R Trainining - Numerical data

sum(Pop_2024$Total_population)

[1] 66488828

mean(Pop_2024$Life_expectancy_at_birth)

[1] 58.075

mean(Pop_2024$Global_fertility_rate)

[1] 4.533333

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

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

summary(Pop_2024$Life_expectancy_at_birth)

   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
  53.50   55.25   57.60   58.08   60.15   63.90 

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

descr(Pop_2024$Life_expectancy_at_birth)

Descriptive Statistics  
Pop_2024$Life_expectancy_at_birth  
N: 12  

                    Life_expectancy_at_birth
----------------- --------------------------
             Mean                      58.08
          Std.Dev                       3.65
              Min                      53.50
               Q1                      55.10
           Median                      57.60
               Q3                      60.70
              Max                      63.90
              MAD                       3.71
              IQR                       4.90
               CV                       0.06
         Skewness                       0.31
      SE.Skewness                       0.64
         Kurtosis                      -1.41
          N.Valid                      12.00
        Pct.Valid                     100.00

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("")