labs_agapova
Agapova Daria
2024-06-19
R Markdown
This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.
When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:
library(readxl)
library(tidyverse)
library(ineq)
library(reshape2)## Warning: пакет 'reshape2' был собран под R версии 4.3.3library(ggplot2)
library(knitr)Lorenz curve
decile_data <- read_excel("C:/Users/astsl/Desktop/GCIPrawdata.xlsx", skip = 2)
head(decile_data)## # A tibble: 6 × 14
## Country Year `Decile 1 Income` `Decile 2 Income` `Decile 3 Income`
## <chr> <dbl> <dbl> <dbl> <dbl>
## 1 Afghanistan 1980 206 350 455
## 2 Afghanistan 1981 212 361 469
## 3 Afghanistan 1982 221 377 490
## 4 Afghanistan 1983 238 405 527
## 5 Afghanistan 1984 249 424 551
## 6 Afghanistan 1985 256 435 566
## # ℹ 9 more variables: `Decile 4 Income` <dbl>, `Decile 5 Income` <dbl>,
## # `Decile 6 Income` <dbl>, `Decile 7 Income` <dbl>, `Decile 8 Income` <dbl>,
## # `Decile 9 Income` <dbl>, `Decile 10 Income` <dbl>, `Mean Income` <dbl>,
## # Population <dbl>sel_Year1 <- c(1980, 2014)
sel_Country1 <- c("Germany", "Finland")
temp1 <- decile_data %>% filter(Country %in% sel_Country1 & Year %in% sel_Year1)
temp1## # A tibble: 4 × 14
## Country Year `Decile 1 Income` `Decile 2 Income` `Decile 3 Income`
## <chr> <dbl> <dbl> <dbl> <dbl>
## 1 Finland 1980 7450 9900 11775
## 2 Finland 2014 5741 7580 9067
## 3 Germany 1980 5077 6461 7689
## 4 Germany 2014 5222 7305 9045
## # ℹ 9 more variables: `Decile 4 Income` <dbl>, `Decile 5 Income` <dbl>,
## # `Decile 6 Income` <dbl>, `Decile 7 Income` <dbl>, `Decile 8 Income` <dbl>,
## # `Decile 9 Income` <dbl>, `Decile 10 Income` <dbl>, `Mean Income` <dbl>,
## # Population <dbl>total_income1 <- temp1[, "Mean Income"] * temp1[, "Population"]
options(scipen = 999)
total_income1## Mean Income
## 1 81347685700
## 2 76845477740
## 3 764805832000
## 4 1239206436000# Germany, 1980
decs_a80 <- unlist(temp1[1, 3:12]) * 2
# Total income for Germany, 1980, assuming a population of 20
total_inc_a80 <- 20 * unlist(temp1[1, "Mean Income"])
cum_inc_share_a80 <- cumsum(decs_a80) / total_inc_a80
# For Germany, 2014
decs_a14 <- unlist(temp1[2, 3:12]) * 2
# Total income for Germany, 2014, assuming a population of 20
total_inc_a14 <- 20 * unlist(temp1[2, "Mean Income"])
cum_inc_share_a14 <- cumsum(decs_a14) / total_inc_a14
# For Finland, 1980
decs_j80 <- unlist(temp1[3, 3:12]) * 2
# Total income for Finland, 1980, assuming a population of 20
total_inc_j80 <- 20 * unlist(temp1[3, "Mean Income"])
cum_inc_share_j80 <- cumsum(decs_j80) / total_inc_j80
# For Finland, 2014
decs_j14 <- unlist(temp1[4, 3:12]) * 2
# Total income for the Finland, 2014, assuming a population of 20
total_inc_j14 <- 20 * unlist(temp1[4, "Mean Income"])
cum_inc_share_j14 <- cumsum(decs_j14) / total_inc_j14
# Plot of the cumulative income share for each country and year with perfect equality line
par(mar = c(5, 5, 4, 2) + 0.1)
plot(cum_inc_share_a80, type = "l", col = "#491d8b",
lty = 2, lwd = 2, xlab = "Deciles",
ylab = "Cumulative income share")
abline(a = 0, b = 0.1, col = "black", lwd = 2)
