Graphing Pew survey responses with ggplot in R

Packages we will need:


We are going to look at a few questions from the 2019 US Pew survey on relations with foreign countries.

Data can be found by following this link:

We are going to make bar charts to plot out responses to the question asked to American participaints: Should the US cooperate more or less with some key countries? The countries asked were China, Russia, Germany, France, Japan and the UK.

Before we dive in, we can find some nice hex colors for the bar chart. There are four possible responses that the participants could give: cooperate more, cooperate less, cooperate the same as before and refuse to answer / don’t know.

pal <- c("Cooperate more" = "#0a9396",
         "Same as before" = "#ee9b00",
         "Don't know" = "#005f73",
         "Cooperate less" ="#ae2012")

We first select the questions we want from the full survey and pivot the dataframe to long form with pivot_longer(). This way we have a single column with all the different survey responses. that we can manipulate more easily with dplyr functions.

Then we summarise the data to count all the survey reponses for each of the four countries and then calculate the frequency of each response as a percentage of all answers.

Then we mutate the variables so that we can add flags. The geom_flag() function from the ggflags packages only recognises ISO2 country codes in lower cases.

After that we change the factors level for the four responses so they from positive to negative views of cooperation

pew %>% 
  select(id = case_id, Q2a:Q2f) %>% 
  pivot_longer(!id, names_to = "survey_question", values_to = "response")  %>% 
  group_by(survey_question, response) %>% 
  summarise(n = n()) %>%
  mutate(freq = n / sum(n)) %>% 
  ungroup() %>% 
  mutate(response_factor = as.factor(response)) %>% 
  mutate(country_question = ifelse(survey_question == "Q2a", "fr",
ifelse(survey_question == "Q2b", "gb",
ifelse(survey_question == "Q2c", "ru",
ifelse(survey_question == "Q2d", "cn",
ifelse(survey_question == "Q2e", "de",
ifelse(survey_question == "Q2f", "jp", survey_question))))))) %>% 
  mutate(response_string = ifelse(response_factor == 1, "Cooperate more",
ifelse(response_factor == 2, "Cooperate less",
ifelse(response_factor == 3, "Same as before",
ifelse(response_factor == 9, "Don't know", response_factor))))) %>% 
  mutate(response_string = fct_relevel(response_string, c("Cooperate less","Same as before","Cooperate more", "Don't know"))) -> pew_clean

We next use ggplot to plot out the responses.

We use the position = "stack" to make all the responses “stack” onto each other for each country. We use stat = "identity" because we are not counting each reponses. Rather we are using the freq variable we calculated above.

pew_clean %>%
  ggplot() +
  geom_bar(aes(x = forcats::fct_reorder(country_question, freq), y = freq, fill = response_string), color = "#e5e5e5", size = 3, position = "stack", stat = "identity") +
  geom_flag(aes(x = country_question, y = -0.05 , country = country_question), color = "black", size = 20) -> pew_graph

And last we change the appearance of the plot with the theme function

pew_graph + 
coord_flip() + 
  scale_fill_manual(values = pal) +
  ggthemes::theme_fivethirtyeight() + 
  ggtitle("Should the US cooperate more or less with the following country?") +
  theme(legend.title = element_blank(),
        legend.position = "top",
        legend.key.size = unit(2, "cm"),
        text = element_text(size = 25),
        legend.text = element_text(size = 20),
        axis.text = element_blank())

Lollipop plots with ggplot2 in R

Packages we will need:


We will plot out a lollipop plot to compare EU countries on their level of income inequality, measured by the Gini coefficient.

A Gini coefficient of zero expresses perfect equality, where all values are the same (e.g. where everyone has the same income). A Gini coefficient of one (or 100%) expresses maximal inequality among values (e.g. for a large number of people where only one person has all the income or consumption and all others have none, the Gini coefficient will be nearly one).

To start, we will take data on the EU from Wikipedia. With rvest package, scrape the table about the EU countries from this Wikipedia page.

Click here to read more about the rvest pacakge

With the gsub() function, we can clean up the different variables with some regex. Namely delete the footnotes / square brackets and change the variable classes.

eu_site <- read_html("")

eu_tables <- eu_site %>% html_table(header = TRUE, fill = TRUE)

eu_members <- eu_tables[[3]]

eu_members %<>% janitor::clean_names()  %>% 

eu_members$iso3 <- countrycode::countrycode(eu_members$geo, "", "iso3c")

eu_members$accession <- as.numeric(gsub("([0-9]+).*$", "\\1",eu_members$accession))

eu_members$name_clean <- gsub("\\[.*?\\]", "", eu_members$name)

eu_members$gini_clean <- gsub("\\[.*?\\]", "", eu_members$gini)

Next some data cleaning and grouping the year member groups into different decades. This indicates what year each country joined the EU. If we see clustering of colours on any particular end of the Gini scale, this may indicate that there is a relationship between the length of time that a country was part of the EU and their domestic income inequality level. Are the founding members of the EU more equal than the new countries? Or conversely are the newer countries that joined from former Soviet countries in the 2000s more equal. We can visualise this with the following mutations:

eu_members %>%
  filter(name_clean != "Totals/Averages") %>% 
  mutate(gini_numeric = as.numeric(gini_clean)) %>% 
  mutate(accession_decades = ifelse(accession < 1960, "1957", ifelse(accession > 1960 & accession < 1990, "1960s-1980s", ifelse(accession == 1995, "1990s", ifelse(accession > 2003, "2000s", accession))))) -> eu_clean 

To create the lollipop plot, we will use the geom_segment() functions. This requires an x and xend argument as the country names (with the fct_reorder() function to make sure the countries print out in descending order) and a y and yend argument with the gini number.

