Project 2
Veronica Chunikhin
11/16/2025
library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.1 ✔ stringr 1.5.2
## ✔ ggplot2 4.0.0 ✔ tibble 3.3.0
## ✔ lubridate 1.9.4 ✔ tidyr 1.3.1
## ✔ purrr 1.1.0
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errorsGDP_data <- read.csv("C:/Users/nika/Downloads/R/csv/GDP_data.csv", skip = 4)Introduction
Did the 2008 financial crisis and COVID-19 pandemic affect GDP growth rates differently across continents? The data set used in this project was taken from the World Bank Open Data: GDP Growth https://data.worldbank.org/indicator/NY.GDP.MKTP.KD.ZG. The data set shows the GDP values per year per country, looking at rate changes from 1961 to the present (2025). The data set holds a variety of different variable and is formulated to show the years as columns with rate changes as dependent variables. The main variables that will be used throughout this study are: GDP Growth Rate, Continent, Crisis Period, Country, and Year.
Data Analysis
To answer the research question, I will create two graphs, a line plot comparing the GDP of continents over the years as well as box plots of the two financial crises for each continent. The line graph would give us a general overview of the trend between each continent and allow us to identify if any of the continents experienced outlines. The box plot on the other hand, will allow us to compare the medium growth rate change between continents during the crisis and establish possible patterns in the data.
colnames(GDP_data)## [1] "Country.Name" "Country.Code" "Indicator.Name" "Indicator.Code"
## [5] "X1960" "X1961" "X1962" "X1963"
## [9] "X1964" "X1965" "X1966" "X1967"
## [13] "X1968" "X1969" "X1970" "X1971"
## [17] "X1972" "X1973" "X1974" "X1975"
## [21] "X1976" "X1977" "X1978" "X1979"
## [25] "X1980" "X1981" "X1982" "X1983"
## [29] "X1984" "X1985" "X1986" "X1987"
## [33] "X1988" "X1989" "X1990" "X1991"
## [37] "X1992" "X1993" "X1994" "X1995"
## [41] "X1996" "X1997" "X1998" "X1999"
## [45] "X2000" "X2001" "X2002" "X2003"
## [49] "X2004" "X2005" "X2006" "X2007"
## [53] "X2008" "X2009" "X2010" "X2011"
## [57] "X2012" "X2013" "X2014" "X2015"
## [61] "X2016" "X2017" "X2018" "X2019"
## [65] "X2020" "X2021" "X2022" "X2023"
## [69] "X2024" "X"head(GDP_data)## Country.Name Country.Code Indicator.Name
## 1 Aruba ABW GDP growth (annual %)
## 2 Africa Eastern and Southern AFE GDP growth (annual %)
## 3 Afghanistan AFG GDP growth (annual %)
## 4 Africa Western and Central AFW GDP growth (annual %)
## 5 Angola AGO GDP growth (annual %)
## 6 Albania ALB GDP growth (annual %)
## Indicator.Code X1960 X1961 X1962 X1963 X1964 X1965
## 1 NY.GDP.MKTP.KD.ZG NA NA NA NA NA NA
## 2 NY.GDP.MKTP.KD.ZG NA 0.4697078 7.868623 5.622472 4.689533 5.159536
## 3 NY.GDP.MKTP.KD.ZG NA NA NA NA NA NA
## 4 NY.GDP.MKTP.KD.ZG NA 1.8696369 3.725941 7.039191 5.364761 4.105616
## 5 NY.GDP.MKTP.KD.ZG NA NA NA NA NA NA
## 6 NY.GDP.MKTP.KD.ZG NA NA NA NA NA NA
## X1966 X1967 X1968 X1969 X1970 X1971 X1972 X1973
## 1 NA NA NA NA NA NA NA NA
## 2 4.822258 5.373938 4.153383 5.091807 1.135154 5.479342 2.771158 4.606450
## 3 NA NA NA NA NA NA NA NA
## 4 -1.512989 -8.967443 1.558993 15.127190 17.382531 10.453272 3.153188 3.952264
## 5 NA