lines(cum_inc_share_a14, col = "#a56eff", lty = 1, lwd = 2)
lines(cum_inc_share_j80, col = "#005d5d", lty = 2, lwd = 2)
lines(cum_inc_share_j14, col = "#3ddbd9", lty = 1, lwd = 2)
title("Lorenz curves, Germany, Finland(1980 and 2014)")
legend("topleft", lty = 2:1, lwd = 2, cex = 0.3, legend =
c("Germany, 1980", "Germany, 2014",
"Finland, 1980", "Finland, 2014"),
col = c("#491d8b", "#a56eff", "#005d5d", "#3ddbd9"))
Gini dynamics
g_g80 <- Gini(decs_a80)
g_g14 <- Gini(decs_a14)
g_f80 <- Gini(decs_j80)
g_f14 <- Gini(decs_j14)
paste("Gini coefficients")## [1] "Gini coefficients"paste("Germany - 1980: ", round(g_g80, 2), ", 2014: ", round(g_g14, 2))## [1] "Germany - 1980: 0.23 , 2014: 0.26"paste("Finland - 1980: ", round(g_f80, 2), ", 2014: ", round(g_f14, 2))## [1] "Finland - 1980: 0.28 , 2014: 0.31"plot(cum_inc_share_a80, type = "l", col = "#491d8b", lty = 2,
lwd = 2, xlab = "Deciles",
ylab = "Cumulative income share")
abline(a = 0, b = 0.1, col = "black", lwd = 2)
lines(cum_inc_share_a14, col = "#a56eff", lty = 1, lwd = 2)
lines(cum_inc_share_j80, col = "#005d5d", lty = 2, lwd = 2)
lines(cum_inc_share_j14, col = "#3ddbd9", lty = 1, lwd = 2)
title("Lorenz curves, Germany and Finland (1980 and 2014)")
legend("topleft", lty = 2.5:1, lwd = 2, cex = 0.3, legend =
c("Germany, 1980", "Germany, 2014",
"Finland, 1980", "Finland, 2014"),
col = c("#491d8b", "#a56eff", "#005d5d", "#3ddbd9"))
text(8.4, 0.78, round(g_g80, digits = 3), col = '#491d8b')
text(9.4, 0.6, round(g_g14, digits = 3), col = '#a56eff')
text(5.2, 0.37, round(g_f80, digits = 3), col = '#005d5d')
text(6.4, 0.31, round(g_f14, digits = 3), col = '#3ddbd9')
###OBSERVATIONS # The curve for Germany in 1980 is further from the line
of perfect equality, with a Gini coefficient of 0.276. This indicates a
higher level of income inequality. During this period, West Germany
faced significant economic disparities due to post-WWII economic
policies and social stratification. The curve for Germany in 2014
(purple solid line) is closer to the line of perfect equality, with a
Gini coefficient of 0.265, indicating reduced income inequality. This
improvement can be attributed to progressive taxation, social welfare
programs, and economic policies aimed at reducing inequality (OECD,
2015).
#The curve for Finland in 1980 indicates notable income inequality, with a Gini coefficient of 0.306. Finland had a relatively balanced economy but still experienced income disparities due to social class differences (Jäntti et al., 2006). The curve for Finland in 2014 is much closer to the line of perfect equality, with a Gini coefficient of 0.23, showing a significant reduction in income inequality. This can be credited to effective social reforms, including investments in education and healthcare, which promoted a more equitable distribution of income (OECD, 2015).
#Sources used: #OECD (2015): “In It Together: Why Less Inequality Benefits All”. OECD Publishing. #Jäntti, M., Riihelä, M., Sullström, R., & Tuomala, M. (2006): “Trends in income inequality: The case of Finland 1971-2002”. Finnish Economic Papers.