All the countries in the EU have a gini score between mid 20s to mid 30s, so I will start the y axis at 20.

We can add the flag for each country when we turn the ISO2 character code to lower case and give it to the country argument.

Click here to read more about the ggflags package

eu_clean %>% 
ggplot(aes(x= name_clean, y= gini_numeric, color = accession_decades)) +
  geom_segment(aes(x = forcats::fct_reorder(name_clean, -gini_numeric), 
                   xend = name_clean, y = 20, yend = gini_numeric, color = accession_decades), size = 4, alpha = 0.8) +
  geom_point(aes(color = accession_decades), size= 10) +
  geom_flag(aes(y = 20, x = name_clean, country = tolower(iso_3166_1_alpha_2)), size = 10) +
  ggtitle("Gini Coefficients of the EU countries") -> eu_plot

Last we add various theme changes to alter the appearance of the graph

eu_plot + 
coord_flip() +
ylim(20, 40) +
  theme(panel.border = element_blank(),
        legend.title = element_blank(),
        axis.title = element_blank(),
        axis.text = element_text(color = "white"),
        text= element_text(size = 35, color = "white"),
        legend.text = element_text(size = 20),
        legend.key = element_rect(colour = "#001219", fill = "#001219"),
        legend.key.width = unit(3, 'cm'),
        legend.position = "bottom",
        panel.grid.major.y = element_line(linetype="dashed"),
        plot.background = element_rect(fill = "#001219"),
        panel.background = element_rect(fill = "#001219"),
        legend.background = element_rect(fill = "#001219") )

We can see there does not seem to be a clear pattern between the year a country joins the EU and their level of domestic income inequality, according to the Gini score.

Of course, the Gini coefficient is not a perfect measurement, so take it with a grain of salt.

Another option for the lolliplot plot comes from the ggpubr package. It does not take the familiar aesthetic arguments like you can do with ggplot2 but it is very quick and the defaults look good!

eu_clean %>% 
  ggdotchart( x = "name_clean", y = "gini_numeric",
              color = "accession_decades",
              sorting = "descending",                      
              rotate = TRUE,                                
              dot.size = 10,   
              y.text.col = TRUE,
              ggtheme = theme_pubr()) + 
  ggtitle("Gini Coefficients of the EU countries") + 
  theme(panel.border = element_blank(),
        legend.title = element_blank(),
        axis.title = element_blank(),
        axis.text = element_text(color = "white"),
        text= element_text(size = 35, color = "white"),
        legend.text = element_text(size = 20),
        legend.key = element_rect(colour = "#001219", fill = "#001219"),
        legend.key.width = unit(3, 'cm'),
        legend.position = "bottom",
        panel.grid.major.y = element_line(linetype="dashed"),
        plot.background = element_rect(fill = "#001219"),
        panel.background = element_rect(fill = "#001219"),
        legend.background = element_rect(fill = "#001219") )

Replicating Eurostat graphs in R

Packages we will need:


In this blog, we will try to replicate this graph from Eurostat!

It compares all European countries on their Digitical Intensity Index scores in 2020. This measures the use of different digital technologies by enterprises.

The higher the score, the higher the digital intensity of the enterprise, ranging from very low to very high. 

For more information on the index, I took the above information from this site:

First, we will download the digital index from Eurostat with the get_eurostat() function.

Click here to learn more about downloading data on EU from the Eurostat package.

Next some data cleaning. To copy the graph, we will aggregate the different levels into very low, low, high and very high categories with the grepl() function in some ifelse() statements.

The variable names look a bit odd with lots of blank space because I wanted to space out the legend in the graph to replicate the Eurostat graph above.

dig <- get_eurostat("isoc_e_dii", type = "label")

dig %<>% 
   mutate(dii_level = ifelse(grepl("very low", indic_is), "Very low        " , ifelse(grepl("with low", indic_is), "Low        ", ifelse(grepl("with high", indic_is), "High        ", ifelse(grepl("very high", indic_is), "Very high        ", indic_is)))))

Next I fliter out the year I want and aggregate all industry groups (from the sizen_r2 variable) in each country to calculate a single DII score for each country.

dig %>% 
  select(sizen_r2, geo, values, dii_level, year) %>%  
  filter(year == 2020) %>% 
  group_by(dii_level, geo) %>% 
  summarise(total_values = sum(values, na.rm = TRUE)) %>% 
  ungroup() -> my_dig

I use a hex finder website to find the same hex colors from the Eurostat graph and assign them to our version.

dii_pal <- c("Very low        " = "#f0aa4f",
             "Low        " = "#fee229",
             "Very high        " = "#154293", 
             "High        " = "#7fa1d4")

We can make sure the factors are in the very low to very high order (rather than alphabetically) with the ordered() function

my_dig$dii_level <- ordered(my_dig$dii_level, levels = c("Very Low        ", "Low        ", "High        ","Very high        "))

Next we filter out the geo rows we don’t want to add to the the graph.

