172.91 Average
## AMR_female.per_1000_female_adults. AMR_male.per_1000_male_adults. Average_CDR
## 1 98.42 207.52 18.40
## 2 63.14 135.85 17.17
## 3 84.50 210.61 16.03
## 4 63.76 164.76 15.47
## 5 77.92 212.30 15.43
## 6 76.77 161.84 14.63
## 7 43.71 105.00 14.33#low
low<- adult_mort %>% arrange(Average_CDR)
low%>% head(7)## Countries Continent Average_Pop.thousands.people. Average_GDP.M..
## 1 Qatar Asia 2751.95 166819.87
## 2 United Arab Emirates Asia 9288.03 394161.48
## 3 Bahrain Asia 1478.31 37526.60
## 4 Kuwait Asia 4350.55 126312.26
## 5 Saudi Arabia Asia 35924.96 813807.64
## 6 Maldives Asia 513.47 4916.58
## 7 Oman Asia 4555.55 83407.89
## Average_GDP_per_capita... Average_HEXP... Development_level
## 1 60618.75 1981.36 High
## 2 42437.57 2185.53 High
## 3 25384.84 1092.18 Average
## 4 29033.61 1805.22 Average
## 5 22652.99 1359.14 Average
## 6 9575.25 1000.92 Short
## 7 18309.09 825.07 Average
## AMR_female.per_1000_female_adults. AMR_male.per_1000_male_adults. Average_CDR
## 1 42.63 52.76 1.17
## 2 46.87 69.84 1.70
## 3 50.73 59.78 2.24
## 4 36.55 69.58 2.78
## 5 83.51 103.07 2.81
## 6 40.94 55.55 2.96
## 7 72.89 105.23 3.01Now I will make bar graphs on three countries from Lowest and Highest CDR, to see what their CDR look like compared to each other
high <- high %>% slice_head(n = 3)
ggplot(high, aes(x = Countries, y = Average_CDR, fill = Countries)) +
geom_col() +
xlab("Country") +
ylab("Average CDR") +
ggtitle("Comparison of CDR for countries with the highest death rate (2019-2021") +
scale_fill_brewer(palette = "Pastel2") +
theme_minimal() 
low <- low %>% slice_head(n = 3)
ggplot(low, aes(x = Countries, y = Average_CDR, fill = Countries)) +
geom_col() +
xlab("Country") +
ylab("Average CDR") +
ggtitle("Comparison of CDR for countries with the lowest death rate (2019-2021") +
scale_fill_brewer(palette = "Pastel2") +
theme_minimal() 
From these plot we can see that though Bulgaria and Serbia close to each other when it comes to death rate but Bulgaria is still higher. While the difference for countries with lowest CDR is quite significant, Qatar is almost half of Bahrain.
For this project I will focus on Qatar and Bulgaria, to see if their GDP have any effect on the CDR. Also, I will be observing if there is a significant difference between death rate of Women vs. Men.
low <- low %>% slice_head(n = 3)
ggplot(low, aes(x = Countries, y = Average_GDP.M.., fill = Countries)) +
geom_col() +
xlab("Country") +
ylab("Average GDP") +
ggtitle("Comparison of GDP for countries with the lowest death rate (2019-2021") +
scale_fill_brewer(palette = "Pastel2") +
theme_minimal() 
This bar graph was intereseting to look at because though United Arab Emirates has GDP more than double of Qatar, it’s CDR is still higher than of Qatar. This might suggest that GDP has no effect on the death rate.
#Qatar vs. Bulgaria GDP
count<- adult_mort %>% filter (Countries == "Qatar" | Countries == "Bulgaria")
ggplot(count, aes(x = Countries, y = Average_GDP.M.., fill = Countries)) +
geom_col() +
xlab("Country") +
ylab("Average GDP") +
ggtitle("Comparison of GDP(2019-2021)") +
scale_fill_brewer(palette = "Pastel2") 
This graph shows that Qatar has slightly more than double of Bulgaria’s GDP
bul_data <- read.csv("bulg_gdp_death.csv")
ggplot(bul_data) +
geom_line(aes(x= Year, y= GDP_currentUS, color= "GDP(in Billion US$)"), size=0.78)+
geom_line(aes(x= Year, y= Death_rate_crude, color= "Crude death rate %"), size= 0.78)+
geom_point(aes(x= Year, y= GDP_currentUS, color= "GDP(in Billion US$)"))+
geom_point(aes(x= Year, y= Death_rate_crude, color= "Crude death rate %"), shape=20)+
#xlim(2018, 2022)+
labs(y="Values", x= "Year",
title= "Bulgaria: CDR vs. GDP (1980-2021)",
color = "Indicators") +
scale_color_manual(labels = c( "Crude Death Rate(%)", "GDP(in Billion US$)"),
values = c("blue","seagreen"))## Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
## ℹ Please use `linewidth` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.## Warning: Removed 1 row containing missing values or values outside the scale range
## (`geom_line()`).## Warning: Removed 1 row containing missing values or values outside the scale range
## (`geom_point()`).
As seen by the plot, we can see that there is a dis proportionality between GDP and CDR. Though, it’s important to note that the two variables are in different scales. We can still observe that while CDR remained constant from 1980 - 2021, GDP for Bulgaria was increasing significantly. Also, in 2021 both GDP and CDR increased, meaning that GDP and death rate have direct relationship. Which is not what I have hypothesized.
rates <- data.frame(
Country = rep(c("Bulgaria", "Qatar"), each = 2),
Gender = c("Female", "Male", "Female", "Male"),
Mortality_Rate = c(98.4, 207.5, 42.6, 52.8) )
ggplot(rates, aes(x = Gender, y = Mortality_Rate, fill = Gender)) +
geom_col() +
facet_wrap(~ Country) +
xlab("Gender") +
ylab("Mortality Rate") +
ggtitle("Female vs Male Average Adult Mortality Rate(per 1000) for Bulgaria and Qatar (2019-2021)") +
theme_minimal() +
scale_fill_manual(values = c("Female" = "lightpink", "Male" = "lightblue"))
This graph was surprising, because I expected to female mortality to be higher due to factors such as femicide, gender inequality and the unequality when it comes to medical access and health. However, for both countries adult males have higher death rate compared to female. Bulgaria’s male death rate is significantly higher of approximately 208 men per 1000.
ggplot(count, aes(x = Countries, y = Average_HEXP..., fill = Countries)) +
geom_col() +
xlab("Country") +
ylab("Average HEXP") +
ggtitle("Comparison of Health Expenditure(2019-2021)") +
scale_fill_brewer(palette = "Set3")