NA NA NA NA NA NA NA
## 6 NA NA NA NA NA NA NA NA
## X1974 X1975 X1976 X1977 X1978 X1979 X1980 X1981
## 1 NA NA NA NA NA NA NA NA
## 2 5.475813 1.404329 2.382201 1.120648 1.508609 2.930523 5.464293 4.014091
## 3 NA NA NA NA NA NA NA NA
## 4 9.975607 -2.077795 8.394825 4.551447 -1.917931 5.001670 1.905791 -6.701354
## 5 NA NA NA NA NA NA NA -4.400001
## 6 NA NA NA NA NA NA NA 5.745635
## X1982 X1983 X1984 X1985 X1986 X1987 X1988
## 1 NA NA NA NA NA 16.0784314 18.648649
## 2 0.3151527 0.03932852 3.3652804 -0.1280365 2.266005 3.9545238 4.274110
## 3 NA NA NA NA NA NA NA
## 4 -3.2229169 -6.25245904 0.5418582 5.3946427 1.337552 1.4297519 4.679828
## 5 0.0000000 4.20000143 6.0000022 3.4999995 2.900002 4.0827486 6.128890
## 6 2.9485968 1.10493826 -1.2515966 1.7806440 5.637243 -0.7878427 -1.420040
## X1989 X1990 X1991 X1992 X1993 X1994
## 1 12.12984055 3.9614017 7.96287173 5.882354 7.3076932 8.2039013
## 2 2.69634244 0.1758673 -0.09546367 -2.350160 -0.5994377 1.9320314
## 3 NA NA NA NA NA NA
## 4 1.72672657 5.6968803 1.06723219 2.350220 -1.3626449 -0.2831964
## 5 0.04162146 -3.4500987 0.99135930 -5.838281 -23.9834174 1.3393634
## 6 9.83654897 -9.5756402 -28.00214165 -7.187111 9.5594117 8.3028666
## X1995 X1996 X1997 X1998 X1999 X2000 X2001
## 1 2.547144 1.185789 7.046875 1.991984 1.238042 7.622921 4.182002
## 2 4.282648 5.454335 3.841977 1.752629 2.649285 3.212167 3.505488
## 3 NA NA NA NA NA NA -9.431974
## 4 1.859801 4.629126 4.403075 3.623420 1.528189 3.842479 5.207033
## 5 15.000000 13.544370 7.274277 4.691146 2.181490 3.054624 4.205999
## 6 13.322333 7.336329 -11.711573 8.310025 12.250728 7.462859 8.863731
## X2002 X2003 X2004 X2005 X2006 X2007 X2008
## 1 -0.9449535 1.110505 7.293728 -0.3831377 1.127411 3.089544 1.835755
## 2 3.8338481 2.952939 5.554448 6.1624933 6.577439 6.646935 4.366173
## 3 28.6000012 8.832278 1.414118 11.2297148 5.357403 13.826320 3.924984
## 4 9.9688021 5.597677 8.094673 5.9121109 5.355184 5.502329 6.276135
## 5 13.6656888 2.990000 10.950000 15.0300000 11.550000 14.010000 11.170000
## 6 4.6283959 5.333264 5.266262 5.1308219 6.018981 6.500093 6.907062
## X2009 X2010 X2011 X2012 X2013 X2014 X2015
## 1 -11.6777414 -2.733457 3.3692372 -1.0407999 6.431483 -1.586575 -0.6236259
## 2 0.8926514 5.207943 4.0589233 1.7679695 4.317725 4.014351 3.0033669
## 3 21.3905284 14.362441 0.4263548 12.7522871 5.600745 2.724543 1.4513147
## 4 6.1255292 7.032025 4.9466662 5.1405756 6.028023 5.712459 2.9280096
## 5 0.8600000 4.398376 3.4720531 8.5421071 4.954613 4.822559 0.9435716
## 6 2.6907515 2.973154 2.4635168 0.9841299 1.707228 2.240227 2.2277041
## X2016 X2017 X2018 X2019 X2020 X2021 X2022
## 1 1.7196250 7.0485334 2.397086 -2.232442 -26.2118202 24.132627 8.517918
## 2 2.1959912 2.6962378 2.665038 2.200340 -2.8597839 4.563568 3.555769
## 3 2.2603142 2.6470032 1.189228 3.911603 -2.3511007 -20.738839 -6.240172
## 4 0.1941775 2.2961675 2.904654 3.282163 -0.9841174 4.030000 3.974964
## 5 -2.5800496 -0.1472129 -1.316362 -0.702273 -5.6382147 1.199211 3.044727
## 6 3.9089355 3.2831759 3.671419 2.062578 -3.3137564 8.969576 4.826696
## X2023 X2024 X
## 1 4.263719 NA NA
## 2 1.891307 2.766804 NA
## 3 2.266944 NA NA
## 4 3.357987 4.176103 NA
## 5 1.078100 4.423905 NA
## 6 3.936617 3.961719 NAGDP_data_clean <- GDP_data |>
pivot_longer(cols = starts_with("X"), names_to = "Year", values_to = "growth_rate") |>