Also we can change the name of Germany to remove its longer title.

my_dig %>% 
  filter(geo != "Euro area (EA11-1999, EA12-2001, EA13-2007, EA15-2008, EA16-2009, EA17-2011, EA18-2014, EA19-2015)") %>% 
  filter(geo != "United Kingdom") %>% 
  filter(geo != "European Union - 27 countries (from 2020)") %>% 
  filter(geo != "European Union - 28 countries (2013-2020)") %>% 
  mutate(geo = ifelse(geo == "Germany (until 1990 former territory of the FRG)", "Germany", geo)) -> my_dig 

And also, to have the same order of countries that are in the graph, we can add them as ordered factors.

my_dig$country <- factor(my_dig$geo, levels = c("Finland", "Denmark", "Malta", "Netherlands", "Belgium", "Sweden", "Estonia", "Slovenia", "Croatia", "Italy", "Ireland","Spain", "Luxembourg", "Austria", "Czechia", "France", "Germany", "Portugal", "Poland", "Cyprus", "Slovakia", "Hungary", "Lithuania", "Latvia", "Greece", "Romania", "Bulgaria", "Norway"), ordered = FALSE)

Now to plot the graph:

my_dig %>% 
  filter(! %>% 
  group_by(country, dii_level) %>% 
  ggplot(aes(y = country, 
             x = total_values,
             fill = forcats::fct_rev(dii_level))) +
  geom_col(position = "fill", width = 0.7) + 
  scale_fill_manual(values = dii_pal) + 
  ggthemes::theme_pander() +
  coord_flip() +
  labs(title = "EU's Digital Intensity Index (DII) in 2020",
       subtitle = ("(% of enterprises with at least 10 persons employed)"),
       caption = "ec.europa/eurostat") +
  xlab("") + 
  ylab("") + 
  theme(text = element_text(family = "Verdana", color = "#154293"),
        axis.line.x = element_line(color = "black", size = 1.5),
        axis.text.x = element_text(angle = 90, size = 20, color = "#154293", hjust = 1),
        axis.text.y = element_text(color = "#808080", size = 13, face = "bold"),
        legend.position = "top", 
        legend.title = element_blank(),
        legend.text = element_text(color = "#808080", size = 20, face = "bold"),
        plot.title = element_text(size = 42, color = "#154293"),
        plot.subtitle = element_text(size = 25, color = "#154293"),
        plot.caption = element_text(size = 20, color = "#154293"),
        panel.background = element_rect(color = "#f2f2f2"))

It is not identical and I had to move the black line up and the Norway model more to the right with Paint on my computer! So a bit of cheating!

Click to read Part 1, Part 2 and Part 3 of the blog series on visualising Eurostat data

For information on the index discussed in this blog post:

Bump charts for ranking with ggbump package in R


Click here for Part 1 and here for Part 2 of the series on Eurostat data – explains how to download and visualise the Eurostat data

In this blog, we will look at government expenditure of the European Union!

Part 1 will go into detail about downloading Eurostat data with their package.

govt <- get_eurostat("gov_10a_main", fix_duplicated = TRUE)

Some quick data cleaning and then we can look at the variables in the dataset.

govt$year <- as.numeric(format(govt$time, format = "%Y"))

The numbers and letters are a bit incomprehensible. We can go to the Eurostat data browser site. It ascts as a codebook for all the variables we downloaded:

I want to take the EU accession data from Wikipedia. Check out the Part 1 blog post to scrape the data.

govt$iso3 <- countrycode(govt$geo, "iso2c", "iso3c")

govt_df <- merge(govt, eu_members, by.x = "iso3", by.y = "iso_3166_1_alpha_3", all.x = TRUE)

We will look at general government spending of the countries from the 2004 accession.

Also we will choose data is government expenditure as a percentage of GDP.

govt_df %<>%
  filter(sector == "S13") %>%      # General government spending
  filter(accession == 2004) %>%    # For countries that joined 2004
  filter(unit == "PC_GDP") %>%     # Spending as percentage of GDP
  filter(na_item == "TE")          # Total expenditure

A little more data cleaning! To use the ggflags package, the ISO 2 character code needs to be in lower case.

Also we will use some regex to remove the strings in the square brackets from the dataset.

govt_df$iso2_lower <- tolower(govt_df$iso_3166_1_alpha_2)

govt_df$name_clean <- gsub("\\[.*?\\]", "", govt_df$name)

To put the flags at the start of the graph and names of the countries at the end of the lines, create mini dataframes with only information for the last year and first year:

last_time <- govt_df %>%
  group_by(geo) %>% 
  slice(which.max(year)) %>% 

first_time <- govt_df %>%
  group_by(geo) %>% 
  slice(which.min(year)) %>% 

I choose some nice hex colours from the coolors website. They need # in the strings to be acknowledged as hex colours by ggplot

add_hashtag <- function(my_vec){
  hash_vec <-  paste0('#', my_vec)

pal <- c("0affc2","ffb8d1","05e6dc","00ccf5","ff7700",

pal_hash <- add_hashtag(pal)

Now we can plot:

govt_df %>% 
  filter(geo != "CY" | geo != "MT") %>% 
  filter( year < 2020) %>% 
  ggplot(aes(x = year,
             y = values, group = name)) + 
  geom_text_repel(data = last_time, aes(label = name_clean, 
                                        color = name), 
                  size = 6, hjust = -3) +
  geom_point(aes(color = name)) + 
  geom_line(aes(color = name), size = 3, alpha = 0.8) +
  ggflags::geom_flag(data = first_time,
                     aes(x = year,
                         y = values,
                         country = iso2_lower),
                     size = 8) +
   scale_color_manual(values = pal_hash) +
  xlim(1994, 2021) + 
   ggthemes::theme_fivethirtyeight() +
  theme(panel.background = element_rect(fill = "#284b63"),
        legend.position = "none",
        axis.text.x = element_text(size = 20),
        axis.text.y = element_text(size = 20),
        panel.grid.major.y = element_line(color = "#495057",
                                          size = 0.5,
                                          linetype = 2),
        panel.grid.minor.y = element_line(color = "#495057",
                                          size = 0.5,
                                          linetype = 2)) +
  guides(colour = guide_legend(override.aes = list(size=10)))

Sometimes a simple line graph doesn’t easily show us the ranking of the countries over time.