LAB 2
#Countries: Greece, Spain, Italy, Portugal
data_lab2 <- read_excel("C:/Users/astsl/Desktop/GCIPrawdata.xlsx", skip = 2)
data_lab2$gini <- 0
noc <- nrow(data_lab2)
for (i in seq(1, noc)){
decs_i <- unlist(data_lab2[i, 3:12])
data_lab2$gini[i] <- Gini(decs_i)
}
summary(data_lab2$gini)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.1791 0.3470 0.4814 0.4617 0.5700 0.7386data_lab2 %>% filter(gini < 0.2) %>% select (Country, Year, gini)## # A tibble: 17 × 3
## Country Year gini
## <chr> <dbl> <dbl>
## 1 Bulgaria 1987 0.191
## 2 Czech Republic 1985 0.195
## 3 Czech Republic 1986 0.194
## 4 Czech Republic 1987 0.192
## 5 Czech Republic 1988 0.191
## 6 Czech Republic 1989 0.194
## 7 Czech Republic 1990 0.196
## 8 Czech Republic 1991 0.199
## 9 Slovak Republic 1985 0.195
## 10 Slovak Republic 1986 0.194
## 11 Slovak Republic 1987 0.193
## 12 Slovak Republic 1988 0.192
## 13 Slovak Republic 1989 0.193
## 14 Slovak Republic 1990 0.194
## 15 Slovak Republic 1991 0.195
## 16 Slovak Republic 1992 0.196
## 17 Slovak Republic 1993 0.179data_lab2 %>% filter(gini > 0.73) %>% select (Country, Year, gini)## # A tibble: 27 × 3
## Country Year gini
## <chr> <dbl> <dbl>
## 1 Burkina Faso 1980 0.738
## 2 Burkina Faso 1981 0.738
## 3 Burkina Faso 1982 0.738
## 4 Burkina Faso 1983 0.738
## 5 Burkina Faso 1984 0.738
## 6 Burkina Faso 1985 0.738
## 7 Burkina Faso 1986 0.738
## 8 Burkina Faso 1987 0.738
## 9 Burkina Faso 1988 0.738
## 10 Burkina Faso 1989 0.739
## # ℹ 17 more rowsgini_s <- data_lab2 %>% filter(Country %in% c("Greece", "Spain", "Italy", "Portugal"))
ggplot(gini_s,
aes(x = Year, y = gini, color = Country)) +
geom_line(size = 1) +
theme_bw() +
ylab("Gini") +
ggtitle("Gini coefficients for the Southern Europe countries")## 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.
###Interpretation #The Gini coefficient for Greece (red line) shows
relatively stable low inequality over the years compared to other
countries. This suggests consistent income distribution policies. #Italy
(green line) exhibits fluctuations with notable peaks and troughs,
indicating varying degrees of income inequality likely influenced by
economic and policy changes. #Portugal (blue line) shows a significant
increase in inequality over time, peaking in certain periods, possibly
reflecting economic challenges and structural adjustments. #Spain
(purple line) displays erratic changes in inequality, highlighting
periods of economic instability and policy shifts.
###Graph of Interdecile P90/P10 ratio dynamics
data_lab2$ratio90_10 <- data_lab2$`Decile 10 Income`/data_lab2$`Decile 1 Income`
ratios_selected <- data_lab2 %>% filter(Country %in% c("Greece", "Spain", "Italy", "Portugal"))
ggplot(ratios_selected,
aes(x = Year, y = ratio90_10, color = Country)) +
geom_line(size = 1) +
theme_bw() +
ylab("Interdecile P90/P10") +
ggtitle("Interdecile P90/P10 for the Southern Europe countries")
###Interpretation #The red line for Greece shows relatively low and
stable inequality initially but a sharp increase in recent years,
indicating rising disparities between high and low-income earners. #The
green line for Italy shows significant fluctuations with sharp peaks,
indicating periods of increased inequality followed by improvements.
#The blue line for Portugal displays a marked increase in inequality,
peaking in recent years, reflecting widening income gaps. #The purple
line for Spain shows variability but an overall increasing trend in
inequality, indicating a growing disparity between the top and bottom
income deciles.