mutate(Year = as.numeric(substring(Year, 2))) |>
filter(!is.na(growth_rate)) |>
filter(Year >= 2006 & Year <= 2024) |>
select('Country.Name', Year, growth_rate) |>
mutate(Covid = Year %in% c(2020, 2021), Financial_Crisis = Year %in% c(2008, 2009)) |>
mutate(Continent = case_when(
`Country.Name` %in% c("Argentina", "Bolivarian Republic of Venezuela", "Brazil", "Chile", "Colombia", "Ecuador", "Guyana", "Paraguay", "Plurinational State of Bolivia", "Peru", "Suriname", "Uruguay", "Aruba", "Bolivia", "Curacao", "Latin America & Caribbean") ~ "South America",
`Country.Name` %in% c("Antigua and Barbuda", "Bahamas", "Barbados", "Belize", "Canada", "Costa Rica", "Cuba", "Dominica", "Dominican Republic", "El Salvador", "Grenada", "Guatemal", "Haiti", "Honduras", "Jamaica", "Mexico", "Nicaragua", "Panama", "Saint Kitts and Nevis", "Saint Lucia", "Saint Vincent and the Grenadines", "Trinidad and Tobago", "United States", "Bahamas, The", "Bermuda", "Caribbean small states", "Cayman Islands", "Greenland", "St. Kitts and Nevis", "St. Lucia", "St. Martin", "North America", "Puerto Rico (US)", "Sint Maarten (Dutch part)", "Turks and Caicos Islands", "St. Vincent and the Grenadines", "Virgin Islands (U.S.)") ~ "North America",
`Country.Name` %in% c("Albania", "Andorra", "Armenia", "Austria", "Azerbaijan", "Belarus", "Belgium", "Bosnia and Herzegovina", "Bulgaria", "Croatia", "Czechia", "Denmark", "Estonia", "Finland", "France", "Georgia", "Germany", "Greece", "Hungary", "Iceland", "Ireland", "Italy", "Netherlands", "Latvia", "Liechtenstein", "Lithuania", "Luxembourg", "Malta", "Monaco", "Montenegro", "North Macedonia", "Norway", "Poland", "Portugal", "Republic of Moldova", "Romania", "Russian Federation", "San Marino", "Serbia", "Slovakia", "Slovenia", "Spain", "Sweden", "Switzerland", "Türkiye", "Ukraine", "United Kingdom", "Central Europe and the Baltics", "Channel Islands", "Europe & Central Asia", "Euro area", "European Union", "Faroe Islands", "Isle of Man", "Moldova", "Slovak Republic", "Kosovo") ~ "Europe",
`Country.Name` %in% c("Afghanistan", "Bahrain", "Bangladesh", "Bhutan", "Brunei Darussalam", "Cambodia", "China", "Cyprus", "North Korea", "India", "Indonesia", "Iraq", "Islamic Republic of Iran", "Israel", "Japan", "Jordan", "Kazakhstan", "Kuwait", "Kyrgyzstan", "Lao People's Democratic Republic", "Lebanon", "Malaysia", "Maldives", "Mongolia", "Myanmar", "Nepal", "Oman", "Pakistan", "Philippines", "Qatar", "Korea", "Saudi Arabia", "Singapore", "Sri Lanka", "Syrian Arab Republic", "Tajikistan", "Thailand", "Timor-Leste", "Turkmenistan", "United Arab Emirates", "Uzbekistan", "Viet Nam", "Yemen", "East Asia & Pacific", "Hong Kong SAR, China", "Iran, Islamic Rep.", "Kyrgyz Republic", "Korea, Rep.", "Macao SAR, China", "Middle East, North Africa, Afghanistan & Pakistan", "West Bank and Gaza", "South Asia", "Turkiye", "Yemen, Rep.") ~ "Asia",