The last graph was a bit cluttered, so we can choose the top average highest government expenditures to compare

govt_rank %>% 
  distinct(geo, mean_rank) %>% 
  top_n(6, mean_rank) %>%
  pull(geo) -> top_rank

We can look at a bump chart that ranks the different positions over time

govt_df %>% 
  filter(geo %in%  top_rank) %>% 
  group_by(year) %>%
  mutate(rank_budget = rank(-values, ties.method = "min")) %>%
  ungroup() %>% 
  group_by(geo) %>% 
  mutate(mean_rank = mean(values)) %>% 
  ungroup()  %>% 
  select(geo, iso2_lower, year, fifth_year, rank_budget, mean_rank) -> govt_rank

We recreate the last and first dataframes for the flags with the new govt_rank dataset.

last_time <- govt_rank %>%
  filter(geo %in% top_rank ) %>% 
  group_by(geo) %>% 
  slice(which.max(year)) %>% 

first_time <- govt_rank %>%
  filter(geo %in% top_rank ) %>% 
  group_by(geo) %>% 
  slice(which.min(year)) %>% 

All left to do is code the bump plot to compare the ranking of highest government expenditure as a percentage of GDP

govt_rank %>% 
  ggplot(aes(x = year, y = rank_budget, 
             group = country,
             color = country, fill = country)) +
  geom_point() +
            size = 3, alpha = 0.8,
            lineend = "round") + 
  geom_flag(data = last_time %>%
              filter(year == max(year)),
            aes(country = iso2_lower ),
            size = 20,
            color = "black") +
  geom_flag(data = first_time %>%
              filter(year == max(year)),
            aes(country = iso2_lower),
            size = 20,
            color = "black") -> govt_bump

Last we change the theme aesthetics of the bump plot

govt_bump + theme(panel.background = element_rect(fill = "#284b63"),
      legend.position = "bottom",
      axis.text.x = element_text(size = 20),
      axis.text.y = element_text(size = 20),
      axis.line = element_line(color='black'),
      axis.title.x = element_blank(), 
      axis.title.y = element_blank(), 
      legend.title = element_blank(),
      legend.text = element_text(size = 20),
      panel.grid.major = element_blank(),
      panel.grid.minor = element_blank()) + 
  guides(colour = guide_legend(override.aes = list(size=10))) + 
  scale_y_reverse(breaks = 1:100)

I added the title and moved the legend with, rather than attempt it with ggplots! I feel bad for cheating a bit.

Visualize EU data with Eurostat package in R: Part 2 (with maps)

In this post, we will map prison populations as a percentage of total populations in Europe with Eurostat data.


Click here to read Part 1 about downloading Eurostat data.

prison_pop <- get_eurostat("crim_pris_pop", type = "label")

prison_pop$iso3 <- countrycode::countrycode(prison_pop$geo, "", "iso3c")

prison_pop$year <- as.numeric(format(prison_pop$time, format = "%Y"))

Next we will download map data with the rnaturalearth package. Click here to read more about using this package.

We only want to zoom in on continental EU (and not include islands and territories that EU countries have around the world) so I use the coordinates for a cropped European map from this R-Bloggers post.

map <- rnaturalearth::ne_countries(scale = "medium", returnclass = "sf")

europe_map <- sf::st_crop(map, xmin = -20, xmax = 45,
                          ymin = 30, ymax = 73)

prison_map <- merge(prison_pop, europe_map, by.x = "iso3", by.y = "adm0_a3", all.x = TRUE)

We will look at data from 2000.

prison_map %>% 
  filter(year == 2000) -> map_2000

To add flags to our map, we will need ISO codes in lower case and longitude / latitude.

prison_map$iso2c <- tolower(countrycode(prison_map$geo, "", "iso2c"))

coord <- read_html("")

coord_tables <- coord %>% html_table(header = TRUE, fill = TRUE)

coord <- coord_tables[[1]]

prison_map <- merge(prison_map, coord, by.x= "iso_a2", by.y = "country", all.y = TRUE)

Nex we will plot it out!

We will focus only on European countries and we will change the variable from total prison populations to prison pop as a percentage of total population. Finally we multiply by 1000 to change the variable to per 1000 people and not have the figures come out with many demical places.

prison_map %>% 
  filter(continent == "Europe") %>% 
  mutate(prison_pc = (values / pop_est)*1000) %>% 
  ggplot() +
  geom_sf(aes(fill = prison_pc, geometry = geometry), 
          position = "identity") + 
  labs(fill='Prison population')  +
  ggflags::geom_flag(aes(x = longitude, 
                         y = latitude+0.5, 
                         country = iso2_lower), 
                     size = 9) +  
  scale_fill_viridis_c(option = "mako", direction = -1) +
  ggthemes::theme_map() -> prison_map

Next we change how it looks, including changing the background of the map to a light blue colour and the legend.

prison_map + 
  theme(legend.title = element_text(size = 20),
        legend.text = element_text(size = 14), 
         legend.position = "bottom",
        legend.background = element_rect(fill = "lightblue",
                                         colour = "lightblue"),
        panel.background = element_rect(fill = "lightblue",
                                        colour = "lightblue"))

I will admit that I did not create the full map in ggplot. I added the final titles and block colours with because it was just easier! I always find fonts very tricky in R so it is nice to have dozens of different fonts in Canva and I can play around with colours and font sizes without needing to reload the plot each time.

