Project 2: Inflation

Introduction: This data set includes global inflation data broken out by country. I aimed to analyze a few different aspects of this data:

1. How do continents compare to one another in terms of their countries’ aggregated inflation rates?
2. Within each continent, which countries are having the highest inflation rates? Lowest inflation rates?
3. What does the USA’s inflation rate trends look like over time? What does it look like globally? With these questions in mind, I began working with and manipulating the data to extract these insights.

Load Packages

library(tidyr)
library(dplyr)
library(ggplot2)
library(stringr)
library(ggrepel)

Inflation: Read Data Set number 2 and pivot the data

# Read inflation data from CSV file
df2 <- read.csv('/Users/williamberritt/Downloads/global_inflation_data.csv')

# Reshape the data from wide to long format using pivot_longer
pivot_df <- df2 |> pivot_longer(cols = (X1980:X2024),
                               names_to = 'year',
                               values_to ='value')

# Display the resulting reshaped data frame
head(pivot_df)

## # A tibble: 6 × 4
##   country_name indicator_name                                  year  value
##   <chr>        <chr>                                           <chr> <dbl>
## 1 Afghanistan  Annual average inflation (consumer prices) rate X1980  13.4
## 2 Afghanistan  Annual average inflation (consumer prices) rate X1981  22.2
## 3 Afghanistan  Annual average inflation (consumer prices) rate X1982  18.2
## 4 Afghanistan  Annual average inflation (consumer prices) rate X1983  15.9
## 5 Afghanistan  Annual average inflation (consumer prices) rate X1984  20.4
## 6 Afghanistan  Annual average inflation (consumer prices) rate X1985   8.7

