TidyTuesday: Global Plastic Waste Management

A few weeks ago I began participating in R’s community TidyTuesday; a community-based data visualization challenge, where a new dataset is released on Tuesday and participants are invited to create visualizations in the tidyverse. I’ve only participated a few times, but have learned so much already from seeing others’ figures and analysis routes, following along with code, and getting feedback. Twitter proves once again to be an excellent learning tool.

This past week’s dataset looked at global plastic waste (mis)management. Below I provide some of the code and figures I produced in exploring this data. As always, I wish the dataset provided us with even more information to wade through. Although, part of the fun is coming up with meaningful analysis from seemingly few variables. My code is available here.

In this dataset we find data about global plastic waste disposal in 2010. We also get information about county 2011 GDP, and coastal and total population according to Gapminder.

In looking at the distributions in the data, I noticed that there were around 50 missing values for several of the variables related to plastic waste. I explored a little bit the population and GDP attributes of these countries compared to others, and found that most of these countries with missing information fall in the 50th percentile for GDP. Let’s take a look at some of the data.

This figure also gives us some information about the distribution of population and GDP across the world. There are some outliers in both, with significantly large population and GDP, not shown in the scatter plot (China, India, and the USA).

Next I started to look at the data on waste, and specifically the relationship between waste management and GDP/population. “Mismanaged waste” is defined by Our World in Data, the data source, as “material which is either littered or inadequately disposed”. First I plotted some scatterplots to get a feel for the association (if any). Below, we can see that the trend if such that richer countries have less waste per capita.

Now I want to present the above information as a map, highlighting the top three countries (with regard to population and GDP) USA, China, and India.

Finally, within each country, what percentage of their total plastic waste is being mismanaged? Does this also correspond to a country’s wealth? I decided to look at a scatterplot with overlaid boxplots across continents and levels of wealth (percentiles of GDP). It looks like the higher a country’s GDP per capita, the less of its plastic is being mismanaged.

Alyssa M. Vanderbeek
MS student in Biostatistics

My research interests include drug development, clinical trial design, R programming, and data analysis and visualization.