Download EU data with Eurostat package in R: Part 1 (with pyramid graphs)


Eurostat is the statistical office of the EU. It publishes statistics and indicators that enable comparisons between countries and regions.

With the eurostat package, we can visualise some data from the EU and compare countries. In this blog, we will create a pyramid graph and a Statista-style bar chart.

First, we use the get_eurostat_toc() function to see what data we can download. We only want to look at datasets.

available_data <- get_eurostat_toc()

available_datasets <- available_data %>% 
  filter(type == "dataset")

A simple dataset that we can download looks at populations. We can browse through the available datasets and choose the code id. We feed this into the get_eurostat() dataset.

demo <- get_eurostat(id = "demo_pjan", 
                     type = "label")


Some quick data cleaning. First changing the date to a numeric variable. Next, extracting the number from the age variable to create a numeric variable.

demo$year <- as.numeric(format(demo$time, format = "%Y"))

demo$age_number <- as.numeric(gsub("([0-9]+).*$", "\\1", demo$age))

Next we filter out the data we don’t need. For this graph, we only want the total columns and two years to compare.

demo %>%
  filter(age != "Total") %>%
  filter(age != "Unknown") %>% 
  filter(sex == "Total") %>% 
  filter(year == 1960 | year == 2019 ) %>% 
  select(geo, iso3, values, age_number) -> demo_two_years

I want to compare the populations of the founding EU countries (in 1957) and those that joined in 2004. I’ll take the data from Wikipedia, using the rvest package. Click here to learn how to scrape data from the Internet.

eu_site <- read_html("")

eu_tables <- eu_site %>% html_table(header = TRUE, fill = TRUE)

eu_members <- eu_tables[[3]]

eu_members %<>% janitor::clean_names()  %>% 

Some quick data cleaning to get rid of the square bracket footnotes from the Wikipedia table data.

eu_members$accession <- as.numeric(gsub("([0-9]+).*$", "\\1",eu_members$accession))

eu_members$name_clean <- gsub("\\[.*?\\]", "", eu_members$name)

We merge the two datasets, on the same variable. In this case, I will use the ISO3C country codes (from the countrycode package). Using the names of each country is always tricky (I’m looking at you, Czechia / Czech Republic).

demo_two_years$iso3 <- countrycode::countrycode(demo_two_years$geo, ", "iso3c")

my_pyramid <- merge(demo_two_years, eu_members, by.x = "iso3", by.y = "iso_3166_1_alpha_3", all.x = TRUE)

We will use the pyramid_chart() function from the ggcharts package. Click to read more about this function.

The function takes the age group (we go from 1 to 99 years of age), the number of people in that age group and we add year to compare the ages in 1960 versus in 2019.

The first graph looks at the countries that founded the EU in 1957.

my_pyramid %>%  
  filter(! %>%  
  filter(accession == 1957 ) %>% 
  arrange(age_number) %>% 
  group_by(year, age_number) %>% 
  summarise(mean_age = mean(values, na.rm = TRUE)) %>% 
  ungroup() %>% 
  pyramid_chart(age_number, mean_age, year,
                bar_colors = c("#9a031e", "#0f4c5c")) 
Source: Eurostat

The second graph is the same, but only looks at the those which joined in 2004.

my_pyramid %>%  
  filter(! %>%  
  filter(accession == 2004 ) %>% 
  arrange(age_number) %>% 
  group_by(year, age_number) %>% 
  summarise(mean_age = mean(values, na.rm = TRUE)) %>% 
  ungroup() %>% 
  pyramid_chart(age_number, mean_age, year,
                bar_colors = c("#9a031e", "#0f4c5c")) 

Next we will use the Eurostat data on languages in the EU and compare countries in a bar chart.

I want to try and make this graph approximate the style of Statista graphs. It is far from identical but I like the clean layout that the Statista website uses.

Similar to above, we add the code to the get_eurostat() function and claen the data like above.

lang <- get_eurostat(id = "edat_aes_l22", 
                     type = "label")

lang$year <- as.numeric(format(lang$time, format = "%Y"))

lang$iso2 <- tolower(countrycode(lang$geo, "", "iso2c"))

lang %>% 
  mutate(geo = ifelse(geo == "Germany (until 1990 former territory of the FRG)", "Germany", 
                      ifelse(geo == "European Union - 28 countries (2013-2020)", "EU", geo))) %>% 
  filter(n_lang == "3 languages or more") %>% 
  filter(year == 2016) %>% 
  filter(age == "From 25 to 34 years") %>% 
  filter(! %>% 
  group_by(geo, year) %>% 
  mutate(mean_age = mean(values, na.rm = TRUE)) %>% 
  arrange(mean_age) -> lang_clean

Next we will create bar chart with the stat = "identity" argument.