`Country.Name` %in% c("Algeria", "Angola", "Benin", "Botswana", "Burkina Faso", "Burundi", "Cabo Verde", "Cameroon", "Central African Republic", "Chad", "Comoros", "Congo", "Côte d'Ivoire", "Democratic Republic of the Congo", "Djibouti", "Egypt", "Equatorial Guinea", "Eritrea", "Eswatini", "Ethiopia", "Gabon", "Gambia", "Ghana", "Guinea", "Guinea Bissau", "Kenya", "Lesotho", "Liberia", "Libya", "Madagascar", "Malawi", "Mali", "Mauritania", "Mauritius", "Morocco", "Mozambique", "Namibia", "Niger", "Nigeria", "Rwanda", "São Tomé and PrÃncipe", "Senegal", "Seychelles", "Sierra Leone", "Somalia", "South Africa", "South Sudan", "Sudan", "Togo", "Tunisia", "Uganda", "United Republic of Tanzania", "Zambia", "Zimbabwe", "Africa Eastern and Southern", "Africa Western and Central", "Arab World", "Cote d'Ivoire", "Congo, Dem. Rep.", "Egypt, Arab Rep.", "Gambia, The", "Guinea-Bissau", "Somalia, Fed. Rep.", "Sub-Saharan Africa", "Sao Tome and Principe", "Tanzania") ~ "Africa",
`Country.Name` %in% c("Australia", "Federated States of Micronesia", "Fiji", "Kiribati", "Marshall Islands", "Nauru", "New Zealand", "Palau", "Papua New Guinea", "Samoa", "Solomon Islands", "Tonga", "Tuvalu", "Vanuatu", "American Samoa", "Micronesia, Fed. Sts.", "Guam", "Northern Mariana Islands", "New Caledonia", "Pacific island small states", "French Polynesia") ~ "Oceania",
TRUE ~ NA_character_
)) |>
mutate(crisis_type = case_when(Financial_Crisis == TRUE ~ "Financial Crisis", Covid == TRUE ~ "COVID-19"))
summary(GDP_data_clean)## Country.Name Year growth_rate Covid
## Length:4842 Min. :2006 Min. :-54.336 Mode :logical
## Class :character 1st Qu.:2010 1st Qu.: 1.307 FALSE:4328
## Mode :character Median :2015 Median : 3.424 TRUE :514
## Mean :2015 Mean : 3.180
## 3rd Qu.:2020 3rd Qu.: 5.604
## Max. :2024 Max. : 91.137
## Financial_Crisis Continent crisis_type
## Mode :logical Length:4842 Length:4842
## FALSE:4331 Class :character Class :character
## TRUE :511 Mode :character Mode :character
##
##
## GDP_data_clean |>
group_by(Covid) |>
summarize(mean_growth = mean(growth_rate, na.rm = TRUE), median_growth = median(growth_rate, na.rm = TRUE), sd_growth = sd(growth_rate, na.rm = TRUE), min_growth = min(growth_rate, na.rm = TRUE), max_growth = max(growth_rate, na.rm = TRUE), count = n())## # A tibble: 2 × 7
## Covid mean_growth median_growth sd_growth min_growth max_growth count
## <lgl> <dbl> <dbl> <dbl> <dbl> <dbl> <int>
## 1 FALSE 3.50 3.52 5.06 -50.3 91.1 4328
## 2 TRUE 0.521 1.30 8.66 -54.3 43.5 514GDP_data_clean |>
group_by(Financial_Crisis) |>
summarize(mean_growth = mean(growth_rate, na.rm = TRUE), median_growth = median(growth_rate, na.rm = TRUE), sd_growth = sd(growth_rate, na.rm = TRUE))## # A tibble: 2 × 4
## Financial_Crisis mean_growth median_growth sd_growth
## <lgl> <dbl> <dbl> <dbl>
## 1 FALSE 3.33 3.50 5.64
## 2 TRUE 1.90 2.75 5.36GDP_data_clean |>
filter(!is.na(Continent)) |>
group_by(Continent, Year) |>
summarize(mean_growth = mean(growth_rate, na.rm = TRUE)) |>
ggplot(aes(x = Year, y = mean_growth, color = Continent)) +
geom_line(size = 1.2) +
geom_point(size = 2) +
geom_vline(xintercept = c(2008, 2020), linetype = "dashed", color = "gray50") +
labs(title = "Mean GDP Growth by Continent (2006-2024)",
x = "Year",
y = "Mean GDP Growth Rate (%)",
color = "Continent") +
theme_minimal() +
theme(legend.position = "bottom")## `summarise()` has grouped output by 'Continent'. You can override using the