Prep the table to be ready for analysis

# Remove 'X' and convert 'year' to numeric
pivot_df$year <- as.numeric(str_replace_all(pivot_df$year, 'X', ''))

# Rename columns
colnames(pivot_df) <- c('country', 'indicator', 'year', 'value')

Group countries together for analysis

# Create data frame that has continental data on each of the countries
asian_countries <- c(
  "Afghanistan", "Armenia", "Azerbaijan", "Bahrain", "Bangladesh", "Bhutan",
  "British Indian Ocean Territory", "Brunei", "Cambodia", "China", "Cyprus",
  "Egypt", "Georgia", "Hong Kong", "India", "Indonesia", "Iran", "Iraq",
  "Israel", "Japan", "Jordan", "Kazakhstan", "Kuwait", "Kyrgyzstan", "Laos",
  "Lebanon", "Macau", "Malaysia", "Maldives", "Mongolia", "Myanmar", "Nepal",
  "North Korea", "Oman", "Pakistan", "Palestine", "Philippines", "Qatar",
  "Russia", "Saudi Arabia", "Singapore", "South Korea", "Sri Lanka", "Syria",
  "Taiwan", "Tajikistan", "Thailand", "Timor-Leste", "Turkey", "Turkmenistan",
  "United Arab Emirates", "Uzbekistan", "Vietnam", "Yemen"
)
asian_countries_df <- data.frame(
  country = asian_countries,
  continent = rep("Asia", length(asian_countries))
)
african_countries <- c(
  "Algeria", "Angola", "Benin", "Botswana", "Burkina Faso", "Burundi",
  "Cabo Verde", "Cameroon", "Central African Republic", "Chad", "Comoros",
  "Congo", "Democratic Republic of the Congo", "Djibouti", "Egypt",
  "Equatorial Guinea", "Eritrea", "Eswatini", "Ethiopia", "Gabon",
  "Gambia, The", "Ghana", "Guinea", "Guinea-Bissau", "Ivory Coast",
  "Kenya", "Lesotho", "Liberia", "Libya", "Madagascar", "Malawi", "Mali",
  "Mauritania", "Mauritius", "Morocco", "Mozambique", "Namibia", "Niger",
  "Nigeria", "Rwanda", "Sao Tome and Principe", "Senegal", "Seychelles",
  "Sierra Leone", "Somalia", "South Africa", "South Sudan", "Sudan",
  "Tanzania", "Togo", "Tunisia", "Uganda", "Zambia", "Zimbabwe"
)
african_countries_df <- data.frame(
  country = african_countries,
  continent = rep("Africa", length(african_countries))
)
european_countries <- c(
  "Albania", "Andorra", "Armenia", "Austria", "Azerbaijan", "Belarus",
  "Belgium", "Bosnia and Herzegovina", "Bulgaria", "Croatia", "Cyprus",
  "Czechia", "Denmark", "Estonia", "Finland", "France", "Georgia", "Germany",
  "Greece", "Hungary", "Iceland", "Ireland", "Italy", "Kazakhstan", "Latvia",
  "Liechtenstein", "Lithuania", "Luxembourg", "Malta", "Moldova", "Monaco",
  "Montenegro", "Netherlands", "North Macedonia", "Norway", "Poland",
  "Portugal", "Romania", "Russia", "San Marino", "Serbia", "Slovakia",
  "Slovenia", "Spain", "Sweden", "Switzerland", "Turkey", "Ukraine",
  "United Kingdom", "Vatican City"
)
european_countries_df <- data.frame(
  country = european_countries,
  continent = rep("Europe", length(european_countries))
)
north_american_countries <- c(
  "Canada",
  "United States"
)
north_american_countries_df <- data.frame(
  country = north_american_countries,
  continent = rep("North America", length(north_american_countries))
)
central <- c(
  "Costa Rica", "Cuba", "Dominica", "Dominican Republic", "El Salvador",
  "Grenada", "Guatemala", "Haiti", "Honduras", "Jamaica", "Mexico",
  "Nicaragua", "Panama", "Saint Kitts and Nevis", "Saint Lucia",
  "Saint Vincent and the Grenadines", "Trinidad and Tobago", 
  "Antigua and Barbuda", "Bahamas", "Barbados", "Belize"
)
central_df <- data.frame(
  country = central,
  continent = rep("Carribean_Central", length(central))
)
oceania_countries <- c(
  "Australia", "Fiji", "Kiribati", "Marshall Islands",
  "Micronesia", "Nauru", "New Zealand",
  "Palau", "Papua New Guinea", "Samoa", "Solomon Islands", "Tonga",
  "Tuvalu", "Vanuatu"
)
oceania_countries_df <- data.frame(
  country = oceania_countries,
  continent = rep("Oceania", length(oceania_countries))
)
south_american_countries <- c(
  "Argentina", "Bolivia", "Brazil", "Chile", "Colombia", "Ecuador",
  "Guyana", "Paraguay", "Peru", "Suriname", "Uruguay", "Venezuela"
)
south_american_countries_df <- data.frame(
  country = south_american_countries,
  continent = rep("South America", length(south_american_countries))
)
combined_df <- rbind(african_countries_df, asian_countries_df, european_countries_df, north_american_countries_df, oceania_countries_df, south_american_countries_df,central_df)

Look at median and mean inflation rates by grouping of countries

# Merge country-continent data with inflation data
country_continent <- left_join(combined_df, pivot_df, by='country')

## Warning in left_join(combined_df, pivot_df, by = "country"): Detected an unexpected many-to-many relationship between `x` and `y`.
## ℹ Row 1 of `x` matches multiple rows in `y`.
## ℹ Row 2296 of `y` matches multiple rows in `x`.
## ℹ If a many-to-many relationship is expected, set `relationship =
##   "many-to-many"` to silence this warning.

country_continent <- na.omit(country_continent)

# Calculate mean inflation by continent and year
mean_by_continent_by_year <- country_continent |> group_by(continent, year) |> 
  summarize(mean_inflation = mean(value)) |> 
  group_by(continent) |> 
  summarize(mean_continental_inflation = mean(mean_inflation))

# Calculate median inflation by continent and year
median_by_continent_by_year <- country_continent |> group_by(continent, year) |> 
  summarize(median_inflation = median(value)) |> 
  group_by(continent) |> 
  summarize(median_continental_inflation = median(median_inflation))

# Merge median and mean inflation data by continent
median_mean_inf_continent <- left_join(median_by_continent_by_year, mean_by_continent_by_year, by='continent')

# Display the results, ordered by median continental inflation
median_mean_inf_continent[order(median_mean_inf_continent$median_continental_inflation),]

## # A tibble: 7 × 3
##   continent         median_continental_inflation mean_continental_inflation
##   <chr>                                    <dbl>                      <dbl>
## 1 North America                             2.55                       3.25
## 2 Europe                                    3.3                       29.7 
## 3 Oceania                                   3.6                        5.21
## 4 Carribean_Central                         4.7                       42.7 
## 5 Africa                                    6.1                       17.4 
## 6 Asia                                      6.2                       30.3 
## 7 South America                             7.35                     261.

