R Training - numerical data

sum(Pop_2024$Total_population)

[1] 33244414

mean(Pop_2024$Life_expectancy_at_birth)

[1] 61.09091

mean(Pop_2024$Global_fertility_rate)

[1] 4.909091

Pop_2024 <- Pop_2024 %>%
  mutate(northern_region = Province %in% c("Niassa", "Cabo Delgado", "Nampula"))

Pop_2024 %>%
  group_by(northern_region) %>%
  summarise(mean(Life_expectancy_at_birth), median(Life_expectancy_at_birth))

ggplot(Pop_2024, aes(x = Life_expectancy_at_birth, fill = northern_region)) +
  geom_density(alpha = .3)

NA
NA

descr(Pop_2024$Life_expectancy_at_birth)

Descriptive Statistics  
Pop_2024$Life_expectancy_at_birth  
N: 11  

                    Life_expectancy_at_birth
----------------- --------------------------
             Mean                      61.09
          Std.Dev                       9.35
              Min                      53.50
               Q1                      54.80
           Median                      59.00
               Q3                      63.70
              Max                      87.00
              MAD                       6.23
              IQR                       7.00
               CV                       0.15
         Skewness                       1.80
      SE.Skewness                       0.66
         Kurtosis                       2.47
          N.Valid                      11.00
        Pct.Valid                     100.00

ggplot(Pop_2024, aes(x = Life_expectancy_at_birth, fill = northern_region)) +
  geom_density(alpha = .3)

NA
NA

Pop_2024 <- Pop_2024 %>%
  mutate(is_outlier = Life_expectancy_at_birth > 65)

Pop_2024 %>%
  filter(!is_outlier) %>%
  arrange(desc(Life_expectancy_at_birth))

Pop_2024 %>%
  filter(!is_outlier) %>%
  ggplot(aes(x = Life_expectancy_at_birth, fill = northern_region)) +
  geom_density(alpha = .3)

Pop_2024 %>%
   ggplot( aes(x=northern_region, y=Life_expectancy_at_birth, fill=northern_region)) + 
    geom_boxplot() +
    xlab("Province") +
    theme(legend.position="none") +
    xlab("") +
    xlab("")