###Once more interdecile (90/50 or 50/10) and compare the two Interdeciles
data_lab2$ratio50_10 <- data_lab2$`Decile 5 Income`/data_lab2$`Decile 1 Income`
ratios_selected <- data_lab2 %>% filter(Country %in% c("Greece", "Spain", "Italy", "Portugal"))
ggplot(ratios_selected,
aes(x = Year, y = ratio50_10, color = Country)) +
geom_line(size = 1) +
theme_bw() +
ylab("Interdecile P50/10") +
ggtitle("Interdecile 50/10 for the Southern Europe countries")
###Comparison of interdeciles #Both plots indicate increasing inequality
in recent years for all countries but highlight different periods and
degrees of fluctuation, especially noticeable in Italy and Spain
#Find the top-5 least unequal and most unequal countries in terms of Gini as of 2014. Are they the same countries with the least and most inequality if we measure the inequality by the interdeciles? Show the tables with the top-5 countries compared and interpret the differences.
dat2014 <- data_lab2 %>% filter(Year == 2014)
top_5_least_unequal_gini <- dat2014 %>% arrange(gini) %>% head(5)
top_5_most_unequal_gini <- dat2014 %>% arrange(desc(gini)) %>% head(5)
top_5_least_unequal_ratio90_10 <- dat2014 %>% arrange(ratio90_10) %>% head(5)
top_5_most_unequal_ratio90_10 <- dat2014 %>% arrange(desc(ratio90_10)) %>% head(5)
print("Top-5 Least Unequal Countries (Gini Coefficient):")## [1] "Top-5 Least Unequal Countries (Gini Coefficient):"print(top_5_least_unequal_gini)## # A tibble: 5 × 17
## Country Year `Decile 1 Income` `Decile 2 Income` `Decile 3 Income`
## <chr> <dbl> <dbl> <dbl> <dbl>
## 1 Slovenia 2014 3983 5754 6979
## 2 Norway 2014 8325 11839 14417
## 3 Slovak Republic 2014 1939 3241 4072
## 4 Czech Republic 2014 3211 4627 5563
## 5 Finland 2014 5741 7580 9067
## # ℹ 12 more variables: `Decile 4 Income` <dbl>, `Decile 5 Income` <dbl>,
## # `Decile 6 Income` <dbl>, `Decile 7 Income` <dbl>, `Decile 8 Income` <dbl>,
## # `Decile 9 Income` <dbl>, `Decile 10 Income` <dbl>, `Mean Income` <dbl>,
## # Population <dbl>, gini <dbl>, ratio90_10 <dbl>, ratio50_10 <dbl>print("Top-5 Most Unequal Countries (Gini Coefficient):")## [1] "Top-5 Most Unequal Countries (Gini Coefficient):"print(top_5_most_unequal_gini)## # A tibble: 5 × 17
## Country Year `Decile 1 Income` `Decile 2 Income` `Decile 3 Income`
## <chr> <dbl> <dbl> <dbl> <dbl>
## 1 Botswana 2014 169 465 778
## 2 South Africa 2014 253 401 584
## 3 Zambia 2014 40 100 158
## 4 Comoros 2014 91 211 334
## 5 Central African R… 2014 21 56 92
## # ℹ 12 more variables: `Decile 4 Income` <dbl>, `Decile 5 Income` <dbl>,
## # `Decile 6 Income` <dbl>, `Decile 7 Income` <dbl>, `Decile 8 Income` <dbl>,
## # `Decile 9 Income` <dbl>, `Decile 10 Income` <dbl>, `Mean Income` <dbl>,
## # Population <dbl>, gini <dbl>, ratio90_10 <dbl>, ratio50_10 <dbl>print("Top-5 Least Unequal Countries (P90/P10 Ratio):")## [1] "Top-5 Least Unequal Countries (P90/P10 Ratio):"print(top_5_least_unequal_ratio90_10)## # A tibble: 5 × 17
## Country Year `Decile 1 Income` `Decile 2 Income` `Decile 3 Income`
## <chr> <dbl> <dbl> <dbl> <dbl>
## 1 Norway 2014 8325 11839 14417
## 2 Slovenia 2014 3983 5754 6979
## 3 Finland 2014 5741 7580 9067
## 4 Czech Republic 2014 3211 4627 5563
## 5 Netherlands 2014 5439 7790 9537
## # ℹ 12 more variables: `Decile 4 Income` <dbl>, `Decile 5 Income` <dbl>,
## # `Decile 6 Income` <dbl>, `Decile 7 Income` <dbl>, `Decile 8 Income` <dbl>,
## # `Decile 9 Income` <dbl>, `Decile 10 Income` <dbl>, `Mean Income` <dbl>,
## # Population <dbl>, gini <dbl>, ratio90_10 <dbl>, ratio50_10 <dbl>print("Top-5 Most Unequal Countries (P90/P10 Ratio):")## [1] "Top-5 Most Unequal Countries (P90/P10 Ratio):"print(top_5_most_unequal_ratio90_10)## # A tibble: 