Look at the inflation leaderboard for each continent

# View each continents' inflation leaderboard
african_mean <- subset(country_continent, continent == 'Africa') |> group_by(country) |> summarize(mean_value=mean(value))
african_median <- subset(country_continent, continent == 'Africa') |> group_by(country) |> summarize(median_value=median(value))
african_mean_median <- left_join(african_median, african_mean, by='country')
african_mean_median[order(african_mean_median$median_value),]

## # A tibble: 49 × 3
##    country      median_value mean_value
##    <chr>               <dbl>      <dbl>
##  1 Zimbabwe              1.1      39.8 
##  2 Niger                 1.6       3.30
##  3 Senegal               1.7       3.74
##  4 Togo                  1.8       3.93
##  5 Benin                 2.1       3.52
##  6 Gabon                 2.1       3.48
##  7 Burkina Faso          2.3       3.5 
##  8 Mali                  2.4       3.54
##  9 Seychelles            2.4       4.24
## 10 Djibouti              2.5       2.96
## # ℹ 39 more rows

american_mean <- subset(country_continent, continent == 'North America') |> group_by(country) |> summarize(mean_value=mean(value))
american_median <- subset(country_continent, continent == 'North America') |> group_by(country) |> summarize(median_value=median(value))
american_mean_median <- left_join(american_median, american_mean, by='country')
american_mean_median[order(american_mean_median$median_value),]

## # A tibble: 2 × 3
##   country       median_value mean_value
##   <chr>                <dbl>      <dbl>
## 1 Canada                 2.3       3.17
## 2 United States          2.9       3.33

european_mean <- subset(country_continent, continent == 'Europe') |> group_by(country) |> summarize(mean_value=mean(value))
european_median <- subset(country_continent, continent == 'Europe') |> group_by(country) |> summarize(median_value=median(value))
european_mean_median <- left_join(european_median, european_mean, by='country')
european_mean_median[order(european_mean_median$median_value),]

## # A tibble: 42 × 3
##    country                median_value mean_value
##    <chr>                         <dbl>      <dbl>
##  1 Switzerland                    0.9        1.62
##  2 Bosnia and Herzegovina         1.75       2.26
##  3 Germany                        1.9        2.36
##  4 San Marino                     1.9        2.03
##  5 Sweden                         2          3.80
##  6 Netherlands                    2.05       2.37
##  7 Austria                        2.1        2.69
##  8 Denmark                        2.1        3.01
##  9 Finland                        2.1        3.22
## 10 France                         2.1        3.14
## # ℹ 32 more rows

oceania_mean <- subset(country_continent, continent == 'Oceania') |> group_by(country) |> summarize(mean_value=mean(value))
oceania_median <- subset(country_continent, continent == 'Oceania') |> group_by(country) |> summarize(median_value=median(value))
oceania_mean_median <- left_join(oceania_median, oceania_mean, by='country')
oceania_mean_median[order(oceania_mean_median$median_value),]

## # A tibble: 13 × 3
##    country          median_value mean_value
##    <chr>                   <dbl>      <dbl>
##  1 Marshall Islands          2         2.52
##  2 Palau                     2.5       3.20
##  3 New Zealand               2.6       4.51
##  4 Australia                 2.9       4.05
##  5 Tuvalu                    3         3.37
##  6 Vanuatu                   3         4.45
##  7 Kiribati                  3.2       3.09
##  8 Fiji                      3.7       4.25
##  9 Nauru                     4.5       4.14
## 10 Samoa                     5         6.27
## 11 Papua New Guinea          5.3       6.72
## 12 Tonga                     5.6       6.13
## 13 Solomon Islands           8         8.09

south_american_mean <- subset(country_continent, continent == 'South America') |> group_by(country) |> summarize(mean_value=mean(value))
south_american_median <- subset(country_continent, continent == 'South America') |> group_by(country) |> summarize(median_value=median(value))
south_american_mean_median <- left_join(south_american_median, south_american_mean, by='country')
south_american_mean_median[order(south_american_mean_median$median_value),]