We need to make sure our ISO2 country code variable is in lower case so that we can add flags to our graph with the ggflags package. Click here to read more about this package

lang_clean %>%
  ggplot(aes(x = reorder(geo, mean_age), y = mean_age)) + 
  geom_bar(stat = "identity", width = 0.7, color = "#0a85e5", fill = "#0a85e5") + 
  ggflags::geom_flag(aes(x = geo, y = -1, country = iso2), size = 8) +
  geom_text(aes(label= values), position = position_dodge(width = 0.9), hjust = -0.5, size = 5, color = "#000500") + 
  labs(title = "Percentage of people that speak 3 or more languages",
       subtitle = ("(% of overall population)"),
       caption = "         Source: Eurostat ") +
  xlab("") + 
  ylab("") -> lang_plot 

To try approximate the Statista graphs, we add many arguments to the theme() function for the ggplot graph!

lang_plot + coord_flip() + 
  expand_limits(y = 65) + 
  ggthemes::theme_pander() + 
  theme(plot.background = element_rect(color = "#f5f9fc"),
        panel.grid = element_line(colour = "#f5f9fc"),
        # axis.title.x = element_blank(),
        axis.text.x = element_blank(),
        axis.text.y = element_text(color = "#000500", size = 16),
        # axis.title.y = element_blank(),
        axis.ticks.x = element_blank(),
        text = element_text(family = "Gadugi"),
        plot.title = element_text(size = 28, color = "#000500"),
        plot.subtitle = element_text(size = 20, color = "#484e4c"),
        plot.caption = element_text(size = 20, color = "#484e4c") )

Next, click here to read Part 2 about visualizing Eurostat data with maps

Building a dataset for political science analysis in R, PART 2

Packages we will need


The main workhorse of this blog is the peacesciencer package by Stephen Miller!

The package will create both dyad datasets and state datasets with all sovereign countries.

Thank you Mr Miller!

There are heaps of options and variables to add.

Go to the page to read about them all in detail.

Here is a short list from the package description of all the key variables that can be quickly added:

We create the dyad dataset with the create_dyadyears() function. A dyad-year dataset focuses on information about the relationship between two countries (such as whether the two countries are at war, how much they trade together, whether they are geographically contiguous et cetera).

In the literature, the study of interstate conflict has adopted a heavy focus on dyads as a unit of analysis.

Alternatively, if we want just state-year data like in the previous blog post, we use the function create_stateyears()

We can add the variables with type D to the create_dyadyears() function and we can add the variables with type S to the create_stateyears() !

Focusing on the create_dyadyears() function, the arguments we can include are directed and mry.

The directed argument indicates whether we want directed or non-directed dyad relationship.

In a directed analysis, data include two observations (i.e. two rows) per dyad per year (such as one for USA – Russia and another row for Russia – USA), but in a nondirected analysis, we include only one observation (one row) per dyad per year.

The mry argument indicates whether they want to extend the data to the most recently concluded calendar year – i.e. 2020 – or not (i.e. until the data was last available).

dyad_df <- create_dyadyears(directed = FALSE, mry = TRUE) %>%
  add_atop_alliance() %>%  
  add_nmc() %>%
  add_cow_trade() %>% 

I added dyadic variables for the

You can follow these links to check out the codebooks if you want more information about descriptions about each variable and how the data were collected!

The code comes with the COW code but I like adding the actual names also!

dyad_df$country_1 <- countrycode(dyad_df$ccode1, "cown", "")

With this dataframe, we can plot the CINC data of the top three superpowers, just looking at any variable that has a 1 at the end and only looking at the corresponding country_1!

According to our pals over at le Wikipedia, the Composite Index of National Capability (CINC) is a statistical measure of national power created by J. David Singer for the Correlates of War project in 1963. It uses an average of percentages of world totals in six different components (such as coal consumption, military expenditure and population). The components represent demographic, economic, and military strength

First, let’s choose some nice hex colors

pal <- c("China" = "#DE2910",
         "United States" = "#3C3B6E", 
         "Russia" = "#FFD900")

And then create the plot

dyad_df %>% 
 filter(country_1 == "Russia" | 
          country_1 == "United States" | 
          country_1 == "China") %>% 
  ggplot(aes(x = year, y = cinc1, group = as.factor(country_1))) +
  geom_line(aes(color = country_1)) +
  geom_line(aes(color = country_1), size = 2, alpha = 0.8) + 
  scale_color_manual(values =  pal) +

In PART 3, we will merge together our data with our variables from PART 1, look at some descriptive statistics and run some panel data regression analysis with our different variables!

Compare Irish census years with compareBars and csodata package in R

Packages we will need:


First, let’s download population data from the Irish census with the Central Statistics Office (CSO) API package, developed by Conor Crowley.

You can search for the data you want to analyse via R or you can go to the CSO website and browse around the site.

I prefer looking through the site because sometimes I stumble across a dataset I didn’t even think to look for!

Keep note of the code beside the red dot star symbol if you’re looking around for datasets.

Click here to check out the CRAN PDF for the CSO package.

You can search for keywords with cso_search_toc(). I want total population counts for the whole country.

cso_search_toc("total population")

We can download the variables we want by entering the code into the cso_get_data() function

irish_pop <- cso_get_data("EY007")

The EY007 code downloads population census data in both 2011 and 2016 at every age.

It needs a little bit of tidying to get it ready for graphing.

irish_pop %<>%  

First, we can be lazy and use the clean_names() function from the janitor package.

GIF by The Good Place - Find & Share on GIPHY

Next we can get rid of the rows that we don’t want with select().