5 × 17
## Country Year `Decile 1 Income` `Decile 2 Income` `Decile 3 Income`
## <chr> <dbl> <dbl> <dbl> <dbl>
## 1 Botswana 2014 169 465 778
## 2 Lesotho 2014 19 56 97
## 3 Central African R… 2014 21 56 92
## 4 Zambia 2014 40 100 158
## 5 Swaziland 2014 38 96 154
## # ℹ 12 more variables: `Decile 4 Income` <dbl>, `Decile 5 Income` <dbl>,
## # `Decile 6 Income` <dbl>, `Decile 7 Income` <dbl>, `Decile 8 Income` <dbl>,
## # `Decile 9 Income` <dbl>, `Decile 10 Income` <dbl>, `Mean Income` <dbl>,
## # Population <dbl>, gini <dbl>, ratio90_10 <dbl>, ratio50_10 <dbl>###Comments #Four out of five countries are consistent across both Gini coefficient and P90/P10 interdecile ratio, indicating similar results. P90/P10 shows a wider range (5.44-6.23) compared to the Gini coefficient (0.25-0.26). #Three out of five countries are the same, showing more variability in P90/P10 (103.4-145.1) than in the Gini coefficient (0.624-0.639). #The P90/P10 ratio exhibits more drastic changes in inequality compared to the Gini coefficient, due to its larger variance in values.
###LAB3
data <- read.csv("C:/Users/astsl/Desktop/gini-coefficient-of-lifespan-inequality-in-females.csv")
data<- data %>% filter(Entity %in% c("Italy", "Japan", "Armenia", "Spain", "Sudan", "Nigeria", "Liberia", "Canada", "China", "USA"))
summary(data)## Entity Code Year
## Length:800 Length:800 Min. :1872
## Class :character Class :character 1st Qu.:1955
## Mode :character Mode :character Median :1977
## Mean :1973
## 3rd Qu.:1999
## Max. :2021
## Gini.coefficient.of.lifespan.inequality...Sex..female
## Min. :0.06931
## 1st Qu.:0.10041
## Median :0.19007
## Mean :0.22429
## 3rd Qu.:0.34217
## Max. :0.55993filtered_data <- data %>% filter(Year >= 1952 & Year <= 2002)Line chart
ggplot(filtered_data, aes(x = Year, y = `Gini.coefficient.of.lifespan.inequality...Sex..female`, color = Entity)) +
geom_line(linewidth = 1) +
theme_bw() +
ylab("Gini") +
ggtitle("Mortality Gini Coefficient") +
theme(legend.position = "bottom")
The plot presents the trends in mortality Gini coefficients for randomly choosen countries over time. Generally, these coefficients measure inequality in the distribution of lifespans within a population. Lower values indicate more equal lifespan distribution, while higher values indicate greater inequality We can see that obviously in African (so-called 3rd world countries) gini is higher.
#Comparing 2 countries: #Armenia shows a decreasing trend in its mortality Gini coefficient over time, especially notable from the mid-1990s onward. This suggests improvements in the equality of lifespan distribution, likely due to better access to healthcare and improved living standards. According to World Bank data, Armenia’s Gini index for income inequality has also shown a decreasing trend from a peak of 37.5 in 2004 to around 25.2 in 2020, reflecting broader improvements in economic equality as well. (World Bank Open Data). (IndexMundi - Country Facts). #Nigeria exhibits a relatively high and fluctuating mortality Gini coefficient, indicating significant inequality in lifespan distribution. This can be attributed to the country’s ongoing struggles with poverty, healthcare access, and political instability, which contribute to disparities in health outcomes. Studies have shown that higher income inequality, measured by the Gini coefficient, is associated with higher mortality rates, particularly for communicable diseases and among certain age groups.
#SOURCES USED: #https://data.worldbank.org/indicator/SI.POV.GINI?locations=AM #https://www.indexmundi.com/facts/armenia/indicator/SI.POV.GINI #https://bmcpublichealth.biomedcentral.com/articles/10.1186/s12889-017-4310-z