KORAID DATASET

Codebook

Variable	Description
country_name
cow_code
project
agreed_usd
agreed_kr
total_usd
total_kr
net_usd
net_kr
gift_value_usd
gift_value_kr
gift_pc
COVID_gift
koraid_gift
north	Russia, China, Mongolia, Kazakhstan
south	Brunei, Cambodia, India, Indonesia, Laos, Malaysia, Myanmar, Philippines, Singapore, Thailand, Vietnam
eth_fraction	Ethnic fractionalization (Source: CREG Project)
eth_polarized	Ethnic polarizarion (Source: CREG Project)
rel_fraction	Religious fractionalization (Source: CREG Project)
rel_polarized	Religious fractionalization (Source: CREG Project)
rugged	Level of terrain ruggedness in country (Source: Gibler and Miller, 2014)
polity	Polity Score (Source: Polity Project)
level_contig	Level of contiguity 1 = direct land contiguity. 2 = separated by max 12 miles of water 3 = separated by max 24 miles. 4 = separated by max 150 miles of water 5 = separated by max 400 miles of water (Source: Correlates of War)
shared_igso	number of mutual IGOs for which country is a member with South Korea (Source: Correlates of War)
dist_seoul	Distance to Seoul
continent	Africa, Americas, Asia, Europe, Oceania
income_group_name	High, Upper Middle, Lower Middle, Low Income Country
pop	World Bank population estimate
GDP_per_cap_constant_2010	World Bank GDP per capita at 2010 US dollars
infant_mortality	World Bank infant deaths per 1000 live births
region	East Asia & Pacific, Europe & Central Asia, Latin America & Caribbean, Middle East & North Africa, North America, South Asia, Sub-Saharan Africa
cases_total	WHO total cumulative COVID cases
cases_total_per_100000	WHO total cumulative COVID cases per 100,000 population
deaths_total	WHO total cumulative COVID deaths
death_total_per_100000	WHO total cumulative COVID deaths per 100,000 population
export_value	Exports from ROK (Source: Korean Customs Service)
import_value	Imports to ROK (Source: Korean Customs Service)
trade_balance	Balance of Payments

Descriptive Statistics

skim(kor_cov) %>% 
  dplyr::select(-c(numeric.p0:numeric.p100))  

Data summary

Name	kor_cov
Number of rows	174
Number of columns	43
_______________________
Column type frequency:
character	7
numeric	36
________________________
Group variables	None

Variable type: character

skim_variable	n_missing	complete_rate	min	max	empty	n_unique	whitespace
country_name	0	1.00	4	32	0	174	0
continent	2	0.99	4	8	0	5	0
region_wb	2	0.99	10	26	0	7	0
income_group_name	8	0.95	18	27	0	4	0
region	1	0.99	10	26	0	7	0
region_who	24	0.86	6	21	0	6	0
country	6	0.97	4	37	0	168	0

Variable type: numeric

skim_variable	n_missing	complete_rate	mean	sd	hist
cow_code	5	0.97	466.64	2.444800e+02	▆▇▇▇▃
project	93	0.47	24.57	3.240000e+01	▇▂▁▁▁
agreed_usd	0	1.00	6508522.22	1.879271e+07	▇▁▁▁▁
agreed_kr	0	1.00	7681671941.79	2.218032e+10	▇▁▁▁▁
total_usd	0	1.00	4130678.76	1.294224e+07	▇▁▁▁▁
total_kr	0	1.00	4874735540.09	1.527352e+10	▇▁▁▁▁
net_usd	0	1.00	3897431.61	1.274026e+07	▇▁▁▁▁
net_kr	0	1.00	4599473581.62	1.503516e+10	▇▁▁▁▁
gift_value_usd	0	1.00	3722901.83	1.135687e+07	▇▁▁▁▁
gift_value_kr	0	1.00	4393505757.28	1.340258e+10	▇▁▁▁▁
gift_pc	0	1.00	0.03	2.000000e-01	▇▁▁▁▁
COVID_gift	0	1.00	625810.90	4.294113e+06	▇▁▁▁▁
koraid_gift	0	1.00	2983056.92	1.129134e+07	▇▁▁▁▁
north	0	1.00	0.02	1.300000e-01	▇▁▁▁▁
south	0	1.00	0.00	0.000000e+00	▁▁▇▁▁
eth_fraction	55	0.68	0.45	2.500000e-01	▆▇▆▆▇
eth_polarized	55	0.68	0.56	2.100000e-01	▂▅▅▇▅
rel_fraction	53	0.70	0.41	2.100000e-01	▆▆▇▇▇
rel_polarized	53	0.70	0.62	2.700000e-01	▃▂▅▇▇
rugged	45	0.74	1.26	1.170000e+00	▇▃▁▁▁
polity	47	0.73	4.39	6.030000e+00	▂▂▁▃▇
level_contig	42	0.76	0.07	5.600000e-01	▇▁▁▁▁
shared_igso	42	0.76	43.84	1.048000e+01	▁▁▇▅▂
dist_seoul	42	0.76	10214.13	3.430590e+03	▁▇▇▆▁
pop	5	0.97	42423485.83	1.531908e+08	▇▁▁▁▁
GDP_per_cap_constant_2010	10	0.94	14235.93	2.001703e+04	▇▁▁▁▁
infant_mortality	5	0.97	21.68	1.993000e+01	▇▂▂▁▁
cases_total	24	0.86	4149.31	4.152320e+03	▇▃▂▁▁
cases_total_per_100000	24	0.86	17274.96	3.935720e+04	▇▁▁▁▁
deaths_total	24	0.86	74.61	9.114000e+01	▇▂▁▁▁
death_total_per_100000	24	0.86	284.73	7.985500e+02	▇▁▁▁▁
number_of_export	6	0.97	50510.72	2.415154e+05	▇▁▁▁▁
export_value	6	0.97	2573188.04	1.150313e+07	▇▁▁▁▁
number_of_import	6	0.97	77301.19	3.765683e+05	▇▁▁▁▁
import_value	6	0.97	2577729.12	9.737862e+06	▇▁▁▁▁
trade_balance	6	0.97	-4541.07	4.404132e+06	▁▇▃▁▁