Then we use the pivot_longer() function to turn the data.frame from wide to long and to turn the x2011 and x2016 variables into one year variable.

irish_pop %>% 
  filter(at_each_year_of_age == "Population") %>% 
  filter(sex == 'Both sexes') %>% 
  filter(age_last_birthday != "All ages") %>% 
  select(!statistic) %>% 
  select(!sex) %>% 
  select(!at_each_year_of_age) -> irish_wide

irish_wide %>% 
    names_to = "year", 
    values_to = "pop_count",
    values_drop_na = TRUE) %>% 
    mutate(year = as.factor(year)) -> irish_long

No we can create our pyramid chart with the pyramid_chart() from the ggcharts package. The first argument is the age category for both the 2011 and 2016 data. The second is the actual population counts for each year. Last, enter the group variable that indicates the year.

irish_long %>%   
  pyramid_chart(age_last_birthday, pop_count, year)

One problem with the pyramid chart is that it is difficult to discern any differences between the two years without really really examining each year.

One way to more easily see the differences with the compareBars function

The compareBars package created by David Ranzolin can help to simplify comparative bar charts! It’s a super simple function to use that does a lot of visualisation leg work under the hood!

First we need to pivot the data.frame back to wide format and then input the age, and then the two groups – x2011 and x2016 – in the compareBars() function.

We can add more labels and colors to customise the graph also!

irish_long %>% 
  pivot_wider(names_from = year, values_from = pop_count) %>% 
  compareBars(age_last_birthday, x2011, x2016, orientation = "horizontal",
              xLabel = "Population",
              yLabel = "Year",
              titleLabel = "Irish Populations",
              subtitleLabel = "Comparing 2011 and 2016",
              fontFamily = "Arial",
              compareVarFill1 = "#FE6D73",
              compareVarFill2 = "#17C3B2") 

We can see that under the age of four-ish, 2011 had more at the time. And again, there were people in their twenties in 2011 compared to 2016.

However, there are more older people in 2016 than in 2011.

Similar to above it is a bit busy! So we can create groups for every five age years categories and examine the broader trends with fewer horizontal bars.

First we want to remove the word “years” from the age variable and convert it to a numeric class variable. We can easily do this with the parse_number() function from the readr package

irish_wide %<>% 
mutate(age_num = readr::parse_number(as.character(age_last_birthday))) 

Next we can group the age years together into five year categories, zero to 5 years, 6 to 10 years et cetera.

We use the cut() function to divide the numeric age_num variable into equal groups. We use the seq() function and input age 0 to 100, in increments of 5.

irish_wide$age_group = cut(irish_wide$age_num, seq(0, 100, 5))

Next, we can use group_by() to calculate the sum of each population number in each five year category.

And finally, we use the distinct() function to remove the duplicated rows (i.e. we only want to keep the first row that gives us the five year category’s population count for each category.

irish_wide %<>% 
  group_by(age_group) %>% 
  mutate(five_year_2011 = sum(x2011)) %>% 
  mutate(five_year_2016 = sum(x2016)) %>% 
  distinct(five_year_2011, five_year_2016, .keep_all = TRUE)

Next plot the bar chart with the five year categories

compareBars(irish_wide, age_group, five_year_2011, five_year_2016, orientation = "horizontal",
              xLabel = "Population",
              yLabel = "Year",
              titleLabel = "Irish Populations",
              subtitleLabel = "Comparing 2011 and 2016",
              fontFamily = "Arial",
              compareVarFill1 = "#FE6D73",
              compareVarFill2 = "#17C3B2") 

irish_wide2 %>% 
  select(age_group, five_year_2011, five_year_2016) %>% 
             names_to = "year", 
             values_to = "pop_count",
             values_drop_na = TRUE) %>% 
  mutate(year = as.factor(year)) -> irishlong2

irishlong2 %>%   
  pyramid_chart(age_group, pop_count, year)

The Good Place Yes GIF by NBC - Find & Share on GIPHY

Interpret multicollinearity tests from the mctest package in R

Packages we will need :


The mctest package’s functions have many multicollinearity diagnostic tests for overall and individual multicollinearity. Additionally, the package can show which regressors may be the reason of for the collinearity problem in your model.

Click here to read the CRAN PDF for all the function arguments available.

So – as always – we first fit a model.

Given the amount of news we have had about elections in the news recently, let’s look at variables that capture different aspects of elections and see how they relate to scores of democracy. These different election components will probably overlap.

In fact, I suspect multicollinearity will be problematic with the variables I am looking at.

Click here for a previous blog post on Variance Inflation Factor (VIF) score, the easiest and fastest way to test for multicollinearity in R.

The variables in my model are:

  • emb_autonomy – the extent to which the election management body of the country has autonomy from the government to apply election laws and administrative rules impartially in national elections.
  • election_multiparty – the extent to which the elections involved real multiparty competition.
  • election_votebuy – the extent to which there was evidence of vote and/or turnout buying.
  • election_intimidate – the extent to which opposition candidates/parties/campaign workers subjected to repression, intimidation, violence, or harassment by the government, the ruling party, or their agents.
  • election_free – the extent to which the election was judged free and fair.

In this model the dependent variable is democracy score for each of the 178 countries in this dataset. The score measures the extent to which a country ensures responsiveness and accountability between leaders and citizens. This is when suffrage is extensive; political and civil society organizations can operate freely; governmental positions are clean and not marred by fraud, corruption or irregularities; and the chief executive of a country is selected directly or indirectly through elections.

election_model <- lm(democracy ~ ., data = election_df)
stargazer(election_model, type = "text")

However, I suspect these variables suffer from high multicollinearity. Usually your knowledge of the variables – and how they were operationalised – will give you a hunch. But it is good practice to check everytime, regardless.