## # A tibble: 12 × 3
##    country   median_value mean_value
##    <chr>            <dbl>      <dbl>
##  1 Peru               4       288.  
##  2 Chile              4.7       9.46
##  3 Bolivia            5.7     312.  
##  4 Guyana             6.5      14   
##  5 Brazil             8.3     264.  
##  6 Paraguay           9        11.5 
##  7 Colombia           9.2      13.1 
##  8 Uruguay            9.6      28.2 
##  9 Argentina         10.6      25.8 
## 10 Ecuador           12.5      20.9 
## 11 Suriname          14        22.9 
## 12 Venezuela         31.4    2042.

asian_mean <- subset(country_continent, continent == 'Asia') |> group_by(country) |> summarize(mean_value=mean(value))
asian_median <- subset(country_continent, continent == 'Asia') |> group_by(country) |> summarize(median_value=median(value))
asian_mean_median <- left_join(asian_median, asian_mean, by='country')
african_mean_median[order(asian_mean_median$median_value),]

## # A tibble: 41 × 3
##    country           median_value mean_value
##    <chr>                    <dbl>      <dbl>
##  1 Eswatini                   7.5       8.96
##  2 Libya                      4         5.98
##  3 Mauritania                 4.7       5.34
##  4 Botswana                   8.5       8.51
##  5 Mauritius                  6         7.06
##  6 Equatorial Guinea          4.5       8.93
##  7 Cameroon                   2.7       4.41
##  8 Guinea                    11.9      16.8 
##  9 Mali                       2.4       3.54
## 10 Niger                      1.6       3.30
## # ℹ 31 more rows

central_mean <- subset(country_continent, continent == 'Carribean_Central') |> group_by(country) |> summarize(mean_value=mean(value))
central_median <- subset(country_continent, continent == 'Carribean_Central') |> group_by(country) |> summarize(median_value=median(value))
central_mean_median <- left_join(central_median, central_mean, by='country')
central_mean_median[order(central_mean_median$median_value),]

## # A tibble: 19 × 3
##    country                          median_value mean_value
##    <chr>                                   <dbl>      <dbl>
##  1 Panama                                    1.3       2.16
##  2 Dominica                                  1.7       3.03
##  3 Belize                                    2         2.49
##  4 Saint Kitts and Nevis                     2.2       2.90
##  5 Antigua and Barbuda                       2.4       3.23
##  6 Saint Vincent and the Grenadines          2.4       3.23
##  7 Grenada                                   2.5       3.28
##  8 Saint Lucia                               2.7       3.20
##  9 Barbados                                  3.6       3.16
## 10 El Salvador                               4.5       8.00
## 11 Trinidad and Tobago                       5.7       6.82
## 12 Mexico                                    6.4      22.5 
## 13 Guatemala                                 6.7       9.10
## 14 Dominican Republic                        7.5      12.5 
## 15 Honduras                                  7.7       9.52
## 16 Jamaica                                   9.4      14.6 
## 17 Nicaragua                                 9.6     676.  
## 18 Costa Rica                               11.3      13.0 
## 19 Haiti                                    11.4      13.1

Observe USA’s inflation history, then look at global to see how they may trend together

# Subset data for the United States with value less than 10
usa <- subset(pivot_df, country == 'United States' & value < 10)

# Plot inflation data for the United States
plot(usa$year, usa$value, type = 'l')

# Create a copy of the original data frame
global_df <- pivot_df

# Remove rows with missing data
global_df <- na.omit(global_df)

# Calculate global median inflation by year
global_inf <- global_df |> group_by(year) |> 
  summarize(median_inflation_by_year = median(value))

# Plot the global median inflation over the years
plot(global_inf$year, global_inf$median_inflation_by_year, type = 'l')

Conclusion:

1. In regard to question one, North America (although only consisting of Canada and USA by my definition) has experienced the lowest mean and median inflation rate since 1980. In some cases we see extreme differences between the mean and median like in South America. This is an indication of outliers skewing the data.
2. As expected, we see that there are countries with relatively low median values but have mean values over 500%! Nicaragua and Venezuela have some of the highest mean inflation rates in recent history.
3. It’s not easy to make out any macro trends on the USA inflation rate plot. There are peaks and dips and there seems to be some cyclicality but much less than compared to the global data