Correlation Matrices

Corrplot package

kor_cov %>% 
   mutate(ln_gift_pc = log(gift_pc),
          ln_covid_gift = log(COVID_gift), 
          ln_total_aid = log(total_usd),
          ln_gdp_pc = log(GDP_per_cap_constant_2010),
          ln_pop = log(pop),
          ln_covid_cases = log(cases_total_per_100000),
          ln_dist = log(dist_seoul),
          ln_export = log(export_value), 
          ln_import = log(import_value)) %>% 
   select(ln_covid_gift, ln_total_aid, ln_pop, ln_gdp_pc, ln_covid_cases, ln_export) -> kor_cov_sub

kor_cov_no_na <- na.omit(kor_cov_sub)

conf_test2 = cor.mtest(kor_cov_no_na, conf.level = 0.95) 

corrplot(cor(kor_cov_no_na, method = "spearman"), 
         p.mat = conf_test2$p,
         method = 'circle',
         type = 'lower', 
         insig ='blank',
         addCoef.col ='black',
         number.cex = 0.8, 
         order = 'AOE', 
         diag = FALSE, 
         tl.srt = 45)

kor_cov %>% 
   mutate(ln_gift_pc = log(gift_pc),
          ln_covid_gift = log(COVID_gift), 
          ln_total_aid = log(total_usd),
          ln_gdp_pc = log(GDP_per_cap_constant_2010),
          ln_pop = log(pop),
          ln_covid_cases = log(cases_total_per_100000),
          ln_dist = log(dist_seoul),
          ln_export = log(export_value), 
          ln_import = log(import_value)) %>% 
   select(ln_covid_gift, ln_total_aid, ln_pop, ln_gdp_pc, ln_covid_cases, ln_export, income_group_name) -> kor_cov_sub2

GGally package

kor_cov2_no_na <- na.omit(kor_cov_sub2)

library(GGally)

kor_cov2_no_na %>%
  filter(income_group_name != "High Income Country") %>%
  filter(!is.na(income_group_name)) %>%
  mutate(income = ifelse(income_group_name == "Low Income Country", "Low",
                  ifelse(income_group_name == "Lower Middle Income Country", "Middle",
                  ifelse(income_group_name == "Upper Middle Income Country", "Upper", income_group_name)))) %>%
  select(!income_group_name) %>%
  ggpairs(mapping = ggplot2::aes(colour = income),
          alpha = 0.5, 
           upper = list(continuous = wrap("cor", size = 2.5))) +
  theme(axis.text.x = element_text(angle = 70, hjust = 1),
        strip.text.x =  element_text(angle = 30),
        strip.text.y = element_text(angle = 20))

Performance Analytics package

library(PerformanceAnalytics)

chart.Correlation(kor_cov_no_na, 
                  histogram = TRUE,
                  method = "spearman",
                  cex.cor = 50, 
                  cex.labels = 50,
                  cex = 1.5, 
                  cex.font = 5)