The eigprop() function can be used to detect the existence of multicollinearity among regressors. The function computes eigenvalues, condition indices and variance decomposition proportions for each of the regression coefficients in my election model.

To check the linear dependencies associated with the corresponding eigenvalue, the eigprop compares variance proportion with threshold value (default is 0.5) and displays the proportions greater than given threshold from each row and column, if any.

So first, let’s run the overall multicollinearity test with the eigprop() function :


If many of the Eigenvalues are near to 0, this indicates that there is multicollinearity.

Unfortunately, the phrase “near to” is not a clear numerical threshold. So we can look next door to the Condition Index score in the next column.

This takes the Eigenvalue index and takes a square root of the ratio of the largest eigenvalue (dimension 1) over the eigenvalue of the dimension.

Condition Index values over 10 risk multicollinearity problems.

In our model, we see the last variable – the extent to which an election is free and fair – suffers from high multicollinearity with other regressors in the model. The Eigenvalue is close to zero and the Condition Index (CI) is near 10. Maybe we can consider dropping this variable, if our research theory allows its.

Another battery of tests that the mctest package offers is the imcdiag( ) function. This looks at individual multicollinearity. That is, when we add or subtract individual variables from the model.


A value of 1 means that the predictor is not correlated with other variables.  As in a previous blog post on Variance Inflation Factor (VIF) score, we want low scores. Scores over 5 are moderately multicollinear. Scores over 10 are very problematic.

And, once again, we see the last variable is HIGHLY problematic, with a score of 14.7. However, all of the VIF scores are not very good.

The Tolerance (TOL) score is related to the VIF score; it is the reciprocal of VIF.

The Wi score is calculated by the Farrar Wi, which an F-test for locating the regressors which are collinear with others and it makes use of multiple correlation coefficients among regressors. Higher scores indicate more problematic multicollinearity.

The Leamer score is measured by Leamer’s Method : calculating the square root of the ratio of variances of estimated coefficients when estimated without and with the other regressors. Lower scores indicate more problematic multicollinearity.

The CVIF score is calculated by evaluating the impact of the correlation among regressors in the variance of the OLSEs. Higher scores indicate more problematic multicollinearity.

The Klein score is calculated by Klein’s Rule, which argues that if Rj from any one of the models minus one regressor is greater than the overall R2 (obtained from the regression of y on all the regressors) then multicollinearity may be troublesome. All scores are 0, which means that the R2 score of any model minus one regression is not greater than the R2 with full model.

Click here to read the mctest paper by its authors – Imdadullah et al. (2016) – that discusses all of the mathematics behind all of the tests in the package.

In conclusion, my model suffers from multicollinearity so I will need to drop some variables or rethink what I am trying to measure.

Click here to run Stepwise regression analysis and see which variables we can drop and come up with a more parsimonious model (the first suspect I would drop would be the free and fair elections variable)

Perhaps, I am capturing the same concept in many variables. Therefore I can run Principal Component Analysis (PCA) and create a new index that covers all of these electoral features.

Next blog will look at running PCA in R and examining the components we can extract.


Imdadullah, M., Aslam, M., & Altaf, S. (2016). mctest: An R Package for Detection of Collinearity among Regressors. R J.8(2), 495.

Check linear regression assumptions with gvlma package in R

Packages we will need:


gvlma stands for Global Validation of Linear Models Assumptions. See Peña and Slate’s (2006) paper on the package if you want to check out the math!

Linear regression analysis rests on many MANY assumptions. If we ignore them, and these assumptions are not met, we will not be able to trust that the regression results are true.

Luckily, R has many packages that can do a lot of the heavy lifting for us. We can check assumptions of our linear regression with a simple function.

So first, fit a simple regression model:

 summary(car_model <- lm(mpg ~ wt, data = mtcars)) 

We then feed our car_model into the gvlma() function:

gvlma_object <- gvlma(car_model)
  • Global Stat checks whether the relationship between the dependent and independent relationship roughly linear. We can see that the assumption is met.
  • Skewness and kurtosis assumptions show that the distribution of the residuals are normal.

  • Link function checks to see if the dependent variable is continuous or categorical. Our variable is continuous.

  • Heteroskedasticity assumption means the error variance is equally random and we have homoskedasticity!

Often the best way to check these assumptions is to plot them out and look at them in graph form.

Next we can plot out the model assumptions:


The relationship is a negative linear relationship between the two variables.

This scatterplot of residuals on the y axis and fitted values (estimated responses) on the x axis. The plot is used to detect non-linearity, unequal error variances, and outliers.

As explained in this Penn State webpage on interpreting residuals versus fitted plots:

  • The residuals “bounce randomly” around the 0 line. This suggests that the assumption that the relationship is linear is reasonable.
  • The residuals roughly form a “horizontal band” around the 0 line. This suggests that the variances of the error terms are equal.
  • No one residual “stands out” from the basic random pattern of residuals. This suggests that there are no outliers.

In this histograpm of standardised residuals, we see they are relatively normal-ish (not too skewed, and there is a single peak).

Next, the normal probability standardized residuals plot, Q-Q plot of sample (y axis) versus theoretical quantiles (x axis). The points do not deviate too far from the line, and so we can visually see how the residuals are normally distributed.

Click here to check out the CRAN pdf for the gvlma package.


Peña, E. A., & Slate, E. H. (2006). Global validation of linear model assumptions. Journal of the American Statistical Association101(473), 341-354.