## `.groups` argument.## 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.
GDP_data_clean |>
filter(!is.na(crisis_type), !is.na(Continent)) |>
ggplot(aes(x = Continent, y = growth_rate, fill = crisis_type)) +
geom_boxplot() +
labs(title = "GDP Growth Rate Distribution: Financial Crisis vs COVID-19 by Continent",
x = "Continent",
y = "GDP Growth Rate (%)",
fill = "Crisis Type") +
theme_minimal() +
theme(axis.text.x = element_text(angle = 45, hjust = 1))
Statistical Analysis
Hypothesis \(H_0\): \(\mu_1\) = \(\mu_2\) = \(\mu_3\) = \(\mu_4\) = \(\mu_5\) = \(\mu_6\) \(H_a\): not all \(\mu_i\) are equal
(\(\mu_1\) = mean GDP growth rate for Africa, \(\mu_2\) = mean GDP growth rate for Asia, \(\mu_3\) = mean GDP growth rate for Europe, \(\mu_4\) = mean GDP growth rate for North America, \(\mu_5\) = mean GDP growth rate for South America, \(\mu_6\) = mean GDP growth rate for Oceania)
GDP_crisis <- GDP_data_clean |>
filter(!is.na(crisis_type), !is.na(Continent))
anova_result <- aov(growth_rate ~ Continent * crisis_type, data = GDP_crisis)
summary(anova_result)## Df Sum Sq Mean Sq F value Pr(>F)
## Continent 5 1909 381.7 7.015 1.94e-06 ***
## crisis_type 1 353 352.9 6.486 0.011042 *
## Continent:crisis_type 5 1225 245.1 4.504 0.000465 ***
## Residuals 865 47064 54.4
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1From the results, we see that the p-value is relatively small (1.94e-06, which is smaller than an a of 0.05) indicating strong evidence against the null hypothesis. Overall, this test suggests that there are significant differences in mean GDP growth rates between continents.
Conclusion
- Summarize the key findings of your analysis.
- Discuss the implications of your results and their relevance to the research question.
- Suggest potential avenues for future research or further analysis.
The analysis examined the effect of the 2008 financial crisis and COVID 19 on GDP growth rates across different continents. The line plot revealed that Europe was most affected by the 2008 financial crisis, quickly followed by North America. On the other hand, during COVID 19, North America was most affected, seconded by South America. We also see that during COVID 19, all continents experience a much more drastic and severe drop than during the 2008 financial crisis. The box plot analysis demonstrates considerable variation in the experience of each continent during each crisis.During the 2008 financial crisis, Europe experienced the widest distribution of growth rates with several extremely negative outliers, indicating that some European countries were hit particularly hard. During COVID 19, the box plots show that all continents have much wider distributions than what they experienced during the 2008 financial crisis, with South America experiencing a particularly wide growth rate distribution. The ANOVA test confirmed these visual observations, with a highly significant p-value which lead us to reject the null hypothesis. This statistical evidence confirms that mean GDP growth rates vary significantly across continents.
These findings are important to understanding global economics and interconnections between countries/continents. The shorter but deeper impact of COVID 19 compared to the prolonged 2008 financial crisis suggests that health related global shocks affect economics differently than that of financial system failures. Furthermore, from the relatively strong performance of Asian and African economies during both crises may reflect lower integration with global financial and public health markets. For policymakers, these results highlight the importance of region-specific economic strategies during global crises. Understanding these impacts can help create better crisis preparedness and recovery strategies.
Future research can deepen this discussion and look at the differences in GDP growth rates between individual countries within each continent and identify national factors that contribute to vulnerability. Furthermore, future research can examine the recovery trajectories of each continent, providing insight into which regions recover fastest and why. Lastly, future studies can expand the time frame to include earlier economic crises to identify long term patterns in responses to